Skip to content

[AMDGPU][True16][MC] true16 for v_not_b16 #120659

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 1 commit into from
Jan 3, 2025
Merged

[AMDGPU][True16][MC] true16 for v_not_b16 #120659

merged 1 commit into from
Jan 3, 2025

Conversation

@broxigarchen
Copy link
Contributor

@broxigarchen broxigarchen commented Dec 20, 2024

Support true16 format for v_not_b16 in MC

@broxigarchen broxigarchen force-pushed the main-merge-true16-mc-vop1-more-instruction-7 branch 4 times, most recently from 43c2118 to cbf196b Compare December 20, 2024 03:54
@broxigarchen broxigarchen force-pushed the main-merge-true16-mc-vop1-more-instruction-7 branch from cbf196b to 0df840b Compare December 20, 2024 03:58
@broxigarchen broxigarchen marked this pull request as ready for review December 20, 2024 15:18
@llvmbot llvmbot added backend:AMDGPU llvm:mc Machine (object) code labels Dec 20, 2024
@llvmbot
Copy link
Member

llvmbot commented Dec 20, 2024

@llvm/pr-subscribers-mc

Author: Brox Chen (broxigarchen)

Changes

Support true16 format for v_not_b16 in MC

Patch is 141.35 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/120659.diff

28 Files Affected:

  • (modified) llvm/lib/Target/AMDGPU/VOP1Instructions.td (+1-1)
  • (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop1.s (+45-30)
  • (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s (+37-28)
  • (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp8.s (+15-6)
  • (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_err.s (+42)
  • (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s (+110-44)
  • (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16_from_vop1.s (+37-28)
  • (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8_from_vop1.s (+15-6)
  • (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop3_from_vop1.s (+39-30)
  • (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1.s (+43-31)
  • (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp16.s (+34-28)
  • (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp8.s (+12-6)
  • (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1_t16_err.s (+42)
  • (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1_t16_promote.s (+110-44)
  • (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1.s (+39-30)
  • (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1_dpp16.s (+37-28)
  • (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1_dpp8.s (+15-6)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1.txt (+48-15)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1_dpp16.txt (+40-14)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1_dpp8.txt (+15-2)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp16_from_vop1.txt (+40-14)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp8_from_vop1.txt (+16-2)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_from_vop1.txt (+42-15)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop1_dpp16.txt (+36-14)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop1_dpp8.txt (+12-2)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1.txt (+42-15)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1_dpp16.txt (+40-14)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1_dpp8.txt (+16-2)
diff --git a/llvm/lib/Target/AMDGPU/VOP1Instructions.td b/llvm/lib/Target/AMDGPU/VOP1Instructions.td
index 1dd39be9e8d9c7..9a9e03eff891cc 100644
--- a/llvm/lib/Target/AMDGPU/VOP1Instructions.td
+++ b/llvm/lib/Target/AMDGPU/VOP1Instructions.td
@@ -1018,7 +1018,7 @@ defm V_CLS_I32             : VOP1_Real_FULL_with_name_gfx11_gfx12<0x03b,
 defm V_SWAP_B16              : VOP1Only_Real_gfx11_gfx12<0x066>;
 defm V_PERMLANE64_B32        : VOP1Only_Real_gfx11_gfx12<0x067>;
 defm V_MOV_B16_t16           : VOP1_Real_FULL_t16_gfx11_gfx12<0x01c, "v_mov_b16">;
-defm V_NOT_B16_fake16        : VOP1_Real_FULL_t16_gfx11_gfx12<0x069, "v_not_b16">;
+defm V_NOT_B16               : VOP1_Real_FULL_t16_and_fake16_gfx11_gfx12<0x069, "v_not_b16">;
 defm V_CVT_I32_I16_fake16    : VOP1_Real_FULL_t16_gfx11_gfx12<0x06a, "v_cvt_i32_i16">;
 defm V_CVT_U32_U16_fake16    : VOP1_Real_FULL_t16_gfx11_gfx12<0x06b, "v_cvt_u32_u16">;
 
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop1.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop1.s
index 4e4dc6647daebd..2332047befb68e 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop1.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop1.s
@@ -2684,50 +2684,65 @@ v_movrelsd_b32 v255, v255
 v_nop
 // GFX11: v_nop                                   ; encoding: [0x00,0x00,0x00,0x7e]
 
-v_not_b16 v5, v1
-// GFX11: v_not_b16_e32 v5, v1                    ; encoding: [0x01,0xd3,0x0a,0x7e]
+v_not_b16 v5.l, v1.l
+// GFX11: v_not_b16_e32 v5.l, v1.l                ; encoding: [0x01,0xd3,0x0a,0x7e]
 
-v_not_b16 v5, v127
-// GFX11: v_not_b16_e32 v5, v127                  ; encoding: [0x7f,0xd3,0x0a,0x7e]
+v_not_b16 v5.l, v127.l
+// GFX11: v_not_b16_e32 v5.l, v127.l              ; encoding: [0x7f,0xd3,0x0a,0x7e]
 
-v_not_b16 v5, s1
-// GFX11: v_not_b16_e32 v5, s1                    ; encoding: [0x01,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, s1
+// GFX11: v_not_b16_e32 v5.l, s1                  ; encoding: [0x01,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, s105
-// GFX11: v_not_b16_e32 v5, s105                  ; encoding: [0x69,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, s105
+// GFX11: v_not_b16_e32 v5.l, s105                ; encoding: [0x69,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, vcc_lo
-// GFX11: v_not_b16_e32 v5, vcc_lo                ; encoding: [0x6a,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, vcc_lo
+// GFX11: v_not_b16_e32 v5.l, vcc_lo              ; encoding: [0x6a,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, vcc_hi
-// GFX11: v_not_b16_e32 v5, vcc_hi                ; encoding: [0x6b,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, vcc_hi
+// GFX11: v_not_b16_e32 v5.l, vcc_hi              ; encoding: [0x6b,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, ttmp15
-// GFX11: v_not_b16_e32 v5, ttmp15                ; encoding: [0x7b,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, ttmp15
+// GFX11: v_not_b16_e32 v5.l, ttmp15              ; encoding: [0x7b,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, m0
-// GFX11: v_not_b16_e32 v5, m0                    ; encoding: [0x7d,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, m0
+// GFX11: v_not_b16_e32 v5.l, m0                  ; encoding: [0x7d,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, exec_lo
-// GFX11: v_not_b16_e32 v5, exec_lo               ; encoding: [0x7e,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, exec_lo
+// GFX11: v_not_b16_e32 v5.l, exec_lo             ; encoding: [0x7e,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, exec_hi
-// GFX11: v_not_b16_e32 v5, exec_hi               ; encoding: [0x7f,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, exec_hi
+// GFX11: v_not_b16_e32 v5.l, exec_hi             ; encoding: [0x7f,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, null
-// GFX11: v_not_b16_e32 v5, null                  ; encoding: [0x7c,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, null
+// GFX11: v_not_b16_e32 v5.l, null                ; encoding: [0x7c,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, -1
-// GFX11: v_not_b16_e32 v5, -1                    ; encoding: [0xc1,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, -1
+// GFX11: v_not_b16_e32 v5.l, -1                  ; encoding: [0xc1,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, 0.5
-// GFX11: v_not_b16_e32 v5, 0.5                   ; encoding: [0xf0,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, 0.5
+// GFX11: v_not_b16_e32 v5.l, 0.5                 ; encoding: [0xf0,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, src_scc
-// GFX11: v_not_b16_e32 v5, src_scc               ; encoding: [0xfd,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, src_scc
+// GFX11: v_not_b16_e32 v5.l, src_scc             ; encoding: [0xfd,0xd2,0x0a,0x7e]
 
-v_not_b16 v127, 0xfe0b
-// GFX11: v_not_b16_e32 v127, 0xfe0b              ; encoding: [0xff,0xd2,0xfe,0x7e,0x0b,0xfe,0x00,0x00]
+v_not_b16 v127.l, 0xfe0b
+// GFX11: v_not_b16_e32 v127.l, 0xfe0b            ; encoding: [0xff,0xd2,0xfe,0x7e,0x0b,0xfe,0x00,0x00]
+
+v_not_b16 v5.l, v1.h
+// GFX11: v_not_b16_e32 v5.l, v1.h                ; encoding: [0x81,0xd3,0x0a,0x7e]
+
+v_not_b16 v5.l, v127.h
+// GFX11: v_not_b16_e32 v5.l, v127.h              ; encoding: [0xff,0xd3,0x0a,0x7e]
+
+v_not_b16 v127.l, 0.5
+// GFX11: v_not_b16_e32 v127.l, 0.5               ; encoding: [0xf0,0xd2,0xfe,0x7e]
+
+v_not_b16 v5.h, src_scc
+// GFX11: v_not_b16_e32 v5.h, src_scc             ; encoding: [0xfd,0xd2,0x0a,0x7f]
+
+v_not_b16 v127.h, 0xfe0b
+// GFX11: v_not_b16_e32 v127.h, 0xfe0b            ; encoding: [0xff,0xd2,0xfe,0x7f,0x0b,0xfe,0x00,0x00]
 
 v_not_b32 v5, v1
 // GFX11: v_not_b32_e32 v5, v1                    ; encoding: [0x01,0x6f,0x0a,0x7e]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s
index 98e4b29b25666e..24a447759cbf3b 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s
@@ -2144,47 +2144,56 @@ v_movrelsd_b32 v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
 v_movrelsd_b32 v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
 // GFX11: v_movrelsd_b32_dpp v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0x88,0xfe,0x7f,0xff,0x6f,0x05,0x30]
 
-v_not_b16 v5, v1 quad_perm:[3,2,1,0]
-// GFX11: v_not_b16_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x1b,0x00,0xff]
+v_not_b16 v5.l, v1.l quad_perm:[3,2,1,0]
+// GFX11: v_not_b16_dpp v5.l, v1.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x1b,0x00,0xff]
 
-v_not_b16 v5, v1 quad_perm:[0,1,2,3]
-// GFX11: v_not_b16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0xe4,0x00,0xff]
+v_not_b16 v5.l, v1.l quad_perm:[0,1,2,3]
+// GFX11: v_not_b16_dpp v5.l, v1.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0xe4,0x00,0xff]
 
-v_not_b16 v5, v1 row_mirror
-// GFX11: v_not_b16_dpp v5, v1 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x40,0x01,0xff]
+v_not_b16 v5.l, v1.l row_mirror
+// GFX11: v_not_b16_dpp v5.l, v1.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x40,0x01,0xff]
 
-v_not_b16 v5, v1 row_half_mirror
-// GFX11: v_not_b16_dpp v5, v1 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x41,0x01,0xff]
+v_not_b16 v5.l, v1.l row_half_mirror
+// GFX11: v_not_b16_dpp v5.l, v1.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x41,0x01,0xff]
 
-v_not_b16 v5, v1 row_shl:1
-// GFX11: v_not_b16_dpp v5, v1 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x01,0x01,0xff]
+v_not_b16 v5.l, v1.l row_shl:1
+// GFX11: v_not_b16_dpp v5.l, v1.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x01,0x01,0xff]
 
-v_not_b16 v5, v1 row_shl:15
-// GFX11: v_not_b16_dpp v5, v1 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x0f,0x01,0xff]
+v_not_b16 v5.l, v1.l row_shl:15
+// GFX11: v_not_b16_dpp v5.l, v1.l row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x0f,0x01,0xff]
 
-v_not_b16 v5, v1 row_shr:1
-// GFX11: v_not_b16_dpp v5, v1 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x11,0x01,0xff]
+v_not_b16 v5.l, v1.l row_shr:1
+// GFX11: v_not_b16_dpp v5.l, v1.l row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x11,0x01,0xff]
 
-v_not_b16 v5, v1 row_shr:15
-// GFX11: v_not_b16_dpp v5, v1 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x1f,0x01,0xff]
+v_not_b16 v5.l, v1.l row_shr:15
+// GFX11: v_not_b16_dpp v5.l, v1.l row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x1f,0x01,0xff]
 
-v_not_b16 v5, v1 row_ror:1
-// GFX11: v_not_b16_dpp v5, v1 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x21,0x01,0xff]
+v_not_b16 v5.l, v1.l row_ror:1
+// GFX11: v_not_b16_dpp v5.l, v1.l row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x21,0x01,0xff]
 
-v_not_b16 v5, v1 row_ror:15
-// GFX11: v_not_b16_dpp v5, v1 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x2f,0x01,0xff]
+v_not_b16 v5.l, v1.l row_ror:15
+// GFX11: v_not_b16_dpp v5.l, v1.l row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x2f,0x01,0xff]
 
-v_not_b16 v5, v1 row_share:0 row_mask:0xf bank_mask:0xf
-// GFX11: v_not_b16_dpp v5, v1 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x50,0x01,0xff]
+v_not_b16 v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf
+// GFX11: v_not_b16_dpp v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x50,0x01,0xff]
 
-v_not_b16 v5, v1 row_share:15 row_mask:0x0 bank_mask:0x1
-// GFX11: v_not_b16_dpp v5, v1 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x5f,0x01,0x01]
+v_not_b16 v5.l, v1.l row_share:15 row_mask:0x0 bank_mask:0x1
+// GFX11: v_not_b16_dpp v5.l, v1.l row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x5f,0x01,0x01]
 
-v_not_b16 v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
-// GFX11: v_not_b16_dpp v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x60,0x09,0x13]
+v_not_b16 v5.l, v1.l row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1
+// GFX11: v_not_b16_dpp v5.l, v1.l row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x60,0x09,0x13]
 
-v_not_b16 v127, v127 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
-// GFX11: v_not_b16_dpp v127, v127 row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xd2,0xfe,0x7e,0x7f,0x6f,0x05,0x30]
+v_not_b16 v127.l, v127.l row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1
+// GFX11: v_not_b16_dpp v127.l, v127.l row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xd2,0xfe,0x7e,0x7f,0x6f,0x05,0x30]
+
+v_not_b16 v127.l, v127.l row_share:15 row_mask:0x0 bank_mask:0x1
+// GFX11: v_not_b16_dpp v127.l, v127.l row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xd2,0xfe,0x7e,0x7f,0x5f,0x01,0x01]
+
+v_not_b16 v5.h, v1.h row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
+// GFX11: v_not_b16_dpp v5.h, v1.h row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0xd2,0x0a,0x7f,0x81,0x60,0x09,0x13]
+
+v_not_b16 v127.h, v127.h row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
+// GFX11: v_not_b16_dpp v127.h, v127.h row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xd2,0xfe,0x7f,0xff,0x6f,0x05,0x30]
 
 v_not_b32 v5, v1 quad_perm:[3,2,1,0]
 // GFX11: v_not_b32_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x6e,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
index ab4606af2bb35c..1b9272d8a99b8c 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp8.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp8.s
@@ -500,14 +500,23 @@ v_movrelsd_b32 v5, v1 dpp8:[7,6,5,4,3,2,1,0] fi:1
 v_movrelsd_b32 v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:0
 // GFX11: v_movrelsd_b32_dpp v255, v255 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0x88,0xfe,0x7f,0xff,0x00,0x00,0x00]
 
-v_not_b16 v5, v1 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_not_b16_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xd2,0x0a,0x7e,0x01,0x77,0x39,0x05]
+v_not_b16 v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_not_b16_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xd2,0x0a,0x7e,0x01,0x77,0x39,0x05]
 
-v_not_b16 v5, v1 dpp8:[7,6,5,4,3,2,1,0] fi:1
-// GFX11: v_not_b16_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0xd2,0x0a,0x7e,0x01,0x77,0x39,0x05]
+v_not_b16 v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] fi:1
+// GFX11: v_not_b16_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0xd2,0x0a,0x7e,0x01,0x77,0x39,0x05]
 
-v_not_b16 v127, v127 dpp8:[0,0,0,0,0,0,0,0] fi:0
-// GFX11: v_not_b16_dpp v127, v127 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xd2,0xfe,0x7e,0x7f,0x00,0x00,0x00]
+v_not_b16 v127.l, v127.l dpp8:[0,0,0,0,0,0,0,0]
+// GFX11: v_not_b16_dpp v127.l, v127.l dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xd2,0xfe,0x7e,0x7f,0x00,0x00,0x00]
+
+v_not_b16 v127.l, v127.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_not_b16_dpp v127.l, v127.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xd2,0xfe,0x7e,0x7f,0x77,0x39,0x05]
+
+v_not_b16 v5.h, v1.h dpp8:[7,6,5,4,3,2,1,0] fi:1
+// GFX11: v_not_b16_dpp v5.h, v1.h dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0xd2,0x0a,0x7f,0x81,0x77,0x39,0x05]
+
+v_not_b16 v127.h, v127.h dpp8:[0,0,0,0,0,0,0,0] fi:0
+// GFX11: v_not_b16_dpp v127.h, v127.h dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xd2,0xfe,0x7f,0xff,0x00,0x00,0x00]
 
 v_not_b32 v5, v1 dpp8:[7,6,5,4,3,2,1,0]
 // GFX11: v_not_b32_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0x6e,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
index 4ae91340386b65..e4917d9364954e 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_err.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_err.s
@@ -584,6 +584,12 @@ v_log_f16_e32 v5.l, v199.l quad_perm:[3,2,1,0]
 v_not_b16_e32 v128, 0xfe0b
 // GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
 
+v_not_b16_e32 v128.h, 0xfe0b
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_not_b16_e32 v128.l, 0xfe0b
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
 v_not_b16_e32 v255, v1
 // GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
 
@@ -593,6 +599,24 @@ v_not_b16_e32 v255, v1 dpp8:[7,6,5,4,3,2,1,0]
 v_not_b16_e32 v255, v1 quad_perm:[3,2,1,0]
 // GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
 
+v_not_b16_e32 v255.h, v1.h
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_not_b16_e32 v255.h, v1.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_not_b16_e32 v255.h, v1.h quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_not_b16_e32 v255.l, v1.l
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_not_b16_e32 v255.l, v1.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_not_b16_e32 v255.l, v1.l quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
 v_not_b16_e32 v5, v199
 // GFX11: :[[@LINE-1]]:19: error: invalid operand for instruction
 
@@ -602,6 +626,24 @@ v_not_b16_e32 v5, v199 dpp8:[7,6,5,4,3,2,1,0]
 v_not_b16_e32 v5, v199 quad_perm:[3,2,1,0]
 // GFX11: :[[@LINE-1]]:19: error: invalid operand for instruction
 
+v_not_b16_e32 v5.h, v199.h
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_not_b16_e32 v5.h, v199.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_not_b16_e32 v5.h, v199.h quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_not_b16_e32 v5.l, v199.l
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_not_b16_e32 v5.l, v199.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_not_b16_e32 v5.l, v199.l quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
 v_rcp_f16_e32 v128.h, 0xfe0b
 // GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
 
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s
index 1d441720280ca2..ee0f125fdac38f 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s
@@ -1538,71 +1538,137 @@ v_log_f16 v5, v199 dpp8:[7,6,5,4,3,2,1,0]
 v_log_f16 v5, v199 quad_perm:[3,2,1,0]
 // GFX11: v_log_f16_e64_dpp v5, v199 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xd7,0xd5,0xfa,0x00,0x00,0x00,0xc7,0x1b,0x00,0xff]
 
-v_not_b16 v128, 0xfe0b
-// GFX11: v_not_b16_e64 v128, 0xfe0b              ; encoding: [0x80,0x00,0xe9,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
+v_not_b16 v128.h, 0xfe0b
+// GFX11: v_not_b16_e64 v128.h, 0xfe0b op_sel:[0,1] ; encoding: [0x80,0x40,0xe9,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
 
-v_not_b16 v255, -1
-// GFX11: v_not_b16_e64 v255, -1                  ; encoding: [0xff,0x00,0xe9,0xd5,0xc1,0x00,0x00,0x00]
+v_not_b16 v128.l, 0xfe0b
+// GFX11: v_not_b16_e64 v128.l, 0xfe0b            ; encoding: [0x80,0x00,0xe9,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
 
-v_not_b16 v255, 0.5
-// GFX11: v_not_b16_e64 v255, 0.5                 ; encoding: [0xff,0x00,0xe9,0xd5,0xf0,0x00,0x00,0x00]
+v_not_b16 v255.h, -1
+// GFX11: v_not_b16_e64 v255.h, -1 op_sel:[0,1]   ; encoding: [0xff,0x40,0xe9,0xd5,0xc1,0x00,0x00,0x00]
 
-v_not_b16 v255, exec_hi
-// GFX11: v_not_b16_e64 v255, exec_hi             ; encoding: [0xff,0x00,0xe9,0xd5,0x7f,0x00,0x00,0x00]
+v_not_b16 v255.h, 0.5
+// GFX11: v_not_b16_e64 v255.h, 0.5 op_sel:[0,1]  ; encoding: [0xff,0x40,0xe9,0xd5,0xf0,0x00,0x00,0x00]
 
-v_not_b16 v255, exec_lo
-// GFX11: v_not_b16_e64 v255, exec_lo             ; encoding: [0xff,0x00,0xe9,0xd5,0x7e,0x00,0x00,0x00]
+v_not_b16 v255.h, exec_hi
+// GFX11: v_not_b16_e64 v255.h, exec_hi op_sel:[0,1] ; encoding: [0xff,0x40,0xe9,0xd5,0x7f,0x00,0x00,0x00]
 
-v_not_b16 v255, m0
-// GFX11: v_not_b16_e64 v255, m0                  ; encoding: [0xff,0x00,0xe9,0xd5,0x7d,0x00,0x00,0x00]
+v_not_b16 v255.h, exec_lo
+// GFX11: v_not_b16_e64 v255.h, exec_lo op_sel:[0,1] ; encoding: [0xff,0x40,0xe9,0xd5,0x7e,0x00,0x00,0x00]
 
-v_not_b16 v255, null
-// GFX11: v_not_b16_e64 v255, null                ; encoding: [0xff,0x00,0xe9,0xd5,0x7c,0x00,0x00,0x00]
+v_not_b16 v255.h, m0
+// GFX11: v_not_b16_e64 v255.h, m0 op_sel:[0,1]   ; encoding: [0xff,0x40,0xe9,0xd5,0x7d,0x00,0x00,0x00]
 
-v_not_b16 v255, s1
-// GFX11: v_not_b16_e64 v255, s1                  ; encoding: [0xff,0x00,0xe9,0xd5,0x01,0x00,0x00,0x00]
+v_not_b16 v255.h, null
+// GFX11: v_not_b16_e64 v255.h, null op_sel:[0,1] ; encoding: [0xff,0x40,0xe9,0xd5,0x7c,0x00,0x00,0x00]
 
-v_not_b16 v255, s105
-// GFX11: v_not_b16_e64 v255, s105                ; encoding: [0xff,0x00,0xe9,0xd5,0x69,0x00,0x00,0x00]
+v_not_b16 v255.h, s1
+// GFX11: v_not_b16_e64 v255.h, s1 op_sel:[0,1]   ; encoding: [0xff,0x40,0xe9,0xd5,0x01,0x00,0x00,0x00]
 
-v_not_b16 v255, src_scc
-// GFX11: v_not_b16_e64 v255, src_scc             ; encoding: [0xff,0x00,0xe9,0xd5,0xfd,0x00,0x00,0x00]
+v_not_b16 v255.h, s105
+// GFX11: v_not_b16_e64 v255.h, s105 op_sel:[0,1] ; encoding: [0xff,0x40,0xe9,0xd5,0x69,0x00,0x00,0x00]
 
-v_not_b16 v255, ttmp15
-// GFX11: v_not_b16_e64 v255, ttmp15              ; encoding: [0xff,0x00,0xe9,0xd5,0x7b,0x00,0x00,0x00]
+v_not_b16 v255.h, src_scc
+// GFX11: v_not_b16_e64 v255.h, src_scc op_sel:[0,1] ; encoding: [0xff,0x40,0xe9,0xd5,0xfd,0x00,0x00,0x00]
 
-v_not_b16 v255, v1
-// GFX11: v_not_b16_e64 v255, v1                  ; encoding: [0xff,0x00,0xe9,0xd5,0x01,0x01,0x00,0x00]
+v_not_b16 v255.h, ttmp15
+// GFX11: v_not_b16_e64 v255.h, ttmp15 op_sel:[0,1] ; encoding: [0xff,0x40,0xe9,0xd5,0x7b,0x00,0x00,0x00]
 
-v_not_b16 v255, v1 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_not_b16_e64_dpp v255, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xe9,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
+v_not_b16 v255.h, v1.h
+// GFX11: v_not_b16_e64 v255.h, v1.h op_sel:[1,1] ; encoding: [0xff,0x48,0xe9,0xd5,0x01,0x01,0x00,0x00]
 
-v_not_b16 v255, v1 quad_perm:[3,2,1,0]
-// GFX11: v_not_b16_e64_dpp v255, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xe9,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
+v_not_b16 v255.h, v1.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_not_b16_e64_d...
[truncated]

@llvmbot
Copy link
Member

llvmbot commented Dec 20, 2024

@llvm/pr-subscribers-backend-amdgpu

Author: Brox Chen (broxigarchen)

Changes

Support true16 format for v_not_b16 in MC

Patch is 141.35 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/120659.diff

28 Files Affected:

  • (modified) llvm/lib/Target/AMDGPU/VOP1Instructions.td (+1-1)
  • (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop1.s (+45-30)
  • (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s (+37-28)
  • (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp8.s (+15-6)
  • (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_err.s (+42)
  • (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s (+110-44)
  • (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16_from_vop1.s (+37-28)
  • (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8_from_vop1.s (+15-6)
  • (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop3_from_vop1.s (+39-30)
  • (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1.s (+43-31)
  • (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp16.s (+34-28)
  • (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp8.s (+12-6)
  • (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1_t16_err.s (+42)
  • (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop1_t16_promote.s (+110-44)
  • (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1.s (+39-30)
  • (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1_dpp16.s (+37-28)
  • (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1_dpp8.s (+15-6)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1.txt (+48-15)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1_dpp16.txt (+40-14)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1_dpp8.txt (+15-2)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp16_from_vop1.txt (+40-14)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp8_from_vop1.txt (+16-2)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_from_vop1.txt (+42-15)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop1_dpp16.txt (+36-14)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop1_dpp8.txt (+12-2)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1.txt (+42-15)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1_dpp16.txt (+40-14)
  • (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1_dpp8.txt (+16-2)
diff --git a/llvm/lib/Target/AMDGPU/VOP1Instructions.td b/llvm/lib/Target/AMDGPU/VOP1Instructions.td
index 1dd39be9e8d9c7..9a9e03eff891cc 100644
--- a/llvm/lib/Target/AMDGPU/VOP1Instructions.td
+++ b/llvm/lib/Target/AMDGPU/VOP1Instructions.td
@@ -1018,7 +1018,7 @@ defm V_CLS_I32             : VOP1_Real_FULL_with_name_gfx11_gfx12<0x03b,
 defm V_SWAP_B16              : VOP1Only_Real_gfx11_gfx12<0x066>;
 defm V_PERMLANE64_B32        : VOP1Only_Real_gfx11_gfx12<0x067>;
 defm V_MOV_B16_t16           : VOP1_Real_FULL_t16_gfx11_gfx12<0x01c, "v_mov_b16">;
-defm V_NOT_B16_fake16        : VOP1_Real_FULL_t16_gfx11_gfx12<0x069, "v_not_b16">;
+defm V_NOT_B16               : VOP1_Real_FULL_t16_and_fake16_gfx11_gfx12<0x069, "v_not_b16">;
 defm V_CVT_I32_I16_fake16    : VOP1_Real_FULL_t16_gfx11_gfx12<0x06a, "v_cvt_i32_i16">;
 defm V_CVT_U32_U16_fake16    : VOP1_Real_FULL_t16_gfx11_gfx12<0x06b, "v_cvt_u32_u16">;
 
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop1.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop1.s
index 4e4dc6647daebd..2332047befb68e 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop1.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop1.s
@@ -2684,50 +2684,65 @@ v_movrelsd_b32 v255, v255
 v_nop
 // GFX11: v_nop                                   ; encoding: [0x00,0x00,0x00,0x7e]
 
-v_not_b16 v5, v1
-// GFX11: v_not_b16_e32 v5, v1                    ; encoding: [0x01,0xd3,0x0a,0x7e]
+v_not_b16 v5.l, v1.l
+// GFX11: v_not_b16_e32 v5.l, v1.l                ; encoding: [0x01,0xd3,0x0a,0x7e]
 
-v_not_b16 v5, v127
-// GFX11: v_not_b16_e32 v5, v127                  ; encoding: [0x7f,0xd3,0x0a,0x7e]
+v_not_b16 v5.l, v127.l
+// GFX11: v_not_b16_e32 v5.l, v127.l              ; encoding: [0x7f,0xd3,0x0a,0x7e]
 
-v_not_b16 v5, s1
-// GFX11: v_not_b16_e32 v5, s1                    ; encoding: [0x01,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, s1
+// GFX11: v_not_b16_e32 v5.l, s1                  ; encoding: [0x01,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, s105
-// GFX11: v_not_b16_e32 v5, s105                  ; encoding: [0x69,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, s105
+// GFX11: v_not_b16_e32 v5.l, s105                ; encoding: [0x69,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, vcc_lo
-// GFX11: v_not_b16_e32 v5, vcc_lo                ; encoding: [0x6a,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, vcc_lo
+// GFX11: v_not_b16_e32 v5.l, vcc_lo              ; encoding: [0x6a,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, vcc_hi
-// GFX11: v_not_b16_e32 v5, vcc_hi                ; encoding: [0x6b,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, vcc_hi
+// GFX11: v_not_b16_e32 v5.l, vcc_hi              ; encoding: [0x6b,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, ttmp15
-// GFX11: v_not_b16_e32 v5, ttmp15                ; encoding: [0x7b,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, ttmp15
+// GFX11: v_not_b16_e32 v5.l, ttmp15              ; encoding: [0x7b,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, m0
-// GFX11: v_not_b16_e32 v5, m0                    ; encoding: [0x7d,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, m0
+// GFX11: v_not_b16_e32 v5.l, m0                  ; encoding: [0x7d,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, exec_lo
-// GFX11: v_not_b16_e32 v5, exec_lo               ; encoding: [0x7e,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, exec_lo
+// GFX11: v_not_b16_e32 v5.l, exec_lo             ; encoding: [0x7e,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, exec_hi
-// GFX11: v_not_b16_e32 v5, exec_hi               ; encoding: [0x7f,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, exec_hi
+// GFX11: v_not_b16_e32 v5.l, exec_hi             ; encoding: [0x7f,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, null
-// GFX11: v_not_b16_e32 v5, null                  ; encoding: [0x7c,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, null
+// GFX11: v_not_b16_e32 v5.l, null                ; encoding: [0x7c,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, -1
-// GFX11: v_not_b16_e32 v5, -1                    ; encoding: [0xc1,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, -1
+// GFX11: v_not_b16_e32 v5.l, -1                  ; encoding: [0xc1,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, 0.5
-// GFX11: v_not_b16_e32 v5, 0.5                   ; encoding: [0xf0,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, 0.5
+// GFX11: v_not_b16_e32 v5.l, 0.5                 ; encoding: [0xf0,0xd2,0x0a,0x7e]
 
-v_not_b16 v5, src_scc
-// GFX11: v_not_b16_e32 v5, src_scc               ; encoding: [0xfd,0xd2,0x0a,0x7e]
+v_not_b16 v5.l, src_scc
+// GFX11: v_not_b16_e32 v5.l, src_scc             ; encoding: [0xfd,0xd2,0x0a,0x7e]
 
-v_not_b16 v127, 0xfe0b
-// GFX11: v_not_b16_e32 v127, 0xfe0b              ; encoding: [0xff,0xd2,0xfe,0x7e,0x0b,0xfe,0x00,0x00]
+v_not_b16 v127.l, 0xfe0b
+// GFX11: v_not_b16_e32 v127.l, 0xfe0b            ; encoding: [0xff,0xd2,0xfe,0x7e,0x0b,0xfe,0x00,0x00]
+
+v_not_b16 v5.l, v1.h
+// GFX11: v_not_b16_e32 v5.l, v1.h                ; encoding: [0x81,0xd3,0x0a,0x7e]
+
+v_not_b16 v5.l, v127.h
+// GFX11: v_not_b16_e32 v5.l, v127.h              ; encoding: [0xff,0xd3,0x0a,0x7e]
+
+v_not_b16 v127.l, 0.5
+// GFX11: v_not_b16_e32 v127.l, 0.5               ; encoding: [0xf0,0xd2,0xfe,0x7e]
+
+v_not_b16 v5.h, src_scc
+// GFX11: v_not_b16_e32 v5.h, src_scc             ; encoding: [0xfd,0xd2,0x0a,0x7f]
+
+v_not_b16 v127.h, 0xfe0b
+// GFX11: v_not_b16_e32 v127.h, 0xfe0b            ; encoding: [0xff,0xd2,0xfe,0x7f,0x0b,0xfe,0x00,0x00]
 
 v_not_b32 v5, v1
 // GFX11: v_not_b32_e32 v5, v1                    ; encoding: [0x01,0x6f,0x0a,0x7e]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s
index 98e4b29b25666e..24a447759cbf3b 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s
@@ -2144,47 +2144,56 @@ v_movrelsd_b32 v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
 v_movrelsd_b32 v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
 // GFX11: v_movrelsd_b32_dpp v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0x88,0xfe,0x7f,0xff,0x6f,0x05,0x30]
 
-v_not_b16 v5, v1 quad_perm:[3,2,1,0]
-// GFX11: v_not_b16_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x1b,0x00,0xff]
+v_not_b16 v5.l, v1.l quad_perm:[3,2,1,0]
+// GFX11: v_not_b16_dpp v5.l, v1.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x1b,0x00,0xff]
 
-v_not_b16 v5, v1 quad_perm:[0,1,2,3]
-// GFX11: v_not_b16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0xe4,0x00,0xff]
+v_not_b16 v5.l, v1.l quad_perm:[0,1,2,3]
+// GFX11: v_not_b16_dpp v5.l, v1.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0xe4,0x00,0xff]
 
-v_not_b16 v5, v1 row_mirror
-// GFX11: v_not_b16_dpp v5, v1 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x40,0x01,0xff]
+v_not_b16 v5.l, v1.l row_mirror
+// GFX11: v_not_b16_dpp v5.l, v1.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x40,0x01,0xff]
 
-v_not_b16 v5, v1 row_half_mirror
-// GFX11: v_not_b16_dpp v5, v1 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x41,0x01,0xff]
+v_not_b16 v5.l, v1.l row_half_mirror
+// GFX11: v_not_b16_dpp v5.l, v1.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x41,0x01,0xff]
 
-v_not_b16 v5, v1 row_shl:1
-// GFX11: v_not_b16_dpp v5, v1 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x01,0x01,0xff]
+v_not_b16 v5.l, v1.l row_shl:1
+// GFX11: v_not_b16_dpp v5.l, v1.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x01,0x01,0xff]
 
-v_not_b16 v5, v1 row_shl:15
-// GFX11: v_not_b16_dpp v5, v1 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x0f,0x01,0xff]
+v_not_b16 v5.l, v1.l row_shl:15
+// GFX11: v_not_b16_dpp v5.l, v1.l row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x0f,0x01,0xff]
 
-v_not_b16 v5, v1 row_shr:1
-// GFX11: v_not_b16_dpp v5, v1 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x11,0x01,0xff]
+v_not_b16 v5.l, v1.l row_shr:1
+// GFX11: v_not_b16_dpp v5.l, v1.l row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x11,0x01,0xff]
 
-v_not_b16 v5, v1 row_shr:15
-// GFX11: v_not_b16_dpp v5, v1 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x1f,0x01,0xff]
+v_not_b16 v5.l, v1.l row_shr:15
+// GFX11: v_not_b16_dpp v5.l, v1.l row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x1f,0x01,0xff]
 
-v_not_b16 v5, v1 row_ror:1
-// GFX11: v_not_b16_dpp v5, v1 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x21,0x01,0xff]
+v_not_b16 v5.l, v1.l row_ror:1
+// GFX11: v_not_b16_dpp v5.l, v1.l row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x21,0x01,0xff]
 
-v_not_b16 v5, v1 row_ror:15
-// GFX11: v_not_b16_dpp v5, v1 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x2f,0x01,0xff]
+v_not_b16 v5.l, v1.l row_ror:15
+// GFX11: v_not_b16_dpp v5.l, v1.l row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x2f,0x01,0xff]
 
-v_not_b16 v5, v1 row_share:0 row_mask:0xf bank_mask:0xf
-// GFX11: v_not_b16_dpp v5, v1 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x50,0x01,0xff]
+v_not_b16 v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf
+// GFX11: v_not_b16_dpp v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x50,0x01,0xff]
 
-v_not_b16 v5, v1 row_share:15 row_mask:0x0 bank_mask:0x1
-// GFX11: v_not_b16_dpp v5, v1 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x5f,0x01,0x01]
+v_not_b16 v5.l, v1.l row_share:15 row_mask:0x0 bank_mask:0x1
+// GFX11: v_not_b16_dpp v5.l, v1.l row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x5f,0x01,0x01]
 
-v_not_b16 v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
-// GFX11: v_not_b16_dpp v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x60,0x09,0x13]
+v_not_b16 v5.l, v1.l row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1
+// GFX11: v_not_b16_dpp v5.l, v1.l row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0xd2,0x0a,0x7e,0x01,0x60,0x09,0x13]
 
-v_not_b16 v127, v127 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
-// GFX11: v_not_b16_dpp v127, v127 row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xd2,0xfe,0x7e,0x7f,0x6f,0x05,0x30]
+v_not_b16 v127.l, v127.l row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1
+// GFX11: v_not_b16_dpp v127.l, v127.l row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xd2,0xfe,0x7e,0x7f,0x6f,0x05,0x30]
+
+v_not_b16 v127.l, v127.l row_share:15 row_mask:0x0 bank_mask:0x1
+// GFX11: v_not_b16_dpp v127.l, v127.l row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xd2,0xfe,0x7e,0x7f,0x5f,0x01,0x01]
+
+v_not_b16 v5.h, v1.h row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
+// GFX11: v_not_b16_dpp v5.h, v1.h row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0xd2,0x0a,0x7f,0x81,0x60,0x09,0x13]
+
+v_not_b16 v127.h, v127.h row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
+// GFX11: v_not_b16_dpp v127.h, v127.h row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xd2,0xfe,0x7f,0xff,0x6f,0x05,0x30]
 
 v_not_b32 v5, v1 quad_perm:[3,2,1,0]
 // GFX11: v_not_b32_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x6e,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
index ab4606af2bb35c..1b9272d8a99b8c 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp8.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp8.s
@@ -500,14 +500,23 @@ v_movrelsd_b32 v5, v1 dpp8:[7,6,5,4,3,2,1,0] fi:1
 v_movrelsd_b32 v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:0
 // GFX11: v_movrelsd_b32_dpp v255, v255 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0x88,0xfe,0x7f,0xff,0x00,0x00,0x00]
 
-v_not_b16 v5, v1 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_not_b16_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xd2,0x0a,0x7e,0x01,0x77,0x39,0x05]
+v_not_b16 v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_not_b16_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xd2,0x0a,0x7e,0x01,0x77,0x39,0x05]
 
-v_not_b16 v5, v1 dpp8:[7,6,5,4,3,2,1,0] fi:1
-// GFX11: v_not_b16_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0xd2,0x0a,0x7e,0x01,0x77,0x39,0x05]
+v_not_b16 v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] fi:1
+// GFX11: v_not_b16_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0xd2,0x0a,0x7e,0x01,0x77,0x39,0x05]
 
-v_not_b16 v127, v127 dpp8:[0,0,0,0,0,0,0,0] fi:0
-// GFX11: v_not_b16_dpp v127, v127 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xd2,0xfe,0x7e,0x7f,0x00,0x00,0x00]
+v_not_b16 v127.l, v127.l dpp8:[0,0,0,0,0,0,0,0]
+// GFX11: v_not_b16_dpp v127.l, v127.l dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xd2,0xfe,0x7e,0x7f,0x00,0x00,0x00]
+
+v_not_b16 v127.l, v127.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_not_b16_dpp v127.l, v127.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xd2,0xfe,0x7e,0x7f,0x77,0x39,0x05]
+
+v_not_b16 v5.h, v1.h dpp8:[7,6,5,4,3,2,1,0] fi:1
+// GFX11: v_not_b16_dpp v5.h, v1.h dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0xd2,0x0a,0x7f,0x81,0x77,0x39,0x05]
+
+v_not_b16 v127.h, v127.h dpp8:[0,0,0,0,0,0,0,0] fi:0
+// GFX11: v_not_b16_dpp v127.h, v127.h dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xd2,0xfe,0x7f,0xff,0x00,0x00,0x00]
 
 v_not_b32 v5, v1 dpp8:[7,6,5,4,3,2,1,0]
 // GFX11: v_not_b32_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0x6e,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
index 4ae91340386b65..e4917d9364954e 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_err.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_err.s
@@ -584,6 +584,12 @@ v_log_f16_e32 v5.l, v199.l quad_perm:[3,2,1,0]
 v_not_b16_e32 v128, 0xfe0b
 // GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
 
+v_not_b16_e32 v128.h, 0xfe0b
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_not_b16_e32 v128.l, 0xfe0b
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
 v_not_b16_e32 v255, v1
 // GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
 
@@ -593,6 +599,24 @@ v_not_b16_e32 v255, v1 dpp8:[7,6,5,4,3,2,1,0]
 v_not_b16_e32 v255, v1 quad_perm:[3,2,1,0]
 // GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
 
+v_not_b16_e32 v255.h, v1.h
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_not_b16_e32 v255.h, v1.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_not_b16_e32 v255.h, v1.h quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_not_b16_e32 v255.l, v1.l
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_not_b16_e32 v255.l, v1.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_not_b16_e32 v255.l, v1.l quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
 v_not_b16_e32 v5, v199
 // GFX11: :[[@LINE-1]]:19: error: invalid operand for instruction
 
@@ -602,6 +626,24 @@ v_not_b16_e32 v5, v199 dpp8:[7,6,5,4,3,2,1,0]
 v_not_b16_e32 v5, v199 quad_perm:[3,2,1,0]
 // GFX11: :[[@LINE-1]]:19: error: invalid operand for instruction
 
+v_not_b16_e32 v5.h, v199.h
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_not_b16_e32 v5.h, v199.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_not_b16_e32 v5.h, v199.h quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_not_b16_e32 v5.l, v199.l
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_not_b16_e32 v5.l, v199.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_not_b16_e32 v5.l, v199.l quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
 v_rcp_f16_e32 v128.h, 0xfe0b
 // GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
 
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s
index 1d441720280ca2..ee0f125fdac38f 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s
@@ -1538,71 +1538,137 @@ v_log_f16 v5, v199 dpp8:[7,6,5,4,3,2,1,0]
 v_log_f16 v5, v199 quad_perm:[3,2,1,0]
 // GFX11: v_log_f16_e64_dpp v5, v199 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xd7,0xd5,0xfa,0x00,0x00,0x00,0xc7,0x1b,0x00,0xff]
 
-v_not_b16 v128, 0xfe0b
-// GFX11: v_not_b16_e64 v128, 0xfe0b              ; encoding: [0x80,0x00,0xe9,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
+v_not_b16 v128.h, 0xfe0b
+// GFX11: v_not_b16_e64 v128.h, 0xfe0b op_sel:[0,1] ; encoding: [0x80,0x40,0xe9,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
 
-v_not_b16 v255, -1
-// GFX11: v_not_b16_e64 v255, -1                  ; encoding: [0xff,0x00,0xe9,0xd5,0xc1,0x00,0x00,0x00]
+v_not_b16 v128.l, 0xfe0b
+// GFX11: v_not_b16_e64 v128.l, 0xfe0b            ; encoding: [0x80,0x00,0xe9,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
 
-v_not_b16 v255, 0.5
-// GFX11: v_not_b16_e64 v255, 0.5                 ; encoding: [0xff,0x00,0xe9,0xd5,0xf0,0x00,0x00,0x00]
+v_not_b16 v255.h, -1
+// GFX11: v_not_b16_e64 v255.h, -1 op_sel:[0,1]   ; encoding: [0xff,0x40,0xe9,0xd5,0xc1,0x00,0x00,0x00]
 
-v_not_b16 v255, exec_hi
-// GFX11: v_not_b16_e64 v255, exec_hi             ; encoding: [0xff,0x00,0xe9,0xd5,0x7f,0x00,0x00,0x00]
+v_not_b16 v255.h, 0.5
+// GFX11: v_not_b16_e64 v255.h, 0.5 op_sel:[0,1]  ; encoding: [0xff,0x40,0xe9,0xd5,0xf0,0x00,0x00,0x00]
 
-v_not_b16 v255, exec_lo
-// GFX11: v_not_b16_e64 v255, exec_lo             ; encoding: [0xff,0x00,0xe9,0xd5,0x7e,0x00,0x00,0x00]
+v_not_b16 v255.h, exec_hi
+// GFX11: v_not_b16_e64 v255.h, exec_hi op_sel:[0,1] ; encoding: [0xff,0x40,0xe9,0xd5,0x7f,0x00,0x00,0x00]
 
-v_not_b16 v255, m0
-// GFX11: v_not_b16_e64 v255, m0                  ; encoding: [0xff,0x00,0xe9,0xd5,0x7d,0x00,0x00,0x00]
+v_not_b16 v255.h, exec_lo
+// GFX11: v_not_b16_e64 v255.h, exec_lo op_sel:[0,1] ; encoding: [0xff,0x40,0xe9,0xd5,0x7e,0x00,0x00,0x00]
 
-v_not_b16 v255, null
-// GFX11: v_not_b16_e64 v255, null                ; encoding: [0xff,0x00,0xe9,0xd5,0x7c,0x00,0x00,0x00]
+v_not_b16 v255.h, m0
+// GFX11: v_not_b16_e64 v255.h, m0 op_sel:[0,1]   ; encoding: [0xff,0x40,0xe9,0xd5,0x7d,0x00,0x00,0x00]
 
-v_not_b16 v255, s1
-// GFX11: v_not_b16_e64 v255, s1                  ; encoding: [0xff,0x00,0xe9,0xd5,0x01,0x00,0x00,0x00]
+v_not_b16 v255.h, null
+// GFX11: v_not_b16_e64 v255.h, null op_sel:[0,1] ; encoding: [0xff,0x40,0xe9,0xd5,0x7c,0x00,0x00,0x00]
 
-v_not_b16 v255, s105
-// GFX11: v_not_b16_e64 v255, s105                ; encoding: [0xff,0x00,0xe9,0xd5,0x69,0x00,0x00,0x00]
+v_not_b16 v255.h, s1
+// GFX11: v_not_b16_e64 v255.h, s1 op_sel:[0,1]   ; encoding: [0xff,0x40,0xe9,0xd5,0x01,0x00,0x00,0x00]
 
-v_not_b16 v255, src_scc
-// GFX11: v_not_b16_e64 v255, src_scc             ; encoding: [0xff,0x00,0xe9,0xd5,0xfd,0x00,0x00,0x00]
+v_not_b16 v255.h, s105
+// GFX11: v_not_b16_e64 v255.h, s105 op_sel:[0,1] ; encoding: [0xff,0x40,0xe9,0xd5,0x69,0x00,0x00,0x00]
 
-v_not_b16 v255, ttmp15
-// GFX11: v_not_b16_e64 v255, ttmp15              ; encoding: [0xff,0x00,0xe9,0xd5,0x7b,0x00,0x00,0x00]
+v_not_b16 v255.h, src_scc
+// GFX11: v_not_b16_e64 v255.h, src_scc op_sel:[0,1] ; encoding: [0xff,0x40,0xe9,0xd5,0xfd,0x00,0x00,0x00]
 
-v_not_b16 v255, v1
-// GFX11: v_not_b16_e64 v255, v1                  ; encoding: [0xff,0x00,0xe9,0xd5,0x01,0x01,0x00,0x00]
+v_not_b16 v255.h, ttmp15
+// GFX11: v_not_b16_e64 v255.h, ttmp15 op_sel:[0,1] ; encoding: [0xff,0x40,0xe9,0xd5,0x7b,0x00,0x00,0x00]
 
-v_not_b16 v255, v1 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_not_b16_e64_dpp v255, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xe9,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
+v_not_b16 v255.h, v1.h
+// GFX11: v_not_b16_e64 v255.h, v1.h op_sel:[1,1] ; encoding: [0xff,0x48,0xe9,0xd5,0x01,0x01,0x00,0x00]
 
-v_not_b16 v255, v1 quad_perm:[3,2,1,0]
-// GFX11: v_not_b16_e64_dpp v255, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xe9,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
+v_not_b16 v255.h, v1.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_not_b16_e64_d...
[truncated]

@broxigarchen broxigarchen merged commit d37aa51 into llvm:main Jan 3, 2025
12 checks passed
kosarev
kosarev reviewed Jan 10, 2025
View reviewed changes
llvm/test/MC/AMDGPU/gfx11_asm_vop3_from_vop1.s
Comment on lines +2723 to +2729
// GFX11: [0x05,0x48,0xe9,0xd5,0x01,0x01,0x00,0x00]

v_not_b16_e64 v5.l, v255.h
// GFX11: [0x05,0x08,0xe9,0xd5,0xff,0x01,0x00,0x00]

v_not_b16_e64 v255.h, 0xfe0b
// GFX11: [0xff,0x40,0xe9,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
Copy link
Collaborator

@kosarev kosarev Jan 10, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

These should also have the instructions in the check lines.

Copy link
Contributor Author

@broxigarchen broxigarchen Jan 10, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for pointing this!. I'll fix it later altogether

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@kosarev kosarev kosarev left review comments

@arsenm arsenm arsenm approved these changes

@Sisyph Sisyph Awaiting requested review from Sisyph

Assignees

No one assigned

Labels

backend:AMDGPU llvm:mc Machine (object) code

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@broxigarchen @llvmbot @arsenm @kosarev