Skip to content

Commit 055893f

Browse files
authored
[AMDGPU][True16][MC] duplicate vop1 tests to fake16 and update real-true16 flags for GFX12 (#100849)
duplicate vop1 tests to fake16 and update real-true16 flags for GFX12 creating duplications here to avoid bulk copy in the following true16 patches --------- Co-authored-by: guochen2 <guochen2@amd.com>
1 parent 366eade commit 055893f

8 files changed

+7562
-9
lines changed

llvm/test/MC/AMDGPU/gfx12_asm_vop1-fake16.s

Lines changed: 3597 additions & 0 deletions
Large diffs are not rendered by default.

llvm/test/MC/AMDGPU/gfx12_asm_vop1.s

Lines changed: 6 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,9 @@
1-
// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize32 -show-encoding %s | FileCheck --strict-whitespace --check-prefixes=GFX12,GFX12-ASM %s
2-
// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize32 -show-encoding %s | %extract-encodings | llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize32 -disassemble -show-encoding | FileCheck --strict-whitespace --check-prefixes=GFX12,GFX12-DIS %s
3-
// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64 -show-encoding %s | FileCheck --strict-whitespace --check-prefixes=GFX12,GFX12-ASM %s
4-
// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64 -show-encoding %s | %extract-encodings | llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64 -disassemble -show-encoding | FileCheck --strict-whitespace --check-prefixes=GFX12,GFX12-DIS %s
1+
// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize32,+real-true16 -show-encoding %s | FileCheck --strict-whitespace --check-prefixes=GFX12,GFX12-ASM %s
2+
// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize32,+real-true16 -show-encoding %s | %extract-encodings | llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize32 -disassemble -show-encoding | FileCheck --strict-whitespace --check-prefixes=GFX12,GFX12-DIS %s
3+
// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64,+real-true16 -show-encoding %s | FileCheck --strict-whitespace --check-prefixes=GFX12,GFX12-ASM %s
4+
// RUN: llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64,+real-true16 -show-encoding %s | %extract-encodings | llvm-mc -triple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64 -disassemble -show-encoding | FileCheck --strict-whitespace --check-prefixes=GFX12,GFX12-DIS %s
5+
6+
// this file will be converted to true16 format when more true16 instructions are supported
57

68
v_bfrev_b32_e32 v5, v1
79
// GFX12: v_bfrev_b32_e32 v5, v1 ; encoding: [0x01,0x71,0x0a,0x7e]

0 commit comments

Comments
 (0)