[AMDGPU] GlobalISel for f8 conversions (llvm#80503)

Author: rampitec

llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp

@@ -4497,6 +4497,14 @@ AMDGPURegisterBankInfo::getInstrMapping(const MachineInstr &MI) const {
     case Intrinsic::amdgcn_dot4_f32_bf8_fp8:
     case Intrinsic::amdgcn_dot4_f32_fp8_fp8:
     case Intrinsic::amdgcn_dot4_f32_bf8_bf8:
+    case Intrinsic::amdgcn_cvt_f32_fp8:
+    case Intrinsic::amdgcn_cvt_f32_bf8:
+    case Intrinsic::amdgcn_cvt_pk_f32_fp8:
+    case Intrinsic::amdgcn_cvt_pk_f32_bf8:
+    case Intrinsic::amdgcn_cvt_pk_fp8_f32:
+    case Intrinsic::amdgcn_cvt_pk_bf8_f32:
+    case Intrinsic::amdgcn_cvt_sr_fp8_f32:
+    case Intrinsic::amdgcn_cvt_sr_bf8_f32:
     case Intrinsic::amdgcn_wmma_bf16_16x16x16_bf16:
     case Intrinsic::amdgcn_wmma_f16_16x16x16_f16:
     case Intrinsic::amdgcn_wmma_bf16_16x16x16_bf16_tied:

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.cvt.fp8.ll

@@ -1,6 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -mcpu=gfx940 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX940 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX12 %s
+; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx940 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX940 %s
+; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx940 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX940 %s
+; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx1200 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX12 %s
+; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx1200 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX12 %s
 
 declare float @llvm.amdgcn.cvt.f32.bf8(i32, i32)
 declare float @llvm.amdgcn.cvt.f32.fp8(i32, i32)