[llvm] af717d4 - [AMDGPU][MachineVerifier] Alignment check for fp32 packed math instructions

[Christudasan Devadasan via llvm-commits]

Author: Christudasan Devadasan
Date: 2022-03-17T08:21:35+05:30
New Revision: af717d4acac81b3abef6d76123b41d96c2bc7356

URL: https://github.com/llvm/llvm-project/commit/af717d4acac81b3abef6d76123b41d96c2bc7356
DIFF: https://github.com/llvm/llvm-project/commit/af717d4acac81b3abef6d76123b41d96c2bc7356.diff

LOG: [AMDGPU][MachineVerifier] Alignment check for fp32 packed math instructions

The fp32 packed math instructions are introduced in gfx90a.
If their vector register operands are not properly aligned, the
verifier should flag them. Currently, the verifier failed to
report it and the compiler ended up emitting a broken assembly.
This patch fixes that missed case in TII::verifyInstruction.

Reviewed By: arsenm

Differential Revision: https://reviews.llvm.org/D121794

Added: 
    

Modified: 
    llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
    llvm/test/CodeGen/AMDGPU/verify-gfx90a-aligned-vgprs.mir

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
index 8b79e1c8f087d..0bf3ef52de47e 100644
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -4051,6 +4051,7 @@ bool SIInstrInfo::verifyInstruction(const MachineInstr &MI,
     case AMDGPU::OPERAND_REG_IMM_INT32:
     case AMDGPU::OPERAND_REG_IMM_FP32:
     case AMDGPU::OPERAND_REG_IMM_FP32_DEFERRED:
+    case AMDGPU::OPERAND_REG_IMM_V2FP32:
       break;
     case AMDGPU::OPERAND_REG_INLINE_C_INT32:
     case AMDGPU::OPERAND_REG_INLINE_C_FP32:

diff  --git a/llvm/test/CodeGen/AMDGPU/verify-gfx90a-aligned-vgprs.mir b/llvm/test/CodeGen/AMDGPU/verify-gfx90a-aligned-vgprs.mir
index 16d308bfcc7fd..bc6137eceb389 100644
--- a/llvm/test/CodeGen/AMDGPU/verify-gfx90a-aligned-vgprs.mir
+++ b/llvm/test/CodeGen/AMDGPU/verify-gfx90a-aligned-vgprs.mir
@@ -109,6 +109,35 @@ body:            |
     %11:areg_128_align2 = IMPLICIT_DEF
     DS_WRITE_B64_gfx9 %9, %10, 0, 0, implicit $exec
     DS_WRITE_B64_gfx9 %9, %11.sub1_sub2, 0, 0, implicit $exec
+
+    ; Check aligned vgprs for FP32 Packed Math instructions.
+    ; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
+    ; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
+    ; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
+    ; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
+    ; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
+    ; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
+    ; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
+    ; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
+    ; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
+    ; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
+    ; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
+    ; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
+    %12:vreg_64 = IMPLICIT_DEF
+    %13:vreg_64_align2 = IMPLICIT_DEF
+    %14:areg_96_align2 = IMPLICIT_DEF
+    $vgpr3_vgpr4 = V_PK_MOV_B32 8, 0, 8, 0, 0, 0, 0, 0, 0, implicit $exec
+    $vgpr0_vgpr1 = V_PK_ADD_F32 0, %12, 11, %13, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    $vgpr0_vgpr1 = V_PK_ADD_F32 0, %13, 11, %12, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    $vgpr0_vgpr1 = V_PK_ADD_F32 0, %13, 11, %14.sub1_sub2, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    $vgpr0_vgpr1 = V_PK_ADD_F32 0, %14.sub1_sub2, 11, %13, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    $vgpr0_vgpr1 = V_PK_MUL_F32 0, %12, 11, %13, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    $vgpr0_vgpr1 = V_PK_MUL_F32 0, %13, 11, %12, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    $vgpr0_vgpr1 = V_PK_MUL_F32 0, %13, 11, %14.sub1_sub2, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    $vgpr0_vgpr1 = V_PK_MUL_F32 0, %14.sub1_sub2, 11, %13, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    $vgpr0_vgpr1 = nofpexcept V_PK_FMA_F32 8, %12, 8, %13, 11, %14.sub0_sub1, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    $vgpr0_vgpr1 = nofpexcept V_PK_FMA_F32 8, %13, 8, %12, 11, %14.sub0_sub1, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    $vgpr0_vgpr1 = nofpexcept V_PK_FMA_F32 8, %13, 8, %13, 11, %14.sub1_sub2, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
 ...
 
 # FIXME: Inline asm is not verified