diff --git a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp index 4fb5cb066be7c..c2199fd587bea 100644 --- a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp +++ b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp @@ -199,7 +199,7 @@ static unsigned macToMad(unsigned Opc) { case AMDGPU::V_FMAC_F16_e64: return AMDGPU::V_FMA_F16_gfx9_e64; case AMDGPU::V_FMAC_F16_fake16_e64: - return AMDGPU::V_FMA_F16_gfx9_e64; + return AMDGPU::V_FMA_F16_gfx9_fake16_e64; case AMDGPU::V_FMAC_LEGACY_F32_e64: return AMDGPU::V_FMA_LEGACY_F32_e64; case AMDGPU::V_FMAC_F64_e64: diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp index f97ea40caa670..692e2867ca88c 100644 --- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp +++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp @@ -3805,6 +3805,36 @@ static void updateLiveVariables(LiveVariables *LV, MachineInstr &MI, } } +static unsigned getNewFMAInst(const GCNSubtarget &ST, unsigned Opc) { + switch (Opc) { + case AMDGPU::V_MAC_F16_e32: + case AMDGPU::V_MAC_F16_e64: + return AMDGPU::V_MAD_F16_e64; + case AMDGPU::V_MAC_F32_e32: + case AMDGPU::V_MAC_F32_e64: + return AMDGPU::V_MAD_F32_e64; + case AMDGPU::V_MAC_LEGACY_F32_e32: + case AMDGPU::V_MAC_LEGACY_F32_e64: + return AMDGPU::V_MAD_LEGACY_F32_e64; + case AMDGPU::V_FMAC_LEGACY_F32_e32: + case AMDGPU::V_FMAC_LEGACY_F32_e64: + return AMDGPU::V_FMA_LEGACY_F32_e64; + case AMDGPU::V_FMAC_F16_e32: + case AMDGPU::V_FMAC_F16_e64: + case AMDGPU::V_FMAC_F16_fake16_e64: + return ST.hasTrue16BitInsts() ? AMDGPU::V_FMA_F16_gfx9_fake16_e64 + : AMDGPU::V_FMA_F16_gfx9_e64; + case AMDGPU::V_FMAC_F32_e32: + case AMDGPU::V_FMAC_F32_e64: + return AMDGPU::V_FMA_F32_e64; + case AMDGPU::V_FMAC_F64_e32: + case AMDGPU::V_FMAC_F64_e64: + return AMDGPU::V_FMA_F64_e64; + default: + llvm_unreachable("invalid instruction"); + } +} + MachineInstr *SIInstrInfo::convertToThreeAddress(MachineInstr &MI, LiveVariables *LV, LiveIntervals *LIS) const { @@ -4040,14 +4070,8 @@ MachineInstr *SIInstrInfo::convertToThreeAddress(MachineInstr &MI, if (Src0Literal && !ST.hasVOP3Literal()) return nullptr; - unsigned NewOpc = IsFMA ? IsF16 ? AMDGPU::V_FMA_F16_gfx9_e64 - : IsF64 ? AMDGPU::V_FMA_F64_e64 - : IsLegacy - ? AMDGPU::V_FMA_LEGACY_F32_e64 - : AMDGPU::V_FMA_F32_e64 - : IsF16 ? AMDGPU::V_MAD_F16_e64 - : IsLegacy ? AMDGPU::V_MAD_LEGACY_F32_e64 - : AMDGPU::V_MAD_F32_e64; + unsigned NewOpc = getNewFMAInst(ST, Opc); + if (pseudoToMCOpcode(NewOpc) == -1) return nullptr; @@ -9294,6 +9318,7 @@ static bool isRenamedInGFX9(int Opcode) { case AMDGPU::V_DIV_FIXUP_F16_gfx9_e64: case AMDGPU::V_DIV_FIXUP_F16_gfx9_fake16_e64: case AMDGPU::V_FMA_F16_gfx9_e64: + case AMDGPU::V_FMA_F16_gfx9_fake16_e64: case AMDGPU::V_INTERP_P2_F16: case AMDGPU::V_MAD_F16_e64: case AMDGPU::V_MAD_U16_e64: diff --git a/llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp b/llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp index 42df4576a774d..979812e07fc3f 100644 --- a/llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp +++ b/llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp @@ -455,6 +455,7 @@ void SIShrinkInstructions::shrinkMadFma(MachineInstr &MI) const { break; case AMDGPU::V_FMA_F16_e64: case AMDGPU::V_FMA_F16_gfx9_e64: + case AMDGPU::V_FMA_F16_gfx9_fake16_e64: NewOpcode = ST->hasTrue16BitInsts() ? AMDGPU::V_FMAAK_F16_fake16 : AMDGPU::V_FMAAK_F16; break; @@ -484,6 +485,7 @@ void SIShrinkInstructions::shrinkMadFma(MachineInstr &MI) const { break; case AMDGPU::V_FMA_F16_e64: case AMDGPU::V_FMA_F16_gfx9_e64: + case AMDGPU::V_FMA_F16_gfx9_fake16_e64: NewOpcode = ST->hasTrue16BitInsts() ? AMDGPU::V_FMAMK_F16_fake16 : AMDGPU::V_FMAMK_F16; break; @@ -956,7 +958,8 @@ bool SIShrinkInstructions::run(MachineFunction &MF) { MI.getOpcode() == AMDGPU::V_FMA_F32_e64 || MI.getOpcode() == AMDGPU::V_MAD_F16_e64 || MI.getOpcode() == AMDGPU::V_FMA_F16_e64 || - MI.getOpcode() == AMDGPU::V_FMA_F16_gfx9_e64) { + MI.getOpcode() == AMDGPU::V_FMA_F16_gfx9_e64 || + MI.getOpcode() == AMDGPU::V_FMA_F16_gfx9_fake16_e64) { shrinkMadFma(MI); continue; } diff --git a/llvm/lib/Target/AMDGPU/VOP3Instructions.td b/llvm/lib/Target/AMDGPU/VOP3Instructions.td index 22e457674c07a..237f6cd817165 100644 --- a/llvm/lib/Target/AMDGPU/VOP3Instructions.td +++ b/llvm/lib/Target/AMDGPU/VOP3Instructions.td @@ -340,7 +340,7 @@ let FPDPRounding = 1 in { let SubtargetPredicate = isGFX9Plus in { defm V_DIV_FIXUP_F16_gfx9 : VOP3Inst_t16 <"v_div_fixup_f16_gfx9", VOP_F16_F16_F16_F16, AMDGPUdiv_fixup>; - defm V_FMA_F16_gfx9 : VOP3Inst <"v_fma_f16_gfx9", VOP3_Profile, any_fma>; + defm V_FMA_F16_gfx9 : VOP3Inst_t16 <"v_fma_f16_gfx9", VOP_F16_F16_F16_F16, any_fma>; } // End SubtargetPredicate = isGFX9Plus } // End FPDPRounding = 1 @@ -1708,7 +1708,7 @@ defm V_PERM_B32 : VOP3_Realtriple_gfx11_gfx12<0x244>; defm V_XAD_U32 : VOP3_Realtriple_gfx11_gfx12<0x245>; defm V_LSHL_ADD_U32 : VOP3_Realtriple_gfx11_gfx12<0x246>; defm V_ADD_LSHL_U32 : VOP3_Realtriple_gfx11_gfx12<0x247>; -defm V_FMA_F16 : VOP3_Realtriple_with_name_gfx11_gfx12<0x248, "V_FMA_F16_gfx9", "v_fma_f16">; +defm V_FMA_F16 : VOP3_Realtriple_t16_and_fake16_gfx11_gfx12<0x248, "v_fma_f16", "V_FMA_F16_gfx9">; defm V_MIN3_F16 : VOP3Only_Realtriple_t16_and_fake16_gfx11<0x249, "v_min3_f16">; defm V_MIN3_I16 : VOP3_Realtriple_t16_and_fake16_gfx11_gfx12<0x24a, "v_min3_i16">; defm V_MIN3_U16 : VOP3_Realtriple_t16_and_fake16_gfx11_gfx12<0x24b, "v_min3_u16">; diff --git a/llvm/test/CodeGen/AMDGPU/fma.f16.ll b/llvm/test/CodeGen/AMDGPU/fma.f16.ll index 005e40159f61b..822d40f7349b0 100644 --- a/llvm/test/CodeGen/AMDGPU/fma.f16.ll +++ b/llvm/test/CodeGen/AMDGPU/fma.f16.ll @@ -5,6 +5,8 @@ ; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck %s -check-prefixes=GFX10,GFX10-GISEL ; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck %s -check-prefixes=GFX11,GFX11-SDAG ; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck %s -check-prefixes=GFX11,GFX11-GISEL +; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx1200 -verify-machineinstrs < %s | FileCheck %s -check-prefixes=GFX12,GFX12-SDAG +; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx1200 -verify-machineinstrs < %s | FileCheck %s -check-prefixes=GFX12,GFX12-GISEL declare half @llvm.fma.f16(half, half, half) declare half @llvm.maxnum.f16(half, half) @@ -27,6 +29,16 @@ define half @test_fma(half %x, half %y, half %z) { ; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) ; GFX11-NEXT: v_fma_f16 v0, v0, v1, v2 ; GFX11-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-LABEL: test_fma: +; GFX12: ; %bb.0: +; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-NEXT: s_wait_expcnt 0x0 +; GFX12-NEXT: s_wait_samplecnt 0x0 +; GFX12-NEXT: s_wait_bvhcnt 0x0 +; GFX12-NEXT: s_wait_kmcnt 0x0 +; GFX12-NEXT: v_fma_f16 v0, v0, v1, v2 +; GFX12-NEXT: s_setpc_b64 s[30:31] %r = call half @llvm.fma.f16(half %x, half %y, half %z) ret half %r } @@ -50,6 +62,16 @@ define half @test_fmac(half %x, half %y, half %z) { ; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) ; GFX11-NEXT: v_fmac_f16_e32 v0, v1, v2 ; GFX11-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-LABEL: test_fmac: +; GFX12: ; %bb.0: +; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-NEXT: s_wait_expcnt 0x0 +; GFX12-NEXT: s_wait_samplecnt 0x0 +; GFX12-NEXT: s_wait_bvhcnt 0x0 +; GFX12-NEXT: s_wait_kmcnt 0x0 +; GFX12-NEXT: v_fmac_f16_e32 v0, v1, v2 +; GFX12-NEXT: s_setpc_b64 s[30:31] %r = call half @llvm.fma.f16(half %y, half %z, half %x) ret half %r } @@ -81,6 +103,16 @@ define half @test_fmaak(half %x, half %y, half %z) { ; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) ; GFX11-NEXT: v_fmaak_f16 v0, v0, v1, 0x4200 ; GFX11-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-LABEL: test_fmaak: +; GFX12: ; %bb.0: +; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-NEXT: s_wait_expcnt 0x0 +; GFX12-NEXT: s_wait_samplecnt 0x0 +; GFX12-NEXT: s_wait_bvhcnt 0x0 +; GFX12-NEXT: s_wait_kmcnt 0x0 +; GFX12-NEXT: v_fmaak_f16 v0, v0, v1, 0x4200 +; GFX12-NEXT: s_setpc_b64 s[30:31] %r = call half @llvm.fma.f16(half %x, half %y, half 0xH4200) ret half %r } @@ -112,6 +144,16 @@ define half @test_fmamk(half %x, half %y, half %z) { ; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) ; GFX11-NEXT: v_fmamk_f16 v0, v0, 0x4200, v2 ; GFX11-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-LABEL: test_fmamk: +; GFX12: ; %bb.0: +; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-NEXT: s_wait_expcnt 0x0 +; GFX12-NEXT: s_wait_samplecnt 0x0 +; GFX12-NEXT: s_wait_bvhcnt 0x0 +; GFX12-NEXT: s_wait_kmcnt 0x0 +; GFX12-NEXT: v_fmamk_f16 v0, v0, 0x4200, v2 +; GFX12-NEXT: s_setpc_b64 s[30:31] %r = call half @llvm.fma.f16(half %x, half 0xH4200, half %z) ret half %r } @@ -193,6 +235,42 @@ define i32 @test_D139469_f16(half %arg) { ; GFX11-GISEL-NEXT: s_delay_alu instid0(SALU_CYCLE_1) ; GFX11-GISEL-NEXT: v_cndmask_b32_e64 v0, 0, 1, s0 ; GFX11-GISEL-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-SDAG-LABEL: test_D139469_f16: +; GFX12-SDAG: ; %bb.0: ; %bb +; GFX12-SDAG-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-SDAG-NEXT: s_wait_expcnt 0x0 +; GFX12-SDAG-NEXT: s_wait_samplecnt 0x0 +; GFX12-SDAG-NEXT: s_wait_bvhcnt 0x0 +; GFX12-SDAG-NEXT: s_wait_kmcnt 0x0 +; GFX12-SDAG-NEXT: v_mov_b32_e32 v1, 0x211e +; GFX12-SDAG-NEXT: v_mul_f16_e32 v2, 0x291e, v0 +; GFX12-SDAG-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_1) +; GFX12-SDAG-NEXT: v_fmac_f16_e32 v1, 0x291e, v0 +; GFX12-SDAG-NEXT: v_min_num_f16_e32 v0, v2, v1 +; GFX12-SDAG-NEXT: s_delay_alu instid0(VALU_DEP_1) +; GFX12-SDAG-NEXT: v_cmp_gt_f16_e32 vcc_lo, 0, v0 +; GFX12-SDAG-NEXT: v_cndmask_b32_e64 v0, 0, 1, vcc_lo +; GFX12-SDAG-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-GISEL-LABEL: test_D139469_f16: +; GFX12-GISEL: ; %bb.0: ; %bb +; GFX12-GISEL-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-GISEL-NEXT: s_wait_expcnt 0x0 +; GFX12-GISEL-NEXT: s_wait_samplecnt 0x0 +; GFX12-GISEL-NEXT: s_wait_bvhcnt 0x0 +; GFX12-GISEL-NEXT: s_wait_kmcnt 0x0 +; GFX12-GISEL-NEXT: v_mov_b32_e32 v1, 0x211e +; GFX12-GISEL-NEXT: v_mul_f16_e32 v2, 0x291e, v0 +; GFX12-GISEL-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2) +; GFX12-GISEL-NEXT: v_fmac_f16_e32 v1, 0x291e, v0 +; GFX12-GISEL-NEXT: v_cmp_gt_f16_e32 vcc_lo, 0, v2 +; GFX12-GISEL-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_1) +; GFX12-GISEL-NEXT: v_cmp_gt_f16_e64 s0, 0, v1 +; GFX12-GISEL-NEXT: s_or_b32 s0, vcc_lo, s0 +; GFX12-GISEL-NEXT: s_wait_alu 0xfffe +; GFX12-GISEL-NEXT: v_cndmask_b32_e64 v0, 0, 1, s0 +; GFX12-GISEL-NEXT: s_setpc_b64 s[30:31] bb: %i = fmul contract half %arg, 0xH291E %i1 = fcmp olt half %i, 0xH0000 @@ -306,6 +384,55 @@ define <2 x i32> @test_D139469_v2f16(<2 x half> %arg) { ; GFX11-GISEL-NEXT: s_delay_alu instid0(SALU_CYCLE_1) ; GFX11-GISEL-NEXT: v_cndmask_b32_e64 v1, 0, 1, s0 ; GFX11-GISEL-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-SDAG-LABEL: test_D139469_v2f16: +; GFX12-SDAG: ; %bb.0: ; %bb +; GFX12-SDAG-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-SDAG-NEXT: s_wait_expcnt 0x0 +; GFX12-SDAG-NEXT: s_wait_samplecnt 0x0 +; GFX12-SDAG-NEXT: s_wait_bvhcnt 0x0 +; GFX12-SDAG-NEXT: s_wait_kmcnt 0x0 +; GFX12-SDAG-NEXT: s_movk_i32 s0, 0x211e +; GFX12-SDAG-NEXT: v_pk_mul_f16 v1, 0x291e, v0 op_sel_hi:[0,1] +; GFX12-SDAG-NEXT: s_wait_alu 0xfffe +; GFX12-SDAG-NEXT: v_pk_fma_f16 v0, 0x291e, v0, s0 op_sel_hi:[0,1,0] +; GFX12-SDAG-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1) +; GFX12-SDAG-NEXT: v_pk_min_num_f16 v0, v1, v0 +; GFX12-SDAG-NEXT: v_lshrrev_b32_e32 v1, 16, v0 +; GFX12-SDAG-NEXT: v_cmp_gt_f16_e32 vcc_lo, 0, v0 +; GFX12-SDAG-NEXT: v_cndmask_b32_e64 v0, 0, 1, vcc_lo +; GFX12-SDAG-NEXT: s_delay_alu instid0(VALU_DEP_3) +; GFX12-SDAG-NEXT: v_cmp_gt_f16_e32 vcc_lo, 0, v1 +; GFX12-SDAG-NEXT: v_cndmask_b32_e64 v1, 0, 1, vcc_lo +; GFX12-SDAG-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-GISEL-LABEL: test_D139469_v2f16: +; GFX12-GISEL: ; %bb.0: ; %bb +; GFX12-GISEL-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-GISEL-NEXT: s_wait_expcnt 0x0 +; GFX12-GISEL-NEXT: s_wait_samplecnt 0x0 +; GFX12-GISEL-NEXT: s_wait_bvhcnt 0x0 +; GFX12-GISEL-NEXT: s_wait_kmcnt 0x0 +; GFX12-GISEL-NEXT: v_mov_b32_e32 v1, 0x211e211e +; GFX12-GISEL-NEXT: v_pk_mul_f16 v2, 0x291e291e, v0 +; GFX12-GISEL-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2) +; GFX12-GISEL-NEXT: v_pk_fma_f16 v0, 0x291e291e, v0, v1 +; GFX12-GISEL-NEXT: v_lshrrev_b32_e32 v1, 16, v2 +; GFX12-GISEL-NEXT: v_cmp_gt_f16_e32 vcc_lo, 0, v2 +; GFX12-GISEL-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(SKIP_1) | instid1(VALU_DEP_4) +; GFX12-GISEL-NEXT: v_lshrrev_b32_e32 v3, 16, v0 +; GFX12-GISEL-NEXT: v_cmp_gt_f16_e64 s0, 0, v0 +; GFX12-GISEL-NEXT: v_cmp_gt_f16_e64 s1, 0, v1 +; GFX12-GISEL-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(VALU_DEP_3) +; GFX12-GISEL-NEXT: v_cmp_gt_f16_e64 s2, 0, v3 +; GFX12-GISEL-NEXT: s_or_b32 s0, vcc_lo, s0 +; GFX12-GISEL-NEXT: s_wait_alu 0xfffe +; GFX12-GISEL-NEXT: v_cndmask_b32_e64 v0, 0, 1, s0 +; GFX12-GISEL-NEXT: s_delay_alu instid0(VALU_DEP_2) +; GFX12-GISEL-NEXT: s_or_b32 s0, s1, s2 +; GFX12-GISEL-NEXT: s_wait_alu 0xfffe +; GFX12-GISEL-NEXT: v_cndmask_b32_e64 v1, 0, 1, s0 +; GFX12-GISEL-NEXT: s_setpc_b64 s[30:31] bb: %i = fmul contract <2 x half> %arg, %i1 = fcmp olt <2 x half> %i, diff --git a/llvm/test/CodeGen/AMDGPU/gfx11-twoaddr-fma.mir b/llvm/test/CodeGen/AMDGPU/gfx11-twoaddr-fma.mir index cefd24032871f..85c6577893396 100644 --- a/llvm/test/CodeGen/AMDGPU/gfx11-twoaddr-fma.mir +++ b/llvm/test/CodeGen/AMDGPU/gfx11-twoaddr-fma.mir @@ -18,7 +18,7 @@ body: | ; GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY [[DEF]].sub1 ; GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY [[DEF]].sub0 ; GFX11-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 1078523331, implicit $exec - ; GFX11-NEXT: [[V_FMA_F16_gfx9_e64_:%[0-9]+]]:vgpr_32 = V_FMA_F16_gfx9_e64 0, killed [[COPY1]], 0, [[V_MOV_B32_e32_]], 0, killed [[COPY]], 0, 0, 0, implicit $mode, implicit $exec + ; GFX11-NEXT: [[V_FMA_F16_gfx9_fake16_e64_:%[0-9]+]]:vgpr_32 = V_FMA_F16_gfx9_fake16_e64 0, killed [[COPY1]], 0, [[V_MOV_B32_e32_]], 0, killed [[COPY]], 0, 0, 0, implicit $mode, implicit $exec %0 = IMPLICIT_DEF %1 = COPY %0.sub1 %2 = COPY %0.sub0 @@ -43,7 +43,7 @@ body: | ; GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY [[DEF]].sub1 ; GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY [[DEF]].sub0 ; GFX11-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 1078523331, implicit $exec - ; GFX11-NEXT: [[V_FMA_F16_gfx9_e64_:%[0-9]+]]:vgpr_32 = V_FMA_F16_gfx9_e64 0, [[COPY1]], 0, killed [[V_MOV_B32_e32_]], 0, killed [[COPY]], 0, 0, 0, implicit $mode, implicit $exec + ; GFX11-NEXT: [[V_FMA_F16_gfx9_fake16_e64_:%[0-9]+]]:vgpr_32 = V_FMA_F16_gfx9_fake16_e64 0, [[COPY1]], 0, killed [[V_MOV_B32_e32_]], 0, killed [[COPY]], 0, 0, 0, implicit $mode, implicit $exec %0 = IMPLICIT_DEF %1 = COPY %0.sub1 %2 = COPY %0.sub0 @@ -68,7 +68,7 @@ body: | ; GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY [[DEF]].sub0 ; GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY [[DEF]].sub1 ; GFX11-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 1078523331, implicit $exec - ; GFX11-NEXT: [[V_FMA_F16_gfx9_e64_:%[0-9]+]]:vgpr_32 = V_FMA_F16_gfx9_e64 0, killed [[COPY]], 0, [[COPY1]], 0, [[V_MOV_B32_e32_]], 0, 0, 0, implicit $mode, implicit $exec + ; GFX11-NEXT: [[V_FMA_F16_gfx9_fake16_e64_:%[0-9]+]]:vgpr_32 = V_FMA_F16_gfx9_fake16_e64 0, killed [[COPY]], 0, [[COPY1]], 0, [[V_MOV_B32_e32_]], 0, 0, 0, implicit $mode, implicit $exec %0 = IMPLICIT_DEF %1 = COPY %0.sub0 %2 = COPY %0.sub1 @@ -90,7 +90,7 @@ body: | ; GFX11-NEXT: {{ $}} ; GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY killed $vgpr0 ; GFX11-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 49664, implicit $exec - ; GFX11-NEXT: [[V_FMA_F16_gfx9_e64_:%[0-9]+]]:vgpr_32 = V_FMA_F16_gfx9_e64 0, 16384, 0, killed [[COPY]], 0, [[V_MOV_B32_e32_]], 0, 0, 0, implicit $mode, implicit $exec + ; GFX11-NEXT: [[V_FMA_F16_gfx9_fake16_e64_:%[0-9]+]]:vgpr_32 = V_FMA_F16_gfx9_fake16_e64 0, 16384, 0, killed [[COPY]], 0, [[V_MOV_B32_e32_]], 0, 0, 0, implicit $mode, implicit $exec ; GFX11-NEXT: S_ENDPGM 0 %0:vgpr_32 = COPY killed $vgpr0 diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s index 628edf7400576..fc8d2bdc0540a 100644 --- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s +++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s @@ -2231,53 +2231,77 @@ v_fma_dx9_zero_f32 v5, -src_scc, |vcc_lo|, -1 mul:4 v_fma_dx9_zero_f32 v255, -|0xaf123456|, -|vcc_hi|, null clamp div:2 // GFX11: v_fma_dx9_zero_f32 v255, -|0xaf123456|, -|vcc_hi|, null clamp div:2 ; encoding: [0xff,0x83,0x09,0xd6,0xff,0xd6,0xf0,0x79,0x56,0x34,0x12,0xaf] -v_fma_f16 v5, v1, v2, s3 -// GFX11: v_fma_f16 v5, v1, v2, s3 ; encoding: [0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00] +v_fma_f16 v5.l, v1.l, v2.l, s3 +// GFX11: v_fma_f16 v5.l, v1.l, v2.l, s3 ; encoding: [0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00] -v_fma_f16 v5, v255, s2, s105 -// GFX11: v_fma_f16 v5, v255, s2, s105 ; encoding: [0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01] +v_fma_f16 v5.l, v255.l, s2, s105 +// GFX11: v_fma_f16 v5.l, v255.l, s2, s105 ; encoding: [0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01] -v_fma_f16 v5, s1, v255, exec_hi -// GFX11: v_fma_f16 v5, s1, v255, exec_hi ; encoding: [0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01] +v_fma_f16 v5.l, s1, v255.l, exec_hi +// GFX11: v_fma_f16 v5.l, s1, v255.l, exec_hi ; encoding: [0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01] -v_fma_f16 v5, s105, s105, exec_lo -// GFX11: v_fma_f16 v5, s105, s105, exec_lo ; encoding: [0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01] +v_fma_f16 v5.l, s105, s105, exec_lo +// GFX11: v_fma_f16 v5.l, s105, s105, exec_lo ; encoding: [0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01] -v_fma_f16 v5, vcc_lo, ttmp15, v3 -// GFX11: v_fma_f16 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04] +v_fma_f16 v5.l, vcc_lo, ttmp15, v3.l +// GFX11: v_fma_f16 v5.l, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04] -v_fma_f16 v5, vcc_hi, 0xfe0b, v255 -// GFX11: v_fma_f16 v5, vcc_hi, 0xfe0b, v255 ; encoding: [0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] +v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.l +// GFX11: v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.l ; encoding: [0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] -v_fma_f16 v5, -|ttmp15|, -|src_scc|, -|ttmp15| -// GFX11: v_fma_f16 v5, -|ttmp15|, -|src_scc|, -|ttmp15| ; encoding: [0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1] +v_fma_f16 v5.l, -|ttmp15|, -|src_scc|, -|ttmp15| +// GFX11: v_fma_f16 v5.l, -|ttmp15|, -|src_scc|, -|ttmp15| ; encoding: [0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1] -v_fma_f16 v5, m0, 0.5, m0 -// GFX11: v_fma_f16 v5, m0, 0.5, m0 ; encoding: [0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01] +v_fma_f16 v5.l, m0, 0.5, m0 +// GFX11: v_fma_f16 v5.l, m0, 0.5, m0 ; encoding: [0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01] -v_fma_f16 v5, |exec_lo|, -1, vcc_hi -// GFX11: v_fma_f16 v5, |exec_lo|, -1, vcc_hi ; encoding: [0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01] +v_fma_f16 v5.l, |exec_lo|, -1, vcc_hi +// GFX11: v_fma_f16 v5.l, |exec_lo|, -1, vcc_hi ; encoding: [0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01] -v_fma_f16 v5, -|exec_hi|, null, -|vcc_lo| op_sel:[1,1,1,1] -// GFX11: v_fma_f16 v5, -|exec_hi|, null, -|vcc_lo| op_sel:[1,1,1,1] ; encoding: [0x05,0x7d,0x48,0xd6,0x7f,0xf8,0xa8,0xa1] +v_fma_f16 v5.h, -|exec_hi|, null, -|vcc_lo| op_sel:[1,1,1,1] +// GFX11: v_fma_f16 v5.h, -|exec_hi|, null, -|vcc_lo| op_sel:[1,1,1,1] ; encoding: [0x05,0x7d,0x48,0xd6,0x7f,0xf8,0xa8,0xa1] -v_fma_f16 v5, null, exec_lo, -|0xfe0b| op_sel:[0,0,0,0] -// GFX11: v_fma_f16 v5, null, exec_lo, -|0xfe0b| ; encoding: [0x05,0x04,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00] +v_fma_f16 v5.l, null, exec_lo, -|0xfe0b| +// GFX11: v_fma_f16 v5.l, null, exec_lo, -|0xfe0b| ; encoding: [0x05,0x04,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00] -v_fma_f16 v5, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] -// GFX11: v_fma_f16 v5, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] ; encoding: [0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3] +v_fma_f16 v5.l, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] +// GFX11: v_fma_f16 v5.l, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] ; encoding: [0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3] -v_fma_f16 v5, 0.5, -m0, 0.5 op_sel:[0,1,0,0] -// GFX11: v_fma_f16 v5, 0.5, -m0, 0.5 op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43] +v_fma_f16 v5.l, 0.5, -m0, 0.5 op_sel:[0,1,0,0] +// GFX11: v_fma_f16 v5.l, 0.5, -m0, 0.5 op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43] -v_fma_f16 v5, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] -// GFX11: v_fma_f16 v5, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] ; encoding: [0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23] +v_fma_f16 v5.l, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] +// GFX11: v_fma_f16 v5.l, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] ; encoding: [0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23] -v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp -// GFX11: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] +v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null clamp +// GFX11: v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] -v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp div:2 -// GFX11: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp div:2 ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x79,0x0b,0xfe,0x00,0x00] +v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp div:2 +// GFX11: v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp div:2 ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x79,0x0b,0xfe,0x00,0x00] + +v_fma_f16 v5.l, v255.h, s2, s105 +// GFX11: v_fma_f16 v5.l, v255.h, s2, s105 op_sel:[1,0,0,0] ; encoding: [0x05,0x08,0x48,0xd6,0xff,0x05,0xa4,0x01] + +v_fma_f16 v5.l, s1, v255.h, exec_hi +// GFX11: v_fma_f16 v5.l, s1, v255.h, exec_hi op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0x01,0xfe,0xff,0x01] + +v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.h +// GFX11: v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] + +v_fma_f16 v5.l, -|exec_hi|, null, -|vcc_lo| +// GFX11: v_fma_f16 v5.l, -|exec_hi|, null, -|vcc_lo| ; encoding: [0x05,0x05,0x48,0xd6,0x7f,0xf8,0xa8,0xa1] + +v_fma_f16 v5.l, -1, -|exec_hi|, -|src_scc| +// GFX11: v_fma_f16 v5.l, -1, -|exec_hi|, -|src_scc| ; encoding: [0x05,0x06,0x48,0xd6,0xc1,0xfe,0xf4,0xc3] + +v_fma_f16 v5.l, 0.5, -m0, 0.5 +// GFX11: v_fma_f16 v5.l, 0.5, -m0, 0.5 ; encoding: [0x05,0x00,0x48,0xd6,0xf0,0xfa,0xc0,0x43] + +v_fma_f16 v5.l, -src_scc, |vcc_lo|, -1 +// GFX11: v_fma_f16 v5.l, -src_scc, |vcc_lo|, -1 ; encoding: [0x05,0x02,0x48,0xd6,0xfd,0xd4,0x04,0x23] + +v_fma_f16 v255.l, -|0xfe0b|, -|vcc_hi|, null clamp div:2 +// GFX11: v_fma_f16 v255.l, -|0xfe0b|, -|vcc_hi|, null clamp div:2 ; encoding: [0xff,0x83,0x48,0xd6,0xff,0xd6,0xf0,0x79,0x0b,0xfe,0x00,0x00] v_fma_f32 v5, v1, v2, s3 // GFX11: v_fma_f32 v5, v1, v2, s3 ; encoding: [0x05,0x00,0x13,0xd6,0x01,0x05,0x0e,0x00] diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s index acbdcfc39d983..f71569433d326 100644 --- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s +++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s @@ -1508,47 +1508,83 @@ v_div_fixup_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 row_xmask:0 row_mask:0x1 ban v_div_fixup_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1 // GFX11: v_div_fixup_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0xc7,0x54,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x05,0x30] -v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] -// GFX11: v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] -v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[0,1,2,3] -// GFX11: v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0xe4,0x00,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0xe4,0x00,0xff] -v_fma_f16_e64_dpp v5, v1, v2, v3 row_mirror -// GFX11: v_fma_f16_e64_dpp v5, v1, v2, v3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x40,0x01,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l row_mirror row_mask:0xf bank_mask:0xf +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x40,0x01,0xff] -v_fma_f16_e64_dpp v5, v1, v2, v255 row_half_mirror -// GFX11: v_fma_f16_e64_dpp v5, v1, v2, v255 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x41,0x01,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l row_half_mirror row_mask:0xf bank_mask:0xf +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x41,0x01,0xff] -v_fma_f16_e64_dpp v5, v1, v2, s105 row_shl:1 -// GFX11: v_fma_f16_e64_dpp v5, v1, v2, s105 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x01,0x01,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 row_shl:1 row_mask:0xf bank_mask:0xf +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x01,0x01,0xff] -v_fma_f16_e64_dpp v5, v1, v2, vcc_hi row_shl:15 -// GFX11: v_fma_f16_e64_dpp v5, v1, v2, vcc_hi row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi row_shl:15 +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff] -v_fma_f16_e64_dpp v5, v1, v2, vcc_lo row_shr:1 -// GFX11: v_fma_f16_e64_dpp v5, v1, v2, vcc_lo row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo row_shr:1 +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff] -v_fma_f16_e64_dpp v5, |v1|, v2, -ttmp15 row_shr:15 -// GFX11: v_fma_f16_e64_dpp v5, |v1|, v2, -ttmp15 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x01,0x48,0xd6,0xfa,0x04,0xee,0x81,0x01,0x1f,0x01,0xff] +v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -ttmp15 row_shr:15 row_mask:0xf bank_mask:0xf +// GFX11: v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -ttmp15 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x01,0x48,0xd6,0xfa,0x04,0xee,0x81,0x01,0x1f,0x01,0xff] -v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi row_ror:1 -// GFX11: v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x02,0x48,0xd6,0xfa,0x04,0xfe,0x41,0x01,0x21,0x01,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, exec_hi row_ror:1 row_mask:0xf bank_mask:0xf +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, exec_hi row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x02,0x48,0xd6,0xfa,0x04,0xfe,0x41,0x01,0x21,0x01,0xff] -v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| row_ror:15 -// GFX11: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x04,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] +v_fma_f16_e64_dpp v5.l, -v1.l, v2.l, |exec_lo| row_ror:15 row_mask:0xf bank_mask:0xf +// GFX11: v_fma_f16_e64_dpp v5.l, -v1.l, v2.l, |exec_lo| row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x04,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] -v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null row_share:0 row_mask:0xf bank_mask:0xf -// GFX11: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x03,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] +v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.l|, null row_share:0 row_mask:0xf bank_mask:0xf +// GFX11: v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.l|, null row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x03,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] -v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| row_share:15 row_mask:0x0 bank_mask:0x1 -// GFX11: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x05,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] +v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.l, -|-1| row_share:15 row_mask:0x0 bank_mask:0x1 +// GFX11: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.l, -|-1| row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x05,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] -v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0 -// GFX11: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x05,0x06,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x09,0x13] +v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x05,0x06,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x09,0x13] -v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1 -// GFX11: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x87,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x05,0x30] +v_fma_f16_e64_dpp v255.l, -|v255.l|, -|v255.l|, -|src_scc| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 +// GFX11: v_fma_f16_e64_dpp v255.l, -|v255.l|, -|v255.l|, -|src_scc| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x87,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x05,0x30] + +v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h quad_perm:[3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h op_sel:[1,1,1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x78,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] + +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h quad_perm:[0,1,2,3] +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h op_sel:[0,0,1,0] quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] + +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s3 row_mirror +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x40,0x01,0xff] + +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 row_half_mirror +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x41,0x01,0xff] + +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, ttmp15 row_shl:1 +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, ttmp15 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xee,0x01,0x01,0x01,0x01,0xff] + +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, -|m0| row_shr:15 +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, -|m0| row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x04,0x48,0xd6,0xfa,0x04,0xf6,0x81,0x01,0x1f,0x01,0xff] + +v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.l, -|exec_hi| row_ror:1 +// GFX11: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.l, -|exec_hi| row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x05,0x48,0xd6,0xfa,0x04,0xfe,0xa1,0x01,0x21,0x01,0xff] + +v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|exec_lo| row_ror:15 +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|exec_lo| row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x06,0x48,0xd6,0xfa,0x04,0xfa,0xc1,0x01,0x2f,0x01,0xff] + +v_fma_f16_e64_dpp v5.l, |v1.l|, -v2.l, null row_share:0 row_mask:0xf bank_mask:0xf +// GFX11: v_fma_f16_e64_dpp v5.l, |v1.l|, -v2.l, null row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x01,0x48,0xd6,0xfa,0x04,0xf2,0x41,0x01,0x50,0x01,0xff] + +v_fma_f16_e64_dpp v5.l, -v1.h, |v2.l|, -1 row_share:15 row_mask:0x0 bank_mask:0x1 +// GFX11: v_fma_f16_e64_dpp v5.l, -v1.h, |v2.l|, -1 op_sel:[1,0,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x0a,0x48,0xd6,0xfa,0x04,0x06,0x23,0x01,0x5f,0x01,0x01] + +v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0 +// GFX11: v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 op_sel:[0,1,0,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x05,0x13,0x48,0xd6,0xfa,0x04,0xc2,0x63,0x01,0x60,0x09,0x13] + +v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1 +// GFX11: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x05,0x30] v_fma_f32_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] // GFX11: v_fma_f32_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x13,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] @@ -4833,20 +4869,20 @@ v_div_fixup_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 v_div_fixup_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 // GFX11: v_div_fixup_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x54,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] -v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf -// GFX11: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x7c,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] +v_fma_f16_e64_dpp v5.h, -v1.h, v2.h, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf +// GFX11: v_fma_f16_e64_dpp v5.h, -v1.h, v2.h, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x7c,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] -v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf -// GFX11: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x0b,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] +v_fma_f16_e64_dpp v5.l, -|v1.h|, -|v2.l|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf +// GFX11: v_fma_f16_e64_dpp v5.l, -|v1.h|, -|v2.l|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x0b,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] -v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 -// GFX11: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x15,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] +v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.h, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 +// GFX11: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.h, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x15,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] -v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 -// GFX11: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x26,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x01,0x13] +v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x26,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x01,0x13] -v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 -// GFX11: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] +v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 +// GFX11: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] v_mad_i16_e64_dpp v5.h, v1.h, v2.h, exec_hi op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf // GFX11: v_mad_i16_e64_dpp v5.h, v1.h, v2.h, exec_hi op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x78,0x53,0xd6,0xfa,0x04,0xfe,0x01,0x01,0x2f,0x01,0xff] diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s index cef501703e69d..2ececc0c78ecd 100644 --- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s +++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s @@ -814,41 +814,74 @@ v_div_fixup_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 dpp8:[7,6,5,4,3,2,1,0] fi:1 v_div_fixup_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| clamp dpp8:[0,0,0,0,0,0,0,0] fi:0 // GFX11: v_div_fixup_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0xc7,0x54,0xd6,0xe9,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] -v_fma_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] -// GFX11: v_fma_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] -// GFX11: v_fma_f16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0] -// GFX11: v_fma_f16_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, v1, v2, vcc_hi dpp8:[7,6,5,4,3,2,1,0] -// GFX11: v_fma_f16_e64_dpp v5, v1, v2, vcc_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xae,0x01,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xae,0x01,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, v1, v2, vcc_lo dpp8:[7,6,5,4,3,2,1,0] -// GFX11: v_fma_f16_e64_dpp v5, v1, v2, vcc_lo dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xaa,0x01,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xaa,0x01,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, |v1|, v2, -ttmp15 dpp8:[7,6,5,4,3,2,1,0] -// GFX11: v_fma_f16_e64_dpp v5, |v1|, v2, -ttmp15 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x48,0xd6,0xe9,0x04,0xee,0x81,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -ttmp15 dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -ttmp15 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x48,0xd6,0xe9,0x04,0xee,0x81,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi dpp8:[7,6,5,4,3,2,1,0] -// GFX11: v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x48,0xd6,0xe9,0x04,0xfe,0x41,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, exec_hi dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, exec_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x48,0xd6,0xe9,0x04,0xfe,0x41,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| dpp8:[7,6,5,4,3,2,1,0] -// GFX11: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x04,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, -v1.l, v2.l, |exec_lo| dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, -v1.l, v2.l, |exec_lo| dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x04,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null dpp8:[7,6,5,4,3,2,1,0] -// GFX11: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x03,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.l|, null dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.l|, null dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x03,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| dpp8:[7,6,5,4,3,2,1,0] -// GFX11: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x05,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.l, -|-1| dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.l, -|-1| dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x05,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| dpp8:[7,6,5,4,3,2,1,0] fi:1 -// GFX11: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x05,0x06,0x48,0xd6,0xea,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| dpp8:[7,6,5,4,3,2,1,0] fi:1 +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x05,0x06,0x48,0xd6,0xea,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp dpp8:[0,0,0,0,0,0,0,0] fi:0 -// GFX11: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x87,0x48,0xd6,0xe9,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +v_fma_f16_e64_dpp v255.l, -|v255.l|, -|v255.l|, -|src_scc| clamp dpp8:[0,0,0,0,0,0,0,0] +// GFX11: v_fma_f16_e64_dpp v255.l, -|v255.l|, -|v255.l|, -|src_scc| clamp dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x87,0x48,0xd6,0xe9,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] + +v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x78,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] + +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] + +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s3 dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05] + +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, ttmp15 dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, ttmp15 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xee,0x01,0x01,0x77,0x39,0x05] + +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, -|m0| dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, -|m0| dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x04,0x48,0xd6,0xe9,0x04,0xf6,0x81,0x01,0x77,0x39,0x05] + +v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.l, -|exec_hi| dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.l, -|exec_hi| dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x05,0x48,0xd6,0xe9,0x04,0xfe,0xa1,0x01,0x77,0x39,0x05] + +v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|exec_lo| dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|exec_lo| dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x06,0x48,0xd6,0xe9,0x04,0xfa,0xc1,0x01,0x77,0x39,0x05] + +v_fma_f16_e64_dpp v5.l, |v1.l|, -v2.l, null dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, |v1.l|, -v2.l, null dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x48,0xd6,0xe9,0x04,0xf2,0x41,0x01,0x77,0x39,0x05] + +v_fma_f16_e64_dpp v5.l, -v1.h, |v2.l|, -1 dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, -v1.h, |v2.l|, -1 op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0a,0x48,0xd6,0xe9,0x04,0x06,0x23,0x01,0x77,0x39,0x05] + +v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 dpp8:[7,6,5,4,3,2,1,0] fi:1 +// GFX11: v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x05,0x13,0x48,0xd6,0xea,0x04,0xc2,0x63,0x01,0x77,0x39,0x05] + +v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| clamp dpp8:[0,0,0,0,0,0,0,0] fi:0 +// GFX11: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0xc7,0x48,0xd6,0xe9,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] v_fma_f32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX11: v_fma_f32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x13,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] @@ -3130,20 +3163,20 @@ v_div_fixup_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5 v_div_fixup_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 // GFX11: v_div_fixup_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x54,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] -v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] -// GFX11: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x7c,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.h, -v1.h, v2.h, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.h, -v1.h, v2.h, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x7c,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] -// GFX11: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0b,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, -|v1.h|, -|v2.l|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, -|v1.h|, -|v2.l|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0b,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] -// GFX11: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x15,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.h, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.h, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x15,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] -// GFX11: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x26,0x48,0xd6,0xe9,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] +// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x26,0x48,0xd6,0xe9,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 -// GFX11: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 +// GFX11: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] v_mad_i16_e64_dpp v5.h, v1.h, v2.h, exec_hi op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] // GFX11: v_mad_i16_e64_dpp v5.h, v1.h, v2.h, exec_hi op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x78,0x53,0xd6,0xe9,0x04,0xfe,0x01,0x01,0x77,0x39,0x05] diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s index 0309b2e8e517e..fbfb2dc4239d1 100644 --- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s +++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s @@ -2234,50 +2234,62 @@ v_fma_dx9_zero_f32 v5, -src_scc, |vcc_lo|, -1 mul:4 v_fma_dx9_zero_f32 v255, -|0xaf123456|, -|vcc_hi|, null clamp div:2 // GFX12: v_fma_dx9_zero_f32 v255, -|0xaf123456|, -|vcc_hi|, null clamp div:2 ; encoding: [0xff,0x83,0x09,0xd6,0xff,0xd6,0xf0,0x79,0x56,0x34,0x12,0xaf] -v_fma_f16 v5, v1, v2, s3 -// GFX12: v_fma_f16 v5, v1, v2, s3 ; encoding: [0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00] +v_fma_f16 v5.l, v1.l, v2.l, s3 +// GFX12: v_fma_f16 v5.l, v1.l, v2.l, s3 ; encoding: [0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00] -v_fma_f16 v5, v255, s2, s105 -// GFX12: v_fma_f16 v5, v255, s2, s105 ; encoding: [0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01] +v_fma_f16 v5.l, v255.l, s2, s105 +// GFX12: v_fma_f16 v5.l, v255.l, s2, s105 ; encoding: [0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01] -v_fma_f16 v5, s1, v255, exec_hi -// GFX12: v_fma_f16 v5, s1, v255, exec_hi ; encoding: [0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01] +v_fma_f16 v5.l, s1, v255.l, exec_hi +// GFX12: v_fma_f16 v5.l, s1, v255.l, exec_hi ; encoding: [0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01] -v_fma_f16 v5, s105, s105, exec_lo -// GFX12: v_fma_f16 v5, s105, s105, exec_lo ; encoding: [0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01] +v_fma_f16 v5.l, s105, s105, exec_lo +// GFX12: v_fma_f16 v5.l, s105, s105, exec_lo ; encoding: [0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01] -v_fma_f16 v5, vcc_lo, ttmp15, v3 -// GFX12: v_fma_f16 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04] +v_fma_f16 v5.l, vcc_lo, ttmp15, v3.l +// GFX12: v_fma_f16 v5.l, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04] -v_fma_f16 v5, vcc_hi, 0xfe0b, v255 -// GFX12: v_fma_f16 v5, vcc_hi, 0xfe0b, v255 ; encoding: [0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] +v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.l +// GFX12: v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.l ; encoding: [0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] -v_fma_f16 v5, -|ttmp15|, -|src_scc|, -|ttmp15| -// GFX12: v_fma_f16 v5, -|ttmp15|, -|src_scc|, -|ttmp15| ; encoding: [0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1] +v_fma_f16 v5.l, -|ttmp15|, -|src_scc|, -|ttmp15| +// GFX12: v_fma_f16 v5.l, -|ttmp15|, -|src_scc|, -|ttmp15| ; encoding: [0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1] -v_fma_f16 v5, m0, 0.5, m0 -// GFX12: v_fma_f16 v5, m0, 0.5, m0 ; encoding: [0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01] +v_fma_f16 v5.l, m0, 0.5, m0 +// GFX12: v_fma_f16 v5.l, m0, 0.5, m0 ; encoding: [0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01] -v_fma_f16 v5, |exec_lo|, -1, vcc_hi -// GFX12: v_fma_f16 v5, |exec_lo|, -1, vcc_hi ; encoding: [0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01] +v_fma_f16 v5.l, |exec_lo|, -1, vcc_hi +// GFX12: v_fma_f16 v5.l, |exec_lo|, -1, vcc_hi ; encoding: [0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01] -v_fma_f16 v5, -|exec_hi|, null, -|vcc_lo| op_sel:[1,1,1,1] -// GFX12: v_fma_f16 v5, -|exec_hi|, null, -|vcc_lo| op_sel:[1,1,1,1] ; encoding: [0x05,0x7d,0x48,0xd6,0x7f,0xf8,0xa8,0xa1] +v_fma_f16 v5.h, -|exec_hi|, null, -|vcc_lo| op_sel:[1,1,1,1] +// GFX12: v_fma_f16 v5.h, -|exec_hi|, null, -|vcc_lo| op_sel:[1,1,1,1] ; encoding: [0x05,0x7d,0x48,0xd6,0x7f,0xf8,0xa8,0xa1] -v_fma_f16 v5, null, exec_lo, -|0xfe0b| op_sel:[0,0,0,0] -// GFX12: v_fma_f16 v5, null, exec_lo, -|0xfe0b| ; encoding: [0x05,0x04,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00] +v_fma_f16 v5.l, null, exec_lo, -|0xfe0b| op_sel:[0,0,0,0] +// GFX12: v_fma_f16 v5.l, null, exec_lo, -|0xfe0b| ; encoding: [0x05,0x04,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00] -v_fma_f16 v5, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] -// GFX12: v_fma_f16 v5, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] ; encoding: [0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3] +v_fma_f16 v5.l, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] +// GFX12: v_fma_f16 v5.l, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] ; encoding: [0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3] -v_fma_f16 v5, 0.5, -m0, 0.5 op_sel:[0,1,0,0] -// GFX12: v_fma_f16 v5, 0.5, -m0, 0.5 op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43] +v_fma_f16 v5.l, 0.5, -m0, 0.5 op_sel:[0,1,0,0] +// GFX12: v_fma_f16 v5.l, 0.5, -m0, 0.5 op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43] -v_fma_f16 v5, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] -// GFX12: v_fma_f16 v5, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] ; encoding: [0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23] +v_fma_f16 v5.l, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] +// GFX12: v_fma_f16 v5.l, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] ; encoding: [0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23] -v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp -// GFX12: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] +v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp +// GFX12: v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] + +v_fma_f16 v5.l, v255.h, s2, s105 +// GFX12: v_fma_f16 v5.l, v255.h, s2, s105 op_sel:[1,0,0,0] ; encoding: [0x05,0x08,0x48,0xd6,0xff,0x05,0xa4,0x01] + +v_fma_f16 v5.l, s1, v255.h, exec_hi +// GFX12: v_fma_f16 v5.l, s1, v255.h, exec_hi op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0x01,0xfe,0xff,0x01] + +v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.h +// GFX12: v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] + +v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null clamp +// GFX12: v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] v_fma_f32 v5, v1, v2, s3 // GFX12: v_fma_f32 v5, v1, v2, s3 ; encoding: [0x05,0x00,0x13,0xd6,0x01,0x05,0x0e,0x00] diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s index b769324d5412f..c936d1d405b15 100644 --- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s +++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s @@ -1775,53 +1775,68 @@ v_div_fixup_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 row_xmask:0 row_mask:0x1 ban v_div_fixup_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1 // GFX12: v_div_fixup_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0xc7,0x54,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x05,0x30] -v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] -v_fma_f16_e64_dpp v5, v1, s2, v3 quad_perm:[3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, v1, s2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0c,0x04,0x01,0x1b,0x00,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, s2, v3.l quad_perm:[3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, s2, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0c,0x04,0x01,0x1b,0x00,0xff] -v_fma_f16_e64_dpp v5, v1, 2.0, v3 quad_perm:[3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, v1, 2.0, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0xe8,0x0d,0x04,0x01,0x1b,0x00,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, 2.0, v3.l quad_perm:[3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, 2.0, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0xe8,0x0d,0x04,0x01,0x1b,0x00,0xff] -v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[0,1,2,3] -// GFX12: v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0xe4,0x00,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[0,1,2,3] +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0xe4,0x00,0xff] -v_fma_f16_e64_dpp v5, v1, v2, v3 row_mirror -// GFX12: v_fma_f16_e64_dpp v5, v1, v2, v3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x40,0x01,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l row_mirror +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x40,0x01,0xff] -v_fma_f16_e64_dpp v5, v1, v2, v255 row_half_mirror -// GFX12: v_fma_f16_e64_dpp v5, v1, v2, v255 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x41,0x01,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l row_half_mirror +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x41,0x01,0xff] -v_fma_f16_e64_dpp v5, v1, v2, s105 row_shl:1 -// GFX12: v_fma_f16_e64_dpp v5, v1, v2, s105 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x01,0x01,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 row_shl:1 +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x01,0x01,0xff] -v_fma_f16_e64_dpp v5, v1, v2, vcc_hi row_shl:15 -// GFX12: v_fma_f16_e64_dpp v5, v1, v2, vcc_hi row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi row_shl:15 +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff] -v_fma_f16_e64_dpp v5, v1, v2, vcc_lo row_shr:1 -// GFX12: v_fma_f16_e64_dpp v5, v1, v2, vcc_lo row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo row_shr:1 +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff] -v_fma_f16_e64_dpp v5, |v1|, v2, -ttmp15 row_shr:15 -// GFX12: v_fma_f16_e64_dpp v5, |v1|, v2, -ttmp15 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x01,0x48,0xd6,0xfa,0x04,0xee,0x81,0x01,0x1f,0x01,0xff] +v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -ttmp15 row_shr:15 +// GFX12: v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -ttmp15 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x01,0x48,0xd6,0xfa,0x04,0xee,0x81,0x01,0x1f,0x01,0xff] -v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi row_ror:1 -// GFX12: v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x02,0x48,0xd6,0xfa,0x04,0xfe,0x41,0x01,0x21,0x01,0xff] +v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, exec_hi row_ror:1 +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, exec_hi row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x02,0x48,0xd6,0xfa,0x04,0xfe,0x41,0x01,0x21,0x01,0xff] -v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| row_ror:15 -// GFX12: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x04,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] +v_fma_f16_e64_dpp v5.l, -v1.l, v2.l, |exec_lo| row_ror:15 +// GFX12: v_fma_f16_e64_dpp v5.l, -v1.l, v2.l, |exec_lo| row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x04,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] -v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null row_share:0 row_mask:0xf bank_mask:0xf -// GFX12: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x03,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] +v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.l|, null row_share:0 row_mask:0xf bank_mask:0xf +// GFX12: v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.l|, null row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x03,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] -v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| row_share:15 row_mask:0x0 bank_mask:0x1 -// GFX12: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x05,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] +v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.l, -|-1| row_share:15 row_mask:0x0 bank_mask:0x1 +// GFX12: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.l, -|-1| row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x05,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] -v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0 -// GFX12: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x05,0x06,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x09,0x13] +v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0 +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x05,0x06,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x09,0x13] -v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1 -// GFX12: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x87,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x05,0x30] +v_fma_f16_e64_dpp v255.l, -|v255.l|, -|v255.l|, -|src_scc| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1 +// GFX12: v_fma_f16_e64_dpp v255.l, -|v255.l|, -|v255.l|, -|src_scc| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x87,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x05,0x30] + +v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h quad_perm:[3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h op_sel:[1,1,1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x78,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] + +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h quad_perm:[0,1,2,3] +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h op_sel:[0,0,1,0] quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] + +v_fma_f16_e64_dpp v5.l, -v1.h, |v2.l|, -1 row_share:15 row_mask:0x0 bank_mask:0x1 +// GFX12: v_fma_f16_e64_dpp v5.l, -v1.h, |v2.l|, -1 op_sel:[1,0,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x0a,0x48,0xd6,0xfa,0x04,0x06,0x23,0x01,0x5f,0x01,0x01] + +v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0 +// GFX12: v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 op_sel:[0,1,0,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x05,0x13,0x48,0xd6,0xfa,0x04,0xc2,0x63,0x01,0x60,0x09,0x13] + +v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1 +// GFX12: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x05,0x30] v_fma_f32_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] // GFX12: v_fma_f32_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x13,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] @@ -5245,20 +5260,20 @@ v_div_fixup_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 v_div_fixup_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 // GFX12: v_div_fixup_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x54,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] -v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf -// GFX12: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x7c,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] +v_fma_f16_e64_dpp v5.h, -v1.h, v2.h, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf +// GFX12: v_fma_f16_e64_dpp v5.h, -v1.h, v2.h, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x7c,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] -v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf -// GFX12: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x0b,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] +v_fma_f16_e64_dpp v5.l, -|v1.h|, -|v2.l|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf +// GFX12: v_fma_f16_e64_dpp v5.l, -|v1.h|, -|v2.l|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x0b,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] -v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 -// GFX12: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x15,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] +v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.h, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 +// GFX12: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.h, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x15,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] -v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 -// GFX12: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x26,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x01,0x13] +v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x26,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x01,0x13] -v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 -// GFX12: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] +v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 +// GFX12: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] v_mad_i16_e64_dpp v5.h, v1.h, v2.h, exec_hi op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf // GFX12: v_mad_i16_e64_dpp v5.h, v1.h, v2.h, exec_hi op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x78,0x53,0xd6,0xfa,0x04,0xfe,0x01,0x01,0x2f,0x01,0xff] diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s index f76dd26623144..d747cc51ae630 100644 --- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s +++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s @@ -1008,47 +1008,62 @@ v_div_fixup_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 dpp8:[7,6,5,4,3,2,1,0] fi:1 v_div_fixup_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| clamp dpp8:[0,0,0,0,0,0,0,0] fi:0 // GFX12: v_div_fixup_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0xc7,0x54,0xd6,0xe9,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] -v_fma_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, v1, s2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, s2, v3.l dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, s2, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0c,0x04,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, v1, 2.0, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, 2.0, v3.l dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, 2.0, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0xe8,0x0d,0x04,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, v1, v2, vcc_hi dpp8:[7,6,5,4,3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, v1, v2, vcc_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xae,0x01,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xae,0x01,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, v1, v2, vcc_lo dpp8:[7,6,5,4,3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, v1, v2, vcc_lo dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xaa,0x01,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xaa,0x01,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, |v1|, v2, -ttmp15 dpp8:[7,6,5,4,3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, |v1|, v2, -ttmp15 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x48,0xd6,0xe9,0x04,0xee,0x81,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -ttmp15 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -ttmp15 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x48,0xd6,0xe9,0x04,0xee,0x81,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi dpp8:[7,6,5,4,3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x48,0xd6,0xe9,0x04,0xfe,0x41,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, exec_hi dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, exec_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x48,0xd6,0xe9,0x04,0xfe,0x41,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| dpp8:[7,6,5,4,3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x04,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, -v1.l, v2.l, |exec_lo| dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, -v1.l, v2.l, |exec_lo| dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x04,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null dpp8:[7,6,5,4,3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x03,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.l|, null dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.l|, null dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x03,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| dpp8:[7,6,5,4,3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x05,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.l, -|-1| dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.l, -|-1| dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x05,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| dpp8:[7,6,5,4,3,2,1,0] fi:1 -// GFX12: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x05,0x06,0x48,0xd6,0xea,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| dpp8:[7,6,5,4,3,2,1,0] fi:1 +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x05,0x06,0x48,0xd6,0xea,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp dpp8:[0,0,0,0,0,0,0,0] fi:0 -// GFX12: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x87,0x48,0xd6,0xe9,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +v_fma_f16_e64_dpp v255.l, -|v255.l|, -|v255.l|, -|src_scc| clamp dpp8:[0,0,0,0,0,0,0,0] fi:0 +// GFX12: v_fma_f16_e64_dpp v255.l, -|v255.l|, -|v255.l|, -|src_scc| clamp dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x87,0x48,0xd6,0xe9,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] + +v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x78,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] + +v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] + +v_fma_f16_e64_dpp v5.l, -v1.h, |v2.l|, -1 dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, -v1.h, |v2.l|, -1 op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0a,0x48,0xd6,0xe9,0x04,0x06,0x23,0x01,0x77,0x39,0x05] + +v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 dpp8:[7,6,5,4,3,2,1,0] fi:1 +// GFX12: v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x05,0x13,0x48,0xd6,0xea,0x04,0xc2,0x63,0x01,0x77,0x39,0x05] + +v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| clamp dpp8:[0,0,0,0,0,0,0,0] fi:0 +// GFX12: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0xc7,0x48,0xd6,0xe9,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] v_fma_f32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] // GFX12: v_fma_f32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x13,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] @@ -3514,20 +3529,20 @@ v_div_fixup_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5 v_div_fixup_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 // GFX12: v_div_fixup_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x54,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] -v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x7c,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.h, -v1.h, v2.h, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.h, -v1.h, v2.h, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x7c,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0b,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, -|v1.h|, -|v2.l|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, -|v1.h|, -|v2.l|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0b,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x15,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.h, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.h, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x15,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] -// GFX12: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x26,0x48,0xd6,0xe9,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] +v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] +// GFX12: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x26,0x48,0xd6,0xe9,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] -v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 -// GFX12: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 +// GFX12: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] v_mad_i16_e64_dpp v5.h, v1.h, v2.h, exec_hi op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] // GFX12: v_mad_i16_e64_dpp v5.h, v1.h, v2.h, exec_hi op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x78,0x53,0xd6,0xe9,0x04,0xfe,0x01,0x01,0x77,0x39,0x05] diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt index 4990c62b9438c..f9e236977c973 100644 --- a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt +++ b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt @@ -2402,53 +2402,125 @@ # GFX11: v_fma_dx9_zero_f32 v255, -|0xaf123456|, -|vcc_hi|, null clamp div:2 ; encoding: [0xff,0x83,0x09,0xd6,0xff,0xd6,0xf0,0x79,0x56,0x34,0x12,0xaf] 0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00 -# GFX11: v_fma_f16 v5, v1, v2, s3 ; encoding: [0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00] +# W32-REAL16: v_fma_f16 v5.l, v1.l, v2.l, s3 ; encoding: [0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00] +# W32-FAKE16: v_fma_f16 v5, v1, v2, s3 ; encoding: [0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00] +# W64-REAL16: v_fma_f16 v5.l, v1.l, v2.l, s3 ; encoding: [0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00] +# W64-FAKE16: v_fma_f16 v5, v1, v2, s3 ; encoding: [0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00] 0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01 -# GFX11: v_fma_f16 v5, v255, s2, s105 ; encoding: [0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01] +# W32-REAL16: v_fma_f16 v5.l, v255.l, s2, s105 ; encoding: [0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01] +# W32-FAKE16: v_fma_f16 v5, v255, s2, s105 ; encoding: [0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01] +# W64-REAL16: v_fma_f16 v5.l, v255.l, s2, s105 ; encoding: [0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01] +# W64-FAKE16: v_fma_f16 v5, v255, s2, s105 ; encoding: [0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01] 0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01 -# GFX11: v_fma_f16 v5, s1, v255, exec_hi ; encoding: [0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01] +# W32-REAL16: v_fma_f16 v5.l, s1, v255.l, exec_hi ; encoding: [0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01] +# W32-FAKE16: v_fma_f16 v5, s1, v255, exec_hi ; encoding: [0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01] +# W64-REAL16: v_fma_f16 v5.l, s1, v255.l, exec_hi ; encoding: [0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01] +# W64-FAKE16: v_fma_f16 v5, s1, v255, exec_hi ; encoding: [0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01] 0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01 -# GFX11: v_fma_f16 v5, s105, s105, exec_lo ; encoding: [0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01] +# W32-REAL16: v_fma_f16 v5.l, s105, s105, exec_lo ; encoding: [0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01] +# W32-FAKE16: v_fma_f16 v5, s105, s105, exec_lo ; encoding: [0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01] +# W64-REAL16: v_fma_f16 v5.l, s105, s105, exec_lo ; encoding: [0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01] +# W64-FAKE16: v_fma_f16 v5, s105, s105, exec_lo ; encoding: [0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01] 0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04 -# GFX11: v_fma_f16 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04] +# W32-REAL16: v_fma_f16 v5.l, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04] +# W32-FAKE16: v_fma_f16 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04] +# W64-REAL16: v_fma_f16 v5.l, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04] +# W64-FAKE16: v_fma_f16 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04] 0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00 -# GFX11: v_fma_f16 v5, vcc_hi, 0xfe0b, v255 ; encoding: [0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] +# W32-REAL16: v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.l ; encoding: [0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] +# W32-FAKE16: v_fma_f16 v5, vcc_hi, 0xfe0b, v255 ; encoding: [0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] +# W64-REAL16: v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.l ; encoding: [0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] +# W64-FAKE16: v_fma_f16 v5, vcc_hi, 0xfe0b, v255 ; encoding: [0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] 0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1 -# GFX11: v_fma_f16 v5, -|ttmp15|, -|src_scc|, -|ttmp15| ; encoding: [0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1] +# W32-REAL16: v_fma_f16 v5.l, -|ttmp15|, -|src_scc|, -|ttmp15| ; encoding: [0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1] +# W32-FAKE16: v_fma_f16 v5, -|ttmp15|, -|src_scc|, -|ttmp15| ; encoding: [0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1] +# W64-REAL16: v_fma_f16 v5.l, -|ttmp15|, -|src_scc|, -|ttmp15| ; encoding: [0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1] +# W64-FAKE16: v_fma_f16 v5, -|ttmp15|, -|src_scc|, -|ttmp15| ; encoding: [0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1] 0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01 -# GFX11: v_fma_f16 v5, m0, 0.5, m0 ; encoding: [0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01] +# W32-REAL16: v_fma_f16 v5.l, m0, 0.5, m0 ; encoding: [0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01] +# W32-FAKE16: v_fma_f16 v5, m0, 0.5, m0 ; encoding: [0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01] +# W64-REAL16: v_fma_f16 v5.l, m0, 0.5, m0 ; encoding: [0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01] +# W64-FAKE16: v_fma_f16 v5, m0, 0.5, m0 ; encoding: [0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01] 0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01 -# GFX11: v_fma_f16 v5, |exec_lo|, -1, vcc_hi ; encoding: [0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01] +# W32-REAL16: v_fma_f16 v5.l, |exec_lo|, -1, vcc_hi ; encoding: [0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01] +# W32-FAKE16: v_fma_f16 v5, |exec_lo|, -1, vcc_hi ; encoding: [0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01] +# W64-REAL16: v_fma_f16 v5.l, |exec_lo|, -1, vcc_hi ; encoding: [0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01] +# W64-FAKE16: v_fma_f16 v5, |exec_lo|, -1, vcc_hi ; encoding: [0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01] 0x05,0x05,0x48,0xd6,0x7f,0xf8,0xa8,0xa1 -# GFX11: v_fma_f16 v5, -|exec_hi|, null, -|vcc_lo| ; encoding: [0x05,0x05,0x48,0xd6,0x7f,0xf8,0xa8,0xa1] +# W32-REAL16: v_fma_f16 v5.l, -|exec_hi|, null, -|vcc_lo| ; encoding: [0x05,0x05,0x48,0xd6,0x7f,0xf8,0xa8,0xa1] +# W32-FAKE16: v_fma_f16 v5, -|exec_hi|, null, -|vcc_lo| ; encoding: [0x05,0x05,0x48,0xd6,0x7f,0xf8,0xa8,0xa1] +# W64-REAL16: v_fma_f16 v5.l, -|exec_hi|, null, -|vcc_lo| ; encoding: [0x05,0x05,0x48,0xd6,0x7f,0xf8,0xa8,0xa1] +# W64-FAKE16: v_fma_f16 v5, -|exec_hi|, null, -|vcc_lo| ; encoding: [0x05,0x05,0x48,0xd6,0x7f,0xf8,0xa8,0xa1] 0x05,0x7c,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00 -# GFX11: v_fma_f16 v5, null, exec_lo, -|0xfe0b| op_sel:[1,1,1,1] ; encoding: [0x05,0x7c,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00] +# W32-REAL16: v_fma_f16 v5.h, null, exec_lo, -|0xfe0b| op_sel:[1,1,1,1] ; encoding: [0x05,0x7c,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00] +# W32-FAKE16: v_fma_f16 v5, null, exec_lo, -|0xfe0b| op_sel:[1,1,1,1] ; encoding: [0x05,0x7c,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00] +# W64-REAL16: v_fma_f16 v5.h, null, exec_lo, -|0xfe0b| op_sel:[1,1,1,1] ; encoding: [0x05,0x7c,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00] +# W64-FAKE16: v_fma_f16 v5, null, exec_lo, -|0xfe0b| op_sel:[1,1,1,1] ; encoding: [0x05,0x7c,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00] 0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3 -# GFX11: v_fma_f16 v5, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] ; encoding: [0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3] +# W32-REAL16: v_fma_f16 v5.l, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] ; encoding: [0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3] +# W32-FAKE16: v_fma_f16 v5, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] ; encoding: [0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3] +# W64-REAL16: v_fma_f16 v5.l, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] ; encoding: [0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3] +# W64-FAKE16: v_fma_f16 v5, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] ; encoding: [0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3] 0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43 -# GFX11: v_fma_f16 v5, 0.5, -m0, 0.5 op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43] +# W32-REAL16: v_fma_f16 v5.l, 0.5, -m0, 0.5 op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43] +# W32-FAKE16: v_fma_f16 v5, 0.5, -m0, 0.5 op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43] +# W64-REAL16: v_fma_f16 v5.l, 0.5, -m0, 0.5 op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43] +# W64-FAKE16: v_fma_f16 v5, 0.5, -m0, 0.5 op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43] 0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23 -# GFX11: v_fma_f16 v5, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] ; encoding: [0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23] +# W32-REAL16: v_fma_f16 v5.l, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] ; encoding: [0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23] +# W32-FAKE16: v_fma_f16 v5, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] ; encoding: [0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23] +# W64-REAL16: v_fma_f16 v5.l, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] ; encoding: [0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23] +# W64-FAKE16: v_fma_f16 v5, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] ; encoding: [0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23] 0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00 -# GFX11: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] +# W32-REAL16: v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] +# W32-FAKE16: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] +# W64-REAL16: v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] +# W64-FAKE16: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] # CHECK: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp div:2 ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x79,0x0b,0xfe,0x00,0x00] 0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x79,0x0b,0xfe,0x00,0x00 -# GFX11: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp div:2 ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x79,0x0b,0xfe,0x00,0x00] +# W32-REAL16: v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp div:2 ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x79,0x0b,0xfe,0x00,0x00] +# W32-FAKE16: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp div:2 ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x79,0x0b,0xfe,0x00,0x00] +# W64-REAL16: v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp div:2 ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x79,0x0b,0xfe,0x00,0x00] +# W64-FAKE16: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp div:2 ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x79,0x0b,0xfe,0x00,0x00] + +0x05,0x08,0x48,0xd6,0xff,0x05,0xa4,0x01 +# W32-REAL16: v_fma_f16 v5.l, v255.h, s2, s105 op_sel:[1,0,0,0] ; encoding: [0x05,0x08,0x48,0xd6,0xff,0x05,0xa4,0x01] +# W32-FAKE16: v_fma_f16 v5, v255, s2, s105 op_sel:[1,0,0,0] ; encoding: [0x05,0x08,0x48,0xd6,0xff,0x05,0xa4,0x01] +# W64-REAL16: v_fma_f16 v5.l, v255.h, s2, s105 op_sel:[1,0,0,0] ; encoding: [0x05,0x08,0x48,0xd6,0xff,0x05,0xa4,0x01] +# W64-FAKE16: v_fma_f16 v5, v255, s2, s105 op_sel:[1,0,0,0] ; encoding: [0x05,0x08,0x48,0xd6,0xff,0x05,0xa4,0x01] + +0x05,0x10,0x48,0xd6,0x01,0xfe,0xff,0x01 +# W32-REAL16: v_fma_f16 v5.l, s1, v255.h, exec_hi op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0x01,0xfe,0xff,0x01] +# W32-FAKE16: v_fma_f16 v5, s1, v255, exec_hi op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0x01,0xfe,0xff,0x01] +# W64-REAL16: v_fma_f16 v5.l, s1, v255.h, exec_hi op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0x01,0xfe,0xff,0x01] +# W64-FAKE16: v_fma_f16 v5, s1, v255, exec_hi op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0x01,0xfe,0xff,0x01] + +0x05,0x20,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00 +# W32-REAL16: v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] +# W32-FAKE16: v_fma_f16 v5, vcc_hi, 0xfe0b, v255 op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] +# W64-REAL16: v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] +# W64-FAKE16: v_fma_f16 v5, vcc_hi, 0xfe0b, v255 op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] + +0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00 +# W32-REAL16: v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] +# W32-FAKE16: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] +# W64-REAL16: v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] +# W64-FAKE16: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] 0x05,0x00,0x13,0xd6,0x01,0x05,0x0e,0x00 # GFX11: v_fma_f32 v5, v1, v2, s3 ; encoding: [0x05,0x00,0x13,0xd6,0x01,0x05,0x0e,0x00] diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp16.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp16.txt index d734cd2bba1aa..132fc80dda47d 100644 --- a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp16.txt +++ b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp16.txt @@ -4431,46 +4431,130 @@ # W64-FAKE16: v_div_fixup_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x54,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] 0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff -# GFX11: v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] 0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff -# GFX11: v_fma_f16_e64_dpp v5, v1, v2, v255 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] 0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x40,0x01,0xff -# GFX11: v_fma_f16_e64_dpp v5, v1, v2, s3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x40,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x40,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, s3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x40,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x40,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, s3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x40,0x01,0xff] 0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x41,0x01,0xff -# GFX11: v_fma_f16_e64_dpp v5, v1, v2, s105 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x41,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x41,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, s105 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x41,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x41,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, s105 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x41,0x01,0xff] 0x05,0x00,0x48,0xd6,0xfa,0x04,0xee,0x01,0x01,0x01,0x01,0xff -# GFX11: v_fma_f16_e64_dpp v5, v1, v2, ttmp15 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xee,0x01,0x01,0x01,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, ttmp15 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xee,0x01,0x01,0x01,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, ttmp15 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xee,0x01,0x01,0x01,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, ttmp15 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xee,0x01,0x01,0x01,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, ttmp15 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xee,0x01,0x01,0x01,0x01,0xff] 0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff -# GFX11: v_fma_f16_e64_dpp v5, v1, v2, vcc_hi row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, vcc_hi row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, vcc_hi row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff] 0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff -# GFX11: v_fma_f16_e64_dpp v5, v1, v2, vcc_lo row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, vcc_lo row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, vcc_lo row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff] 0x05,0x01,0x48,0xd6,0xfa,0x04,0xf6,0x81,0x01,0x1f,0x01,0xff -# GFX11: v_fma_f16_e64_dpp v5, |v1|, v2, -m0 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x01,0x48,0xd6,0xfa,0x04,0xf6,0x81,0x01,0x1f,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -m0 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x01,0x48,0xd6,0xfa,0x04,0xf6,0x81,0x01,0x1f,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, |v1|, v2, -m0 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x01,0x48,0xd6,0xfa,0x04,0xf6,0x81,0x01,0x1f,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -m0 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x01,0x48,0xd6,0xfa,0x04,0xf6,0x81,0x01,0x1f,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, |v1|, v2, -m0 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x01,0x48,0xd6,0xfa,0x04,0xf6,0x81,0x01,0x1f,0x01,0xff] 0x05,0x02,0x48,0xd6,0xfa,0x04,0xfe,0x41,0x01,0x21,0x01,0xff -# GFX11: v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x02,0x48,0xd6,0xfa,0x04,0xfe,0x41,0x01,0x21,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, exec_hi row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x02,0x48,0xd6,0xfa,0x04,0xfe,0x41,0x01,0x21,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x02,0x48,0xd6,0xfa,0x04,0xfe,0x41,0x01,0x21,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, exec_hi row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x02,0x48,0xd6,0xfa,0x04,0xfe,0x41,0x01,0x21,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x02,0x48,0xd6,0xfa,0x04,0xfe,0x41,0x01,0x21,0x01,0xff] 0x05,0x7c,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff -# GFX11: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x7c,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.h, -v1.h, v2.h, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x7c,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x7c,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.h, -v1.h, v2.h, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x7c,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x7c,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] 0x05,0x0b,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff -# GFX11: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x0b,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.h|, -|v2.l|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x0b,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x0b,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.h|, -|v2.l|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x0b,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x0b,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] 0x05,0x15,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01 -# GFX11: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x15,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.h, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x15,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x15,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.h, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x15,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x15,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] 0x05,0x26,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x01,0x13 -# GFX11: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x26,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x01,0x13] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x26,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x01,0x13] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x26,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x01,0x13] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x26,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x01,0x13] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x26,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x01,0x13] 0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30 -# GFX11: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] +# W32-REAL16: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] +# W32-FAKE16: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] +# W64-REAL16: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] +# W64-FAKE16: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] + +0x05,0x78,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff +# W32-REAL16: v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h op_sel:[1,1,1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x78,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 op_sel:[1,1,1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x78,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h op_sel:[1,1,1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x78,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 op_sel:[1,1,1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x78,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] + +0x05,0x20,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h op_sel:[0,0,1,0] quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h op_sel:[0,0,1,0] quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] + +0x05,0x78,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff +# W32-REAL16: v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h op_sel:[1,1,1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x78,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 op_sel:[1,1,1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x78,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h op_sel:[1,1,1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x78,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 op_sel:[1,1,1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x78,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] + +0x05,0x20,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h op_sel:[0,0,1,0] quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h op_sel:[0,0,1,0] quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] + +0x05,0x0a,0x48,0xd6,0xfa,0x04,0x06,0x23,0x01,0x5f,0x01,0x01 +# W32-REAL16: v_fma_f16_e64_dpp v5.l, -v1.h, |v2.l|, -1 op_sel:[1,0,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x0a,0x48,0xd6,0xfa,0x04,0x06,0x23,0x01,0x5f,0x01,0x01] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -v1, |v2|, -1 op_sel:[1,0,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x0a,0x48,0xd6,0xfa,0x04,0x06,0x23,0x01,0x5f,0x01,0x01] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, -v1.h, |v2.l|, -1 op_sel:[1,0,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x0a,0x48,0xd6,0xfa,0x04,0x06,0x23,0x01,0x5f,0x01,0x01] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -v1, |v2|, -1 op_sel:[1,0,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x0a,0x48,0xd6,0xfa,0x04,0x06,0x23,0x01,0x5f,0x01,0x01] + +0x05,0x13,0x48,0xd6,0xfa,0x04,0xc2,0x63,0x01,0x60,0x01,0x13 +# W32-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 op_sel:[0,1,0,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x13,0x48,0xd6,0xfa,0x04,0xc2,0x63,0x01,0x60,0x01,0x13] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, 0.5 op_sel:[0,1,0,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x13,0x48,0xd6,0xfa,0x04,0xc2,0x63,0x01,0x60,0x01,0x13] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 op_sel:[0,1,0,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x13,0x48,0xd6,0xfa,0x04,0xc2,0x63,0x01,0x60,0x01,0x13] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, 0.5 op_sel:[0,1,0,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x13,0x48,0xd6,0xfa,0x04,0xc2,0x63,0x01,0x60,0x01,0x13] + +0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30 +# W32-REAL16: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] +# W32-FAKE16: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] +# W64-REAL16: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] +# W64-FAKE16: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] 0x05,0x00,0x53,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff # W32-REAL16: v_mad_i16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x53,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp8.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp8.txt index 3b3d39844b792..714fac9fe62a0 100644 --- a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp8.txt +++ b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp8.txt @@ -2547,46 +2547,130 @@ # W64-FAKE16: v_div_fixup_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x54,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] 0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05 -# GFX11: v_fma_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] 0x05,0x00,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05 -# GFX11: v_fma_f16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] 0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05 -# GFX11: v_fma_f16_e64_dpp v5, v1, v2, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05] 0x05,0x00,0x48,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05 -# GFX11: v_fma_f16_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05] 0x05,0x00,0x48,0xd6,0xe9,0x04,0xee,0x01,0x01,0x77,0x39,0x05 -# GFX11: v_fma_f16_e64_dpp v5, v1, v2, ttmp15 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xee,0x01,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, ttmp15 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xee,0x01,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, ttmp15 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xee,0x01,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, ttmp15 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xee,0x01,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, ttmp15 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xee,0x01,0x01,0x77,0x39,0x05] 0x05,0x00,0x48,0xd6,0xe9,0x04,0xae,0x01,0x01,0x77,0x39,0x05 -# GFX11: v_fma_f16_e64_dpp v5, v1, v2, vcc_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xae,0x01,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xae,0x01,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, vcc_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xae,0x01,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xae,0x01,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, vcc_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xae,0x01,0x01,0x77,0x39,0x05] 0x05,0x00,0x48,0xd6,0xe9,0x04,0xaa,0x01,0x01,0x77,0x39,0x05 -# GFX11: v_fma_f16_e64_dpp v5, v1, v2, vcc_lo dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xaa,0x01,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xaa,0x01,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, vcc_lo dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xaa,0x01,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xaa,0x01,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, vcc_lo dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xaa,0x01,0x01,0x77,0x39,0x05] 0x05,0x01,0x48,0xd6,0xe9,0x04,0xf6,0x81,0x01,0x77,0x39,0x05 -# GFX11: v_fma_f16_e64_dpp v5, |v1|, v2, -m0 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x48,0xd6,0xe9,0x04,0xf6,0x81,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -m0 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x48,0xd6,0xe9,0x04,0xf6,0x81,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, |v1|, v2, -m0 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x48,0xd6,0xe9,0x04,0xf6,0x81,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -m0 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x48,0xd6,0xe9,0x04,0xf6,0x81,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, |v1|, v2, -m0 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x48,0xd6,0xe9,0x04,0xf6,0x81,0x01,0x77,0x39,0x05] 0x05,0x02,0x48,0xd6,0xe9,0x04,0xfe,0x41,0x01,0x77,0x39,0x05 -# GFX11: v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x48,0xd6,0xe9,0x04,0xfe,0x41,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, exec_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x48,0xd6,0xe9,0x04,0xfe,0x41,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x48,0xd6,0xe9,0x04,0xfe,0x41,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, exec_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x48,0xd6,0xe9,0x04,0xfe,0x41,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x48,0xd6,0xe9,0x04,0xfe,0x41,0x01,0x77,0x39,0x05] 0x05,0x7c,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05 -# GFX11: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x7c,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.h, -v1.h, v2.h, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x7c,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x7c,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.h, -v1.h, v2.h, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x7c,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x7c,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] 0x05,0x0b,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05 -# GFX11: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0b,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.h|, -|v2.l|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0b,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0b,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.h|, -|v2.l|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0b,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0b,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] 0x05,0x15,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05 -# GFX11: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x15,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.h, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x15,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x15,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.h, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x15,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x15,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] 0x05,0x26,0x48,0xd6,0xe9,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05 -# GFX11: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x26,0x48,0xd6,0xe9,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x26,0x48,0xd6,0xe9,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x26,0x48,0xd6,0xe9,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x26,0x48,0xd6,0xe9,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x26,0x48,0xd6,0xe9,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] 0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00 -# GFX11: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +# W32-REAL16: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +# W32-FAKE16: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +# W64-REAL16: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +# W64-FAKE16: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] + +0x05,0x78,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05 +# W32-REAL16: v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x78,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x78,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x78,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x78,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] + +0x05,0x20,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05 +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] + +0x05,0x78,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05 +# W32-REAL16: v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x78,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x78,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x78,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x78,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] + +0x05,0x20,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05 +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] + +0x05,0x0a,0x48,0xd6,0xe9,0x04,0x06,0x23,0x01,0x77,0x39,0x05 +# W32-REAL16: v_fma_f16_e64_dpp v5.l, -v1.h, |v2.l|, -1 op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0a,0x48,0xd6,0xe9,0x04,0x06,0x23,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -v1, |v2|, -1 op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0a,0x48,0xd6,0xe9,0x04,0x06,0x23,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, -v1.h, |v2.l|, -1 op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0a,0x48,0xd6,0xe9,0x04,0x06,0x23,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -v1, |v2|, -1 op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0a,0x48,0xd6,0xe9,0x04,0x06,0x23,0x01,0x77,0x39,0x05] + +0x05,0x13,0x48,0xd6,0xe9,0x04,0xc2,0x63,0x01,0x77,0x39,0x05 +# W32-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x13,0x48,0xd6,0xe9,0x04,0xc2,0x63,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, 0.5 op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x13,0x48,0xd6,0xe9,0x04,0xc2,0x63,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x13,0x48,0xd6,0xe9,0x04,0xc2,0x63,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, 0.5 op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x13,0x48,0xd6,0xe9,0x04,0xc2,0x63,0x01,0x77,0x39,0x05] + +0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00 +# W32-REAL16: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +# W32-FAKE16: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +# W64-REAL16: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +# W64-FAKE16: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] 0x05,0x78,0x53,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05 # W32-REAL16: v_mad_i16_e64_dpp v5.h, v1.h, v2.h, v3.h op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x78,0x53,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3.txt index 4c2060ad44b8a..3823859d26fad 100644 --- a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3.txt +++ b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3.txt @@ -2377,49 +2377,118 @@ # GFX12: v_fma_dx9_zero_f32 v255, -|0xaf123456|, -|vcc_hi|, null clamp div:2 ; encoding: [0xff,0x83,0x09,0xd6,0xff,0xd6,0xf0,0x79,0x56,0x34,0x12,0xaf] 0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00 -# GFX12: v_fma_f16 v5, v1, v2, s3 ; encoding: [0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00] +# W32-REAL16: v_fma_f16 v5.l, v1.l, v2.l, s3 ; encoding: [0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00] +# W32-FAKE16: v_fma_f16 v5, v1, v2, s3 ; encoding: [0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00] +# W64-REAL16: v_fma_f16 v5.l, v1.l, v2.l, s3 ; encoding: [0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00] +# W64-FAKE16: v_fma_f16 v5, v1, v2, s3 ; encoding: [0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00] 0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01 -# GFX12: v_fma_f16 v5, v255, s2, s105 ; encoding: [0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01] +# W32-REAL16: v_fma_f16 v5.l, v255.l, s2, s105 ; encoding: [0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01] +# W32-FAKE16: v_fma_f16 v5, v255, s2, s105 ; encoding: [0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01] +# W64-REAL16: v_fma_f16 v5.l, v255.l, s2, s105 ; encoding: [0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01] +# W64-FAKE16: v_fma_f16 v5, v255, s2, s105 ; encoding: [0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01] 0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01 -# GFX12: v_fma_f16 v5, s1, v255, exec_hi ; encoding: [0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01] +# W32-REAL16: v_fma_f16 v5.l, s1, v255.l, exec_hi ; encoding: [0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01] +# W32-FAKE16: v_fma_f16 v5, s1, v255, exec_hi ; encoding: [0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01] +# W64-REAL16: v_fma_f16 v5.l, s1, v255.l, exec_hi ; encoding: [0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01] +# W64-FAKE16: v_fma_f16 v5, s1, v255, exec_hi ; encoding: [0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01] 0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01 -# GFX12: v_fma_f16 v5, s105, s105, exec_lo ; encoding: [0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01] +# W32-REAL16: v_fma_f16 v5.l, s105, s105, exec_lo ; encoding: [0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01] +# W32-FAKE16: v_fma_f16 v5, s105, s105, exec_lo ; encoding: [0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01] +# W64-REAL16: v_fma_f16 v5.l, s105, s105, exec_lo ; encoding: [0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01] +# W64-FAKE16: v_fma_f16 v5, s105, s105, exec_lo ; encoding: [0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01] 0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04 -# GFX12: v_fma_f16 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04] +# W32-REAL16: v_fma_f16 v5.l, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04] +# W32-FAKE16: v_fma_f16 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04] +# W64-REAL16: v_fma_f16 v5.l, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04] +# W64-FAKE16: v_fma_f16 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04] 0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00 -# GFX12: v_fma_f16 v5, vcc_hi, 0xfe0b, v255 ; encoding: [0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] +# W32-REAL16: v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.l ; encoding: [0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] +# W32-FAKE16: v_fma_f16 v5, vcc_hi, 0xfe0b, v255 ; encoding: [0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] +# W64-REAL16: v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.l ; encoding: [0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] +# W64-FAKE16: v_fma_f16 v5, vcc_hi, 0xfe0b, v255 ; encoding: [0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] 0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1 -# GFX12: v_fma_f16 v5, -|ttmp15|, -|src_scc|, -|ttmp15| ; encoding: [0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1] +# W32-REAL16: v_fma_f16 v5.l, -|ttmp15|, -|src_scc|, -|ttmp15| ; encoding: [0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1] +# W32-FAKE16: v_fma_f16 v5, -|ttmp15|, -|src_scc|, -|ttmp15| ; encoding: [0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1] +# W64-REAL16: v_fma_f16 v5.l, -|ttmp15|, -|src_scc|, -|ttmp15| ; encoding: [0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1] +# W64-FAKE16: v_fma_f16 v5, -|ttmp15|, -|src_scc|, -|ttmp15| ; encoding: [0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1] 0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01 -# GFX12: v_fma_f16 v5, m0, 0.5, m0 ; encoding: [0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01] +# W32-REAL16: v_fma_f16 v5.l, m0, 0.5, m0 ; encoding: [0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01] +# W32-FAKE16: v_fma_f16 v5, m0, 0.5, m0 ; encoding: [0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01] +# W64-REAL16: v_fma_f16 v5.l, m0, 0.5, m0 ; encoding: [0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01] +# W64-FAKE16: v_fma_f16 v5, m0, 0.5, m0 ; encoding: [0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01] 0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01 -# GFX12: v_fma_f16 v5, |exec_lo|, -1, vcc_hi ; encoding: [0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01] +# W32-REAL16: v_fma_f16 v5.l, |exec_lo|, -1, vcc_hi ; encoding: [0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01] +# W32-FAKE16: v_fma_f16 v5, |exec_lo|, -1, vcc_hi ; encoding: [0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01] +# W64-REAL16: v_fma_f16 v5.l, |exec_lo|, -1, vcc_hi ; encoding: [0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01] +# W64-FAKE16: v_fma_f16 v5, |exec_lo|, -1, vcc_hi ; encoding: [0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01] 0x05,0x05,0x48,0xd6,0x7f,0xf8,0xa8,0xa1 -# GFX12: v_fma_f16 v5, -|exec_hi|, null, -|vcc_lo| ; encoding: [0x05,0x05,0x48,0xd6,0x7f,0xf8,0xa8,0xa1] +# W32-REAL16: v_fma_f16 v5.l, -|exec_hi|, null, -|vcc_lo| ; encoding: [0x05,0x05,0x48,0xd6,0x7f,0xf8,0xa8,0xa1] +# W32-FAKE16: v_fma_f16 v5, -|exec_hi|, null, -|vcc_lo| ; encoding: [0x05,0x05,0x48,0xd6,0x7f,0xf8,0xa8,0xa1] +# W64-REAL16: v_fma_f16 v5.l, -|exec_hi|, null, -|vcc_lo| ; encoding: [0x05,0x05,0x48,0xd6,0x7f,0xf8,0xa8,0xa1] +# W64-FAKE16: v_fma_f16 v5, -|exec_hi|, null, -|vcc_lo| ; encoding: [0x05,0x05,0x48,0xd6,0x7f,0xf8,0xa8,0xa1] 0x05,0x7c,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00 -# GFX12: v_fma_f16 v5, null, exec_lo, -|0xfe0b| op_sel:[1,1,1,1] ; encoding: [0x05,0x7c,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00] +# W32-REAL16: v_fma_f16 v5.h, null, exec_lo, -|0xfe0b| op_sel:[1,1,1,1] ; encoding: [0x05,0x7c,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00] +# W32-FAKE16: v_fma_f16 v5, null, exec_lo, -|0xfe0b| op_sel:[1,1,1,1] ; encoding: [0x05,0x7c,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00] +# W64-REAL16: v_fma_f16 v5.h, null, exec_lo, -|0xfe0b| op_sel:[1,1,1,1] ; encoding: [0x05,0x7c,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00] +# W64-FAKE16: v_fma_f16 v5, null, exec_lo, -|0xfe0b| op_sel:[1,1,1,1] ; encoding: [0x05,0x7c,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00] 0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3 -# GFX12: v_fma_f16 v5, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] ; encoding: [0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3] +# W32-REAL16: v_fma_f16 v5.l, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] ; encoding: [0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3] +# W32-FAKE16: v_fma_f16 v5, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] ; encoding: [0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3] +# W64-REAL16: v_fma_f16 v5.l, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] ; encoding: [0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3] +# W64-FAKE16: v_fma_f16 v5, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] ; encoding: [0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3] 0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43 -# GFX12: v_fma_f16 v5, 0.5, -m0, 0.5 op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43] +# W32-REAL16: v_fma_f16 v5.l, 0.5, -m0, 0.5 op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43] +# W32-FAKE16: v_fma_f16 v5, 0.5, -m0, 0.5 op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43] +# W64-REAL16: v_fma_f16 v5.l, 0.5, -m0, 0.5 op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43] +# W64-FAKE16: v_fma_f16 v5, 0.5, -m0, 0.5 op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43] 0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23 -# GFX12: v_fma_f16 v5, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] ; encoding: [0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23] +# W32-REAL16: v_fma_f16 v5.l, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] ; encoding: [0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23] +# W32-FAKE16: v_fma_f16 v5, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] ; encoding: [0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23] +# W64-REAL16: v_fma_f16 v5.l, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] ; encoding: [0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23] +# W64-FAKE16: v_fma_f16 v5, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] ; encoding: [0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23] 0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00 -# GFX12: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] +# W32-REAL16: v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] +# W32-FAKE16: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] +# W64-REAL16: v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] +# W64-FAKE16: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] + +0x05,0x08,0x48,0xd6,0xff,0x05,0xa4,0x01 +# W32-REAL16: v_fma_f16 v5.l, v255.h, s2, s105 op_sel:[1,0,0,0] ; encoding: [0x05,0x08,0x48,0xd6,0xff,0x05,0xa4,0x01] +# W32-FAKE16: v_fma_f16 v5, v255, s2, s105 op_sel:[1,0,0,0] ; encoding: [0x05,0x08,0x48,0xd6,0xff,0x05,0xa4,0x01] +# W64-REAL16: v_fma_f16 v5.l, v255.h, s2, s105 op_sel:[1,0,0,0] ; encoding: [0x05,0x08,0x48,0xd6,0xff,0x05,0xa4,0x01] +# W64-FAKE16: v_fma_f16 v5, v255, s2, s105 op_sel:[1,0,0,0] ; encoding: [0x05,0x08,0x48,0xd6,0xff,0x05,0xa4,0x01] + +0x05,0x10,0x48,0xd6,0x01,0xfe,0xff,0x01 +# W32-REAL16: v_fma_f16 v5.l, s1, v255.h, exec_hi op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0x01,0xfe,0xff,0x01] +# W32-FAKE16: v_fma_f16 v5, s1, v255, exec_hi op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0x01,0xfe,0xff,0x01] +# W64-REAL16: v_fma_f16 v5.l, s1, v255.h, exec_hi op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0x01,0xfe,0xff,0x01] +# W64-FAKE16: v_fma_f16 v5, s1, v255, exec_hi op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0x01,0xfe,0xff,0x01] + +0x05,0x20,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00 +# W32-REAL16: v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] +# W32-FAKE16: v_fma_f16 v5, vcc_hi, 0xfe0b, v255 op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] +# W64-REAL16: v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] +# W64-FAKE16: v_fma_f16 v5, vcc_hi, 0xfe0b, v255 op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00] + +0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00 +# W32-REAL16: v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] +# W32-FAKE16: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] +# W64-REAL16: v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] +# W64-FAKE16: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00] 0x05,0x00,0x13,0xd6,0x01,0x05,0x0e,0x00 # GFX12: v_fma_f32 v5, v1, v2, s3 ; encoding: [0x05,0x00,0x13,0xd6,0x01,0x05,0x0e,0x00] diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_dpp16.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_dpp16.txt index c64fe39d32558..f8bc3739cd104 100644 --- a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_dpp16.txt +++ b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_dpp16.txt @@ -4764,49 +4764,124 @@ # W64-FAKE16: v_div_fixup_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x54,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] 0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff -# GFX12: v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] 0x05,0x00,0x48,0xd6,0xfa,0x06,0x0c,0x04,0x01,0x1b,0x00,0xff -# GFX12: v_fma_f16_e64_dpp v5, v1, s3, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x06,0x0c,0x04,0x01,0x1b,0x00,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, s3, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x06,0x0c,0x04,0x01,0x1b,0x00,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, s3, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x06,0x0c,0x04,0x01,0x1b,0x00,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, s3, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x06,0x0c,0x04,0x01,0x1b,0x00,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, s3, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x06,0x0c,0x04,0x01,0x1b,0x00,0xff] 0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff -# GFX12: v_fma_f16_e64_dpp v5, v1, v2, v255 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] 0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x40,0x01,0xff -# GFX12: v_fma_f16_e64_dpp v5, v1, v2, s3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x40,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x40,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, s3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x40,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x40,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, s3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x40,0x01,0xff] 0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x41,0x01,0xff -# GFX12: v_fma_f16_e64_dpp v5, v1, v2, s105 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x41,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x41,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, s105 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x41,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x41,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, s105 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x41,0x01,0xff] 0x05,0x00,0x48,0xd6,0xfa,0x04,0xee,0x01,0x01,0x01,0x01,0xff -# GFX12: v_fma_f16_e64_dpp v5, v1, v2, ttmp15 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xee,0x01,0x01,0x01,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, ttmp15 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xee,0x01,0x01,0x01,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, ttmp15 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xee,0x01,0x01,0x01,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, ttmp15 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xee,0x01,0x01,0x01,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, ttmp15 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xee,0x01,0x01,0x01,0x01,0xff] 0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff -# GFX12: v_fma_f16_e64_dpp v5, v1, v2, vcc_hi row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, vcc_hi row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, vcc_hi row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff] 0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff -# GFX12: v_fma_f16_e64_dpp v5, v1, v2, vcc_lo row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, vcc_lo row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, vcc_lo row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff] 0x05,0x01,0x48,0xd6,0xfa,0x04,0xf6,0x81,0x01,0x1f,0x01,0xff -# GFX12: v_fma_f16_e64_dpp v5, |v1|, v2, -m0 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x01,0x48,0xd6,0xfa,0x04,0xf6,0x81,0x01,0x1f,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -m0 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x01,0x48,0xd6,0xfa,0x04,0xf6,0x81,0x01,0x1f,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, |v1|, v2, -m0 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x01,0x48,0xd6,0xfa,0x04,0xf6,0x81,0x01,0x1f,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -m0 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x01,0x48,0xd6,0xfa,0x04,0xf6,0x81,0x01,0x1f,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, |v1|, v2, -m0 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x01,0x48,0xd6,0xfa,0x04,0xf6,0x81,0x01,0x1f,0x01,0xff] 0x05,0x02,0x48,0xd6,0xfa,0x04,0xfe,0x41,0x01,0x21,0x01,0xff -# GFX12: v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x02,0x48,0xd6,0xfa,0x04,0xfe,0x41,0x01,0x21,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, exec_hi row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x02,0x48,0xd6,0xfa,0x04,0xfe,0x41,0x01,0x21,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x02,0x48,0xd6,0xfa,0x04,0xfe,0x41,0x01,0x21,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, exec_hi row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x02,0x48,0xd6,0xfa,0x04,0xfe,0x41,0x01,0x21,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x02,0x48,0xd6,0xfa,0x04,0xfe,0x41,0x01,0x21,0x01,0xff] 0x05,0x7c,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff -# GFX12: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x7c,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.h, -v1.h, v2.h, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x7c,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x7c,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.h, -v1.h, v2.h, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x7c,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x7c,0x48,0xd6,0xfa,0x04,0xfa,0x21,0x01,0x2f,0x01,0xff] 0x05,0x0b,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff -# GFX12: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x0b,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.h|, -|v2.l|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x0b,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x0b,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.h|, -|v2.l|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x0b,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x0b,0x48,0xd6,0xfa,0x04,0xf2,0x61,0x01,0x50,0x01,0xff] 0x05,0x15,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01 -# GFX12: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x15,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.h, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x15,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x15,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.h, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x15,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x15,0x48,0xd6,0xfa,0x04,0x06,0xa3,0x01,0x5f,0x01,0x01] 0x05,0x26,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x01,0x13 -# GFX12: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x26,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x01,0x13] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x26,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x01,0x13] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x26,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x01,0x13] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x26,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x01,0x13] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x26,0x48,0xd6,0xfa,0x04,0xc2,0xc3,0x01,0x60,0x01,0x13] 0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30 -# GFX12: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] +# W32-REAL16: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] +# W32-FAKE16: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] +# W64-REAL16: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] +# W64-FAKE16: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] + +0x05,0x78,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff +# W32-REAL16: v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h op_sel:[1,1,1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x78,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 op_sel:[1,1,1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x78,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h op_sel:[1,1,1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x78,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 op_sel:[1,1,1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x78,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] + +0x05,0x20,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h op_sel:[0,0,1,0] quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h op_sel:[0,0,1,0] quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0xe4,0x00,0xff] + +0x05,0x0a,0x48,0xd6,0xfa,0x04,0x06,0x23,0x01,0x5f,0x01,0x01 +# W32-REAL16: v_fma_f16_e64_dpp v5.l, -v1.h, |v2.l|, -1 op_sel:[1,0,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x0a,0x48,0xd6,0xfa,0x04,0x06,0x23,0x01,0x5f,0x01,0x01] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -v1, |v2|, -1 op_sel:[1,0,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x0a,0x48,0xd6,0xfa,0x04,0x06,0x23,0x01,0x5f,0x01,0x01] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, -v1.h, |v2.l|, -1 op_sel:[1,0,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x0a,0x48,0xd6,0xfa,0x04,0x06,0x23,0x01,0x5f,0x01,0x01] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -v1, |v2|, -1 op_sel:[1,0,0,0] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x0a,0x48,0xd6,0xfa,0x04,0x06,0x23,0x01,0x5f,0x01,0x01] + +0x05,0x13,0x48,0xd6,0xfa,0x04,0xc2,0x63,0x01,0x60,0x01,0x13 +# W32-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 op_sel:[0,1,0,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x13,0x48,0xd6,0xfa,0x04,0xc2,0x63,0x01,0x60,0x01,0x13] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, 0.5 op_sel:[0,1,0,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x13,0x48,0xd6,0xfa,0x04,0xc2,0x63,0x01,0x60,0x01,0x13] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 op_sel:[0,1,0,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x13,0x48,0xd6,0xfa,0x04,0xc2,0x63,0x01,0x60,0x01,0x13] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, 0.5 op_sel:[0,1,0,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x13,0x48,0xd6,0xfa,0x04,0xc2,0x63,0x01,0x60,0x01,0x13] + +0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30 +# W32-REAL16: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] +# W32-FAKE16: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] +# W64-REAL16: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] +# W64-FAKE16: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x0d,0x30] 0x05,0x00,0x53,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff # W32-REAL16: v_mad_i16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x53,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff] diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_dpp8.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_dpp8.txt index 9ed20c70c17a2..3e5b796ee97b7 100644 --- a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_dpp8.txt +++ b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_dpp8.txt @@ -2814,52 +2814,130 @@ # W64-FAKE16: v_div_fixup_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x54,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] 0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05 -# GFX12: v_fma_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] 0x05,0x00,0x48,0xd6,0xe9,0x06,0x0c,0x04,0x01,0x77,0x39,0x05 -# GFX12: v_fma_f16_e64_dpp v5, v1, s3, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x06,0x0c,0x04,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, s3, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x06,0x0c,0x04,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, s3, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x06,0x0c,0x04,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, s3, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x06,0x0c,0x04,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, s3, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x06,0x0c,0x04,0x01,0x77,0x39,0x05] 0x05,0x00,0x48,0xd6,0xe9,0xec,0x0d,0x04,0x01,0x77,0x39,0x05 -# GFX12: v_fma_f16_e64_dpp v5, v1, 4.0, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0xec,0x0d,0x04,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, 4.0, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0xec,0x0d,0x04,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, 4.0, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0xec,0x0d,0x04,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, 4.0, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0xec,0x0d,0x04,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, 4.0, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0xec,0x0d,0x04,0x01,0x77,0x39,0x05] 0x05,0x00,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05 -# GFX12: v_fma_f16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] 0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05 -# GFX12: v_fma_f16_e64_dpp v5, v1, v2, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05] 0x05,0x00,0x48,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05 -# GFX12: v_fma_f16_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05] 0x05,0x00,0x48,0xd6,0xe9,0x04,0xee,0x01,0x01,0x77,0x39,0x05 -# GFX12: v_fma_f16_e64_dpp v5, v1, v2, ttmp15 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xee,0x01,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, ttmp15 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xee,0x01,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, ttmp15 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xee,0x01,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, ttmp15 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xee,0x01,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, ttmp15 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xee,0x01,0x01,0x77,0x39,0x05] 0x05,0x00,0x48,0xd6,0xe9,0x04,0xae,0x01,0x01,0x77,0x39,0x05 -# GFX12: v_fma_f16_e64_dpp v5, v1, v2, vcc_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xae,0x01,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xae,0x01,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, vcc_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xae,0x01,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xae,0x01,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, vcc_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xae,0x01,0x01,0x77,0x39,0x05] 0x05,0x00,0x48,0xd6,0xe9,0x04,0xaa,0x01,0x01,0x77,0x39,0x05 -# GFX12: v_fma_f16_e64_dpp v5, v1, v2, vcc_lo dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xaa,0x01,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xaa,0x01,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, vcc_lo dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xaa,0x01,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xaa,0x01,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, vcc_lo dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x48,0xd6,0xe9,0x04,0xaa,0x01,0x01,0x77,0x39,0x05] 0x05,0x01,0x48,0xd6,0xe9,0x04,0xf6,0x81,0x01,0x77,0x39,0x05 -# GFX12: v_fma_f16_e64_dpp v5, |v1|, v2, -m0 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x48,0xd6,0xe9,0x04,0xf6,0x81,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -m0 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x48,0xd6,0xe9,0x04,0xf6,0x81,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, |v1|, v2, -m0 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x48,0xd6,0xe9,0x04,0xf6,0x81,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -m0 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x48,0xd6,0xe9,0x04,0xf6,0x81,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, |v1|, v2, -m0 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x01,0x48,0xd6,0xe9,0x04,0xf6,0x81,0x01,0x77,0x39,0x05] 0x05,0x02,0x48,0xd6,0xe9,0x04,0xfe,0x41,0x01,0x77,0x39,0x05 -# GFX12: v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x48,0xd6,0xe9,0x04,0xfe,0x41,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, exec_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x48,0xd6,0xe9,0x04,0xfe,0x41,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x48,0xd6,0xe9,0x04,0xfe,0x41,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, exec_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x48,0xd6,0xe9,0x04,0xfe,0x41,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, -|v2|, exec_hi dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x02,0x48,0xd6,0xe9,0x04,0xfe,0x41,0x01,0x77,0x39,0x05] 0x05,0x7c,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05 -# GFX12: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x7c,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.h, -v1.h, v2.h, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x7c,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x7c,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.h, -v1.h, v2.h, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x7c,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -v1, v2, |exec_lo| op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x7c,0x48,0xd6,0xe9,0x04,0xfa,0x21,0x01,0x77,0x39,0x05] 0x05,0x0b,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05 -# GFX12: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0b,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.h|, -|v2.l|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0b,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0b,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.h|, -|v2.l|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0b,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, null op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0b,0x48,0xd6,0xe9,0x04,0xf2,0x61,0x01,0x77,0x39,0x05] 0x05,0x15,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05 -# GFX12: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x15,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.h, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x15,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x15,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.l|, v2.h, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x15,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, v2, -|-1| op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x15,0x48,0xd6,0xe9,0x04,0x06,0xa3,0x01,0x77,0x39,0x05] 0x05,0x26,0x48,0xd6,0xe9,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05 -# GFX12: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x26,0x48,0xd6,0xe9,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x26,0x48,0xd6,0xe9,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x26,0x48,0xd6,0xe9,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, -|v2.l|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x26,0x48,0xd6,0xe9,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, -|v2|, -|0.5| op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x26,0x48,0xd6,0xe9,0x04,0xc2,0xc3,0x01,0x77,0x39,0x05] 0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00 -# GFX12: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +# W32-REAL16: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +# W32-FAKE16: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +# W64-REAL16: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +# W64-FAKE16: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] + +0x05,0x78,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05 +# W32-REAL16: v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x78,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x78,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.h, v1.h, v2.h, v3.h op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x78,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v3 op_sel:[1,1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x78,0x48,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05] + +0x05,0x20,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05 +# W32-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, v1, v2, v255 op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05] + +0x05,0x0a,0x48,0xd6,0xe9,0x04,0x06,0x23,0x01,0x77,0x39,0x05 +# W32-REAL16: v_fma_f16_e64_dpp v5.l, -v1.h, |v2.l|, -1 op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0a,0x48,0xd6,0xe9,0x04,0x06,0x23,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -v1, |v2|, -1 op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0a,0x48,0xd6,0xe9,0x04,0x06,0x23,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, -v1.h, |v2.l|, -1 op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0a,0x48,0xd6,0xe9,0x04,0x06,0x23,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -v1, |v2|, -1 op_sel:[1,0,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x0a,0x48,0xd6,0xe9,0x04,0x06,0x23,0x01,0x77,0x39,0x05] + +0x05,0x13,0x48,0xd6,0xe9,0x04,0xc2,0x63,0x01,0x77,0x39,0x05 +# W32-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x13,0x48,0xd6,0xe9,0x04,0xc2,0x63,0x01,0x77,0x39,0x05] +# W32-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, 0.5 op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x13,0x48,0xd6,0xe9,0x04,0xc2,0x63,0x01,0x77,0x39,0x05] +# W64-REAL16: v_fma_f16_e64_dpp v5.l, -|v1.l|, -|v2.h|, 0.5 op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x13,0x48,0xd6,0xe9,0x04,0xc2,0x63,0x01,0x77,0x39,0x05] +# W64-FAKE16: v_fma_f16_e64_dpp v5, -|v1|, -|v2|, 0.5 op_sel:[0,1,0,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x13,0x48,0xd6,0xe9,0x04,0xc2,0x63,0x01,0x77,0x39,0x05] + +0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00 +# W32-REAL16: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +# W32-FAKE16: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +# W64-REAL16: v_fma_f16_e64_dpp v255.h, -|v255.l|, -|v255.l|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] +# W64-FAKE16: v_fma_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| op_sel:[0,0,0,1] clamp dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc7,0x48,0xd6,0xea,0xfe,0xf7,0xe3,0xff,0x00,0x00,0x00] 0x05,0x00,0x53,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05 # W32-REAL16: v_mad_i16_e64_dpp v5.l, v1.l, v2.l, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x53,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05]