llvm · broxigarchen · Jan 3, 2025 · Dec 20, 2024
diff --git a/llvm/lib/Target/AMDGPU/VOP1Instructions.td b/llvm/lib/Target/AMDGPU/VOP1Instructions.td
@@ -1042,7 +1042,7 @@ defm V_FLOOR_F16_t16         : VOP1_Real_FULL_t16_gfx11_gfx12<0x05b, "v_floor_f1
 defm V_FLOOR_F16_fake16      : VOP1_Real_FULL_t16_gfx11_gfx12<0x05b, "v_floor_f16">;
 defm V_CEIL_F16_t16          : VOP1_Real_FULL_t16_gfx11_gfx12<0x05c, "v_ceil_f16">;
 defm V_CEIL_F16_fake16       : VOP1_Real_FULL_t16_gfx11_gfx12<0x05c, "v_ceil_f16">;
-defm V_TRUNC_F16_fake16      : VOP1_Real_FULL_t16_gfx11_gfx12<0x05d, "v_trunc_f16">;
+defm V_TRUNC_F16             : VOP1_Real_FULL_t16_and_fake16_gfx11_gfx12<0x05d, "v_trunc_f16">;
 defm V_RNDNE_F16_fake16      : VOP1_Real_FULL_t16_gfx11_gfx12<0x05e, "v_rndne_f16">;
 defm V_FRACT_F16_fake16      : VOP1_Real_FULL_t16_gfx11_gfx12<0x05f, "v_fract_f16">;
 defm V_SIN_F16_fake16        : VOP1_Real_FULL_t16_gfx11_gfx12<0x060, "v_sin_f16">;

diff --git a/llvm/test/CodeGen/AMDGPU/llvm.trunc.f16.ll b/llvm/test/CodeGen/AMDGPU/llvm.trunc.f16.ll
@@ -2,6 +2,7 @@
 ; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefixes=SI %s
 ; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=VI %s
 ; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=gfx1100 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX11 %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=gfx1200 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX12 %s
 
 declare half @llvm.trunc.f16(half %a)
 declare <2 x half> @llvm.trunc.v2f16(<2 x half> %a)
@@ -62,6 +63,24 @@ define amdgpu_kernel void @trunc_f16(
 ; GFX11-NEXT:    v_trunc_f16_e32 v0, v0
 ; GFX11-NEXT:    buffer_store_b16 v0, off, s[4:7], 0
 ; GFX11-NEXT:    s_endpgm
+;
+; GFX12-LABEL: trunc_f16:
+; GFX12:       ; %bb.0: ; %entry
+; GFX12-NEXT:    s_load_b128 s[0:3], s[4:5], 0x24
+; GFX12-NEXT:    s_mov_b32 s6, -1
+; GFX12-NEXT:    s_mov_b32 s7, 0x31016000
+; GFX12-NEXT:    s_mov_b32 s10, s6
+; GFX12-NEXT:    s_mov_b32 s11, s7
+; GFX12-NEXT:    s_wait_kmcnt 0x0
+; GFX12-NEXT:    s_mov_b32 s8, s2
+; GFX12-NEXT:    s_mov_b32 s9, s3
+; GFX12-NEXT:    s_mov_b32 s4, s0
+; GFX12-NEXT:    buffer_load_u16 v0, off, s[8:11], null
+; GFX12-NEXT:    s_mov_b32 s5, s1
+; GFX12-NEXT:    s_wait_loadcnt 0x0
+; GFX12-NEXT:    v_trunc_f16_e32 v0, v0
+; GFX12-NEXT:    buffer_store_b16 v0, off, s[4:7], null
+; GFX12-NEXT:    s_endpgm
     ptr addrspace(1) %r,
     ptr addrspace(1) %a) {
 entry:
@@ -147,6 +166,28 @@ define amdgpu_kernel void @trunc_v2f16(
 ; GFX11-NEXT:    v_pack_b32_f16 v0, v0, v1
 ; GFX11-NEXT:    buffer_store_b32 v0, off, s[4:7], 0
 ; GFX11-NEXT:    s_endpgm
+;
+; GFX12-LABEL: trunc_v2f16:
+; GFX12:       ; %bb.0: ; %entry
+; GFX12-NEXT:    s_load_b128 s[0:3], s[4:5], 0x24
+; GFX12-NEXT:    s_mov_b32 s6, -1
+; GFX12-NEXT:    s_mov_b32 s7, 0x31016000
+; GFX12-NEXT:    s_mov_b32 s10, s6
+; GFX12-NEXT:    s_mov_b32 s11, s7
+; GFX12-NEXT:    s_wait_kmcnt 0x0
+; GFX12-NEXT:    s_mov_b32 s8, s2
+; GFX12-NEXT:    s_mov_b32 s9, s3
+; GFX12-NEXT:    s_mov_b32 s4, s0
+; GFX12-NEXT:    buffer_load_b32 v0, off, s[8:11], null
+; GFX12-NEXT:    s_mov_b32 s5, s1
+; GFX12-NEXT:    s_wait_loadcnt 0x0
+; GFX12-NEXT:    v_lshrrev_b32_e32 v1, 16, v0
+; GFX12-NEXT:    v_trunc_f16_e32 v0, v0
+; GFX12-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX12-NEXT:    v_trunc_f16_e32 v1, v1
+; GFX12-NEXT:    v_pack_b32_f16 v0, v0, v1
+; GFX12-NEXT:    buffer_store_b32 v0, off, s[4:7], null
+; GFX12-NEXT:    s_endpgm
     ptr addrspace(1) %r,
     ptr addrspace(1) %a) {
 entry:

diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop1.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop1.s
@@ -3524,50 +3524,65 @@ v_swaprel_b32 v5, v1
 v_swaprel_b32 v255, v255
 // GFX11: v_swaprel_b32 v255, v255                ; encoding: [0xff,0xd1,0xfe,0x7f]
 
-v_trunc_f16 v5, v1
-// GFX11: v_trunc_f16_e32 v5, v1                  ; encoding: [0x01,0xbb,0x0a,0x7e]
+v_trunc_f16 v5.l, v1.l
+// GFX11: v_trunc_f16_e32 v5.l, v1.l              ; encoding: [0x01,0xbb,0x0a,0x7e]
 
-v_trunc_f16 v5, v127
-// GFX11: v_trunc_f16_e32 v5, v127                ; encoding: [0x7f,0xbb,0x0a,0x7e]
+v_trunc_f16 v5.l, v127.l
+// GFX11: v_trunc_f16_e32 v5.l, v127.l            ; encoding: [0x7f,0xbb,0x0a,0x7e]
 
-v_trunc_f16 v5, s1
-// GFX11: v_trunc_f16_e32 v5, s1                  ; encoding: [0x01,0xba,0x0a,0x7e]
+v_trunc_f16 v5.l, s1
+// GFX11: v_trunc_f16_e32 v5.l, s1                ; encoding: [0x01,0xba,0x0a,0x7e]
 
-v_trunc_f16 v5, s105
-// GFX11: v_trunc_f16_e32 v5, s105                ; encoding: [0x69,0xba,0x0a,0x7e]
+v_trunc_f16 v5.l, s105
+// GFX11: v_trunc_f16_e32 v5.l, s105              ; encoding: [0x69,0xba,0x0a,0x7e]
 
-v_trunc_f16 v5, vcc_lo
-// GFX11: v_trunc_f16_e32 v5, vcc_lo              ; encoding: [0x6a,0xba,0x0a,0x7e]
+v_trunc_f16 v5.l, vcc_lo
+// GFX11: v_trunc_f16_e32 v5.l, vcc_lo            ; encoding: [0x6a,0xba,0x0a,0x7e]
 
-v_trunc_f16 v5, vcc_hi
-// GFX11: v_trunc_f16_e32 v5, vcc_hi              ; encoding: [0x6b,0xba,0x0a,0x7e]
+v_trunc_f16 v5.l, vcc_hi
+// GFX11: v_trunc_f16_e32 v5.l, vcc_hi            ; encoding: [0x6b,0xba,0x0a,0x7e]
 
-v_trunc_f16 v5, ttmp15
-// GFX11: v_trunc_f16_e32 v5, ttmp15              ; encoding: [0x7b,0xba,0x0a,0x7e]
+v_trunc_f16 v5.l, ttmp15
+// GFX11: v_trunc_f16_e32 v5.l, ttmp15            ; encoding: [0x7b,0xba,0x0a,0x7e]
 
-v_trunc_f16 v5, m0
-// GFX11: v_trunc_f16_e32 v5, m0                  ; encoding: [0x7d,0xba,0x0a,0x7e]
+v_trunc_f16 v5.l, m0
+// GFX11: v_trunc_f16_e32 v5.l, m0                ; encoding: [0x7d,0xba,0x0a,0x7e]
 
-v_trunc_f16 v5, exec_lo
-// GFX11: v_trunc_f16_e32 v5, exec_lo             ; encoding: [0x7e,0xba,0x0a,0x7e]
+v_trunc_f16 v5.l, exec_lo
+// GFX11: v_trunc_f16_e32 v5.l, exec_lo           ; encoding: [0x7e,0xba,0x0a,0x7e]
 
-v_trunc_f16 v5, exec_hi
-// GFX11: v_trunc_f16_e32 v5, exec_hi             ; encoding: [0x7f,0xba,0x0a,0x7e]
+v_trunc_f16 v5.l, exec_hi
+// GFX11: v_trunc_f16_e32 v5.l, exec_hi           ; encoding: [0x7f,0xba,0x0a,0x7e]
 
-v_trunc_f16 v5, null
-// GFX11: v_trunc_f16_e32 v5, null                ; encoding: [0x7c,0xba,0x0a,0x7e]
+v_trunc_f16 v5.l, null
+// GFX11: v_trunc_f16_e32 v5.l, null              ; encoding: [0x7c,0xba,0x0a,0x7e]
 
-v_trunc_f16 v5, -1
-// GFX11: v_trunc_f16_e32 v5, -1                  ; encoding: [0xc1,0xba,0x0a,0x7e]
+v_trunc_f16 v5.l, -1
+// GFX11: v_trunc_f16_e32 v5.l, -1                ; encoding: [0xc1,0xba,0x0a,0x7e]
 
-v_trunc_f16 v5, 0.5
-// GFX11: v_trunc_f16_e32 v5, 0.5                 ; encoding: [0xf0,0xba,0x0a,0x7e]
+v_trunc_f16 v5.l, 0.5
+// GFX11: v_trunc_f16_e32 v5.l, 0.5               ; encoding: [0xf0,0xba,0x0a,0x7e]
 
-v_trunc_f16 v5, src_scc
-// GFX11: v_trunc_f16_e32 v5, src_scc             ; encoding: [0xfd,0xba,0x0a,0x7e]
+v_trunc_f16 v5.l, src_scc
+// GFX11: v_trunc_f16_e32 v5.l, src_scc           ; encoding: [0xfd,0xba,0x0a,0x7e]
 
-v_trunc_f16 v127, 0xfe0b
-// GFX11: v_trunc_f16_e32 v127, 0xfe0b            ; encoding: [0xff,0xba,0xfe,0x7e,0x0b,0xfe,0x00,0x00]
+v_trunc_f16 v127.l, 0xfe0b
+// GFX11: v_trunc_f16_e32 v127.l, 0xfe0b          ; encoding: [0xff,0xba,0xfe,0x7e,0x0b,0xfe,0x00,0x00]
+
+v_trunc_f16 v5.l, v1.h
+// GFX11: v_trunc_f16_e32 v5.l, v1.h              ; encoding: [0x81,0xbb,0x0a,0x7e]
+
+v_trunc_f16 v5.l, v127.h
+// GFX11: v_trunc_f16_e32 v5.l, v127.h            ; encoding: [0xff,0xbb,0x0a,0x7e]
+
+v_trunc_f16 v127.l, 0.5
+// GFX11: v_trunc_f16_e32 v127.l, 0.5             ; encoding: [0xf0,0xba,0xfe,0x7e]
+
+v_trunc_f16 v5.h, src_scc
+// GFX11: v_trunc_f16_e32 v5.h, src_scc           ; encoding: [0xfd,0xba,0x0a,0x7f]
+
+v_trunc_f16 v127.h, 0xfe0b
+// GFX11: v_trunc_f16_e32 v127.h, 0xfe0b          ; encoding: [0xff,0xba,0xfe,0x7f,0x0b,0xfe,0x00,0x00]
 
 v_trunc_f32 v5, v1
 // GFX11: v_trunc_f32_e32 v5, v1                  ; encoding: [0x01,0x43,0x0a,0x7e]

diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s
@@ -2732,47 +2732,56 @@ v_sqrt_f32 v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
 v_sqrt_f32 v255, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
 // GFX11: v_sqrt_f32_dpp v255, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0x66,0xfe,0x7f,0xff,0x6f,0x35,0x30]
 
-v_trunc_f16 v5, v1 quad_perm:[3,2,1,0]
-// GFX11: v_trunc_f16_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x1b,0x00,0xff]
+v_trunc_f16 v5.l, v1.l quad_perm:[3,2,1,0]
+// GFX11: v_trunc_f16_dpp v5.l, v1.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x1b,0x00,0xff]
 
-v_trunc_f16 v5, v1 quad_perm:[0,1,2,3]
-// GFX11: v_trunc_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0xe4,0x00,0xff]
+v_trunc_f16 v5.l, v1.l quad_perm:[0,1,2,3]
+// GFX11: v_trunc_f16_dpp v5.l, v1.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0xe4,0x00,0xff]
 
-v_trunc_f16 v5, v1 row_mirror
-// GFX11: v_trunc_f16_dpp v5, v1 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x40,0x01,0xff]
+v_trunc_f16 v5.l, v1.l row_mirror
+// GFX11: v_trunc_f16_dpp v5.l, v1.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x40,0x01,0xff]
 
-v_trunc_f16 v5, v1 row_half_mirror
-// GFX11: v_trunc_f16_dpp v5, v1 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x41,0x01,0xff]
+v_trunc_f16 v5.l, v1.l row_half_mirror
+// GFX11: v_trunc_f16_dpp v5.l, v1.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x41,0x01,0xff]
 
-v_trunc_f16 v5, v1 row_shl:1
-// GFX11: v_trunc_f16_dpp v5, v1 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x01,0x01,0xff]
+v_trunc_f16 v5.l, v1.l row_shl:1
+// GFX11: v_trunc_f16_dpp v5.l, v1.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x01,0x01,0xff]
 
-v_trunc_f16 v5, v1 row_shl:15
-// GFX11: v_trunc_f16_dpp v5, v1 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x0f,0x01,0xff]
+v_trunc_f16 v5.l, v1.l row_shl:15
+// GFX11: v_trunc_f16_dpp v5.l, v1.l row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x0f,0x01,0xff]
 
-v_trunc_f16 v5, v1 row_shr:1
-// GFX11: v_trunc_f16_dpp v5, v1 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x11,0x01,0xff]
+v_trunc_f16 v5.l, v1.l row_shr:1
+// GFX11: v_trunc_f16_dpp v5.l, v1.l row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x11,0x01,0xff]
 
-v_trunc_f16 v5, v1 row_shr:15
-// GFX11: v_trunc_f16_dpp v5, v1 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x1f,0x01,0xff]
+v_trunc_f16 v5.l, v1.l row_shr:15
+// GFX11: v_trunc_f16_dpp v5.l, v1.l row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x1f,0x01,0xff]
 
-v_trunc_f16 v5, v1 row_ror:1
-// GFX11: v_trunc_f16_dpp v5, v1 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x21,0x01,0xff]
+v_trunc_f16 v5.l, v1.l row_ror:1
+// GFX11: v_trunc_f16_dpp v5.l, v1.l row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x21,0x01,0xff]
 
-v_trunc_f16 v5, v1 row_ror:15
-// GFX11: v_trunc_f16_dpp v5, v1 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x2f,0x01,0xff]
+v_trunc_f16 v5.l, v1.l row_ror:15
+// GFX11: v_trunc_f16_dpp v5.l, v1.l row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x2f,0x01,0xff]
 
-v_trunc_f16 v5, v1 row_share:0 row_mask:0xf bank_mask:0xf
-// GFX11: v_trunc_f16_dpp v5, v1 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x50,0x01,0xff]
+v_trunc_f16 v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf
+// GFX11: v_trunc_f16_dpp v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x50,0x01,0xff]
 
-v_trunc_f16 v5, v1 row_share:15 row_mask:0x0 bank_mask:0x1
-// GFX11: v_trunc_f16_dpp v5, v1 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x5f,0x01,0x01]
+v_trunc_f16 v5.l, v1.l row_share:15 row_mask:0x0 bank_mask:0x1
+// GFX11: v_trunc_f16_dpp v5.l, v1.l row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x5f,0x01,0x01]
 
-v_trunc_f16 v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
-// GFX11: v_trunc_f16_dpp v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x60,0x09,0x13]
+v_trunc_f16 v5.l, v1.l row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1
+// GFX11: v_trunc_f16_dpp v5.l, v1.l row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0xba,0x0a,0x7e,0x01,0x60,0x09,0x13]
 
-v_trunc_f16 v127, -|v127| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
-// GFX11: v_trunc_f16_dpp v127, -|v127| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xba,0xfe,0x7e,0x7f,0x6f,0x35,0x30]
+v_trunc_f16 v127.l, -|v127.l| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1
+// GFX11: v_trunc_f16_dpp v127.l, -|v127.l| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xba,0xfe,0x7e,0x7f,0x6f,0x35,0x30]
+
+v_trunc_f16 v127.l, v127.l row_share:15 row_mask:0x0 bank_mask:0x1
+// GFX11: v_trunc_f16_dpp v127.l, v127.l row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xba,0xfe,0x7e,0x7f,0x5f,0x01,0x01]
+
+v_trunc_f16 v5.h, v1.h row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
+// GFX11: v_trunc_f16_dpp v5.h, v1.h row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0xba,0x0a,0x7f,0x81,0x60,0x09,0x13]
+
+v_trunc_f16 v127.h, -|v127.h| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
+// GFX11: v_trunc_f16_dpp v127.h, -|v127.h| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xba,0xfe,0x7f,0xff,0x6f,0x35,0x30]
 
 v_trunc_f32 v5, v1 quad_perm:[3,2,1,0]
 // GFX11: v_trunc_f32_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x42,0x0a,0x7e,0x01,0x1b,0x00,0xff]

diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp8.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp8.s
@@ -635,14 +635,23 @@ v_sqrt_f32 v5, v1 dpp8:[7,6,5,4,3,2,1,0] fi:1
 v_sqrt_f32 v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:0
 // GFX11: v_sqrt_f32_dpp v255, v255 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0x66,0xfe,0x7f,0xff,0x00,0x00,0x00]
 
-v_trunc_f16 v5, v1 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_trunc_f16_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xba,0x0a,0x7e,0x01,0x77,0x39,0x05]
+v_trunc_f16 v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_trunc_f16_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xba,0x0a,0x7e,0x01,0x77,0x39,0x05]
 
-v_trunc_f16 v5, v1 dpp8:[7,6,5,4,3,2,1,0] fi:1
-// GFX11: v_trunc_f16_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0xba,0x0a,0x7e,0x01,0x77,0x39,0x05]
+v_trunc_f16 v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] fi:1
+// GFX11: v_trunc_f16_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0xba,0x0a,0x7e,0x01,0x77,0x39,0x05]
 
-v_trunc_f16 v127, v127 dpp8:[0,0,0,0,0,0,0,0] fi:0
-// GFX11: v_trunc_f16_dpp v127, v127 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xba,0xfe,0x7e,0x7f,0x00,0x00,0x00]
+v_trunc_f16 v127.l, v127.l dpp8:[0,0,0,0,0,0,0,0]
+// GFX11: v_trunc_f16_dpp v127.l, v127.l dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xba,0xfe,0x7e,0x7f,0x00,0x00,0x00]
+
+v_trunc_f16 v127.l, v127.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_trunc_f16_dpp v127.l, v127.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xba,0xfe,0x7e,0x7f,0x77,0x39,0x05]
+
+v_trunc_f16 v5.h, v1.h dpp8:[7,6,5,4,3,2,1,0] fi:1
+// GFX11: v_trunc_f16_dpp v5.h, v1.h dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0xba,0x0a,0x7f,0x81,0x77,0x39,0x05]
+
+v_trunc_f16 v127.h, v127.h dpp8:[0,0,0,0,0,0,0,0] fi:0
+// GFX11: v_trunc_f16_dpp v127.h, v127.h dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xba,0xfe,0x7f,0xff,0x00,0x00,0x00]
 
 v_trunc_f32 v5, v1 dpp8:[7,6,5,4,3,2,1,0]
 // GFX11: v_trunc_f32_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0x42,0x0a,0x7e,0x01,0x77,0x39,0x05]

diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_err.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_err.s
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_mc_test_checks.py UTC_ARGS: --version 5
+// NOTE: Assertions have been autogenerated by utils/update_mc_test_checks.py UTC_ARGS: --version 5
 // RUN: not llvm-mc -triple=amdgcn -mcpu=gfx1100 -mattr=+real-true16,+wavefrontsize32 -show-encoding %s 2>&1 | FileCheck --check-prefix=GFX11 --implicit-check-not=error: %s
 // RUN: not llvm-mc -triple=amdgcn -mcpu=gfx1100 -mattr=+real-true16,+wavefrontsize64 -show-encoding %s 2>&1 | FileCheck --check-prefix=GFX11 --implicit-check-not=error: %s
 
@@ -794,6 +794,12 @@ v_swap_b16_e32 v128.l, v0.l
 v_trunc_f16_e32 v128, 0xfe0b
 // GFX11: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
 
+v_trunc_f16_e32 v128.h, 0xfe0b
+// GFX11: :[[@LINE-1]]:17: error: invalid operand for instruction
+
+v_trunc_f16_e32 v128.l, 0xfe0b
+// GFX11: :[[@LINE-1]]:17: error: invalid operand for instruction
+
 v_trunc_f16_e32 v255, v1
 // GFX11: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
 
@@ -803,6 +809,24 @@ v_trunc_f16_e32 v255, v1 dpp8:[7,6,5,4,3,2,1,0]
 v_trunc_f16_e32 v255, v1 quad_perm:[3,2,1,0]
 // GFX11: :[[@LINE-1]]:26: error: invalid operand for instruction
 
+v_trunc_f16_e32 v255.h, v1.h
+// GFX11: :[[@LINE-1]]:17: error: invalid operand for instruction
+
+v_trunc_f16_e32 v255.h, v1.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:17: error: invalid operand for instruction
+
+v_trunc_f16_e32 v255.h, v1.h quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:17: error: invalid operand for instruction
+
+v_trunc_f16_e32 v255.l, v1.l
+// GFX11: :[[@LINE-1]]:17: error: invalid operand for instruction
+
+v_trunc_f16_e32 v255.l, v1.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:17: error: invalid operand for instruction
+
+v_trunc_f16_e32 v255.l, v1.l quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:17: error: invalid operand for instruction
+
 v_trunc_f16_e32 v5, v199
 // GFX11: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
 
@@ -811,3 +835,21 @@ v_trunc_f16_e32 v5, v199 dpp8:[7,6,5,4,3,2,1,0]
 
 v_trunc_f16_e32 v5, v199 quad_perm:[3,2,1,0]
 // GFX11: :[[@LINE-1]]:26: error: invalid operand for instruction
+
+v_trunc_f16_e32 v5.h, v199.h
+// GFX11: :[[@LINE-1]]:23: error: invalid operand for instruction
+
+v_trunc_f16_e32 v5.h, v199.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:23: error: invalid operand for instruction
+
+v_trunc_f16_e32 v5.h, v199.h quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:23: error: invalid operand for instruction
+
+v_trunc_f16_e32 v5.l, v199.l
+// GFX11: :[[@LINE-1]]:23: error: invalid operand for instruction
+
+v_trunc_f16_e32 v5.l, v199.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:23: error: invalid operand for instruction
+
+v_trunc_f16_e32 v5.l, v199.l quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:23: error: invalid operand for instruction