[AMDGPU] Do not emit V_DOT2C_F32_F16_e32 on GFX12 (#78709)

That instruction is not supported on GFX12.
Added a testcase which previously crashed without this change.

Co-authored-by: pvanhout <[email protected]>

Author: jayfoad

clang/test/CodeGenOpenCL/amdgpu-features.cl

@@ -100,8 +100,8 @@
 // GFX1103: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
 // GFX1150: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
 // GFX1151: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
-// GFX1200: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
-// GFX1201: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
+// GFX1200: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
+// GFX1201: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
 
 // GFX1103-W64: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize64"
 

llvm/lib/Target/AMDGPU/AMDGPU.td

@@ -1487,7 +1487,6 @@ def FeatureISAVersion12 : FeatureSet<
   [FeatureGFX12,
    FeatureLDSBankCount32,
    FeatureDLInsts,
-   FeatureDot5Insts,
    FeatureDot7Insts,
    FeatureDot8Insts,
    FeatureDot9Insts,

llvm/lib/TargetParser/TargetParser.cpp

@@ -275,7 +275,6 @@ void AMDGPU::fillAMDGPUFeatureMap(StringRef GPU, const Triple &T,
     case GK_GFX1201:
     case GK_GFX1200:
       Features["ci-insts"] = true;
-      Features["dot5-insts"] = true;
       Features["dot7-insts"] = true;
       Features["dot8-insts"] = true;
       Features["dot9-insts"] = true;

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.fdot2.ll

@@ -3,12 +3,14 @@
 ; RUN: llc -mtriple=amdgcn -mcpu=gfx1011 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=GCN,GFX10
 ; RUN: llc -mtriple=amdgcn -mcpu=gfx1012 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=GCN,GFX10
 ; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -amdgpu-enable-vopd=0 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=GCN,GFX10
+; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -amdgpu-enable-vopd=0 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=GCN,GFX12
 
 declare float @llvm.amdgcn.fdot2(<2 x half> %a, <2 x half> %b, float %c, i1 %clamp)
 
 ; GCN-LABEL: {{^}}test_llvm_amdgcn_fdot2_clamp
 ; GFX9:   v_dot2_f32_f16 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} clamp{{$}}
 ; GFX10:  v_dot2_f32_f16 v{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}} clamp{{$}}
+; GFX12:  v_dot2_f32_f16 v{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}} clamp{{$}}
 define amdgpu_kernel void @test_llvm_amdgcn_fdot2_clamp(
     ptr addrspace(1) %r,
     ptr addrspace(1) %a,
@@ -27,6 +29,7 @@ entry:
 ; GFX906: v_dot2_f32_f16 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}{{$}}
 ; GFX940: v_dot2c_f32_f16_e32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}{{$}}
 ; GFX10:  {{v_dot2c_f32_f16|v_dot2acc_f32_f16}} v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}{{$}}
+; GFX12: v_dot2_f32_f16 v{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}{{$}}
 define amdgpu_kernel void @test_llvm_amdgcn_fdot2_no_clamp(
     ptr addrspace(1) %r,
     ptr addrspace(1) %a,
@@ -44,6 +47,7 @@ entry:
 ; GFX9-LABEL: {{^}}fdot2_inline_literal
 ; GFX906: v_dot2_f32_f16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, 1.0
 ; GFX940: v_dot2c_f32_f16_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}{{$}}
+; GFX12: v_dot2_f32_f16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, 1.0{{$}}
 define float @fdot2_inline_literal(<2 x half> %a, <2 x half> %b) {
   %ret = tail call float @llvm.amdgcn.fdot2(<2 x half> %a, <2 x half> %b, float 1.0, i1 false)
   ret float %ret