AMDGPU: Allow readonly features to be written to IR when there is no target

Author: changpeng

clang/lib/Basic/Targets/AMDGPU.cpp

@@ -266,11 +266,9 @@ AMDGPUTargetInfo::AMDGPUTargetInfo(const llvm::Triple &Triple,
 
   MaxAtomicPromoteWidth = MaxAtomicInlineWidth = 64;
   CUMode = !(GPUFeatures & llvm::AMDGPU::FEATURE_WGP);
-  // Mark these features as read-only when the target supports them.
-  llvm::StringMap<bool> Features;
-  llvm::AMDGPU::fillAMDGPUFeatureMap(Opts.CPU, Triple, Features);
+
   for (auto F : {"image-insts", "gws", "vmem-to-lds-load-insts"}) {
-    if (Features[F] == true)
+    if (GPUKind != llvm::AMDGPU::GK_NONE)
       ReadOnlyFeatures.insert(F);
   }
   HalfArgsAndReturns = true;

clang/test/CodeGenOpenCL/amdgpu-target-supported-readonly-features.cl renamed to clang/test/CodeGenOpenCL/amdgpu-readonly-features-written-with-no-target.cl

@@ -1,16 +1,16 @@
 // REQUIRES: amdgpu-registered-target
 
-// Check the "gws" feature will not be written to the IR
-// if the target supports it (gfx942 and gfx1100) 
+// Check the readonly feature will can be written to the IR
+// if there is no target specified.
 
 // RUN: %clang_cc1 -triple amdgcn -emit-llvm -o - %s | FileCheck --check-prefix=NOCPU %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx942 -emit-llvm -o - %s | FileCheck --check-prefix=GFX942 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1100 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1100 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1200 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1200 %s
 
-__attribute__((target("gws"))) void test() {}
+__attribute__((target("gws,image-insts,vmem-to-lds-load-insts"))) void test() {}
 
-// NOCPU: "target-features"="+gws"
+// NOCPU: "target-features"="+gws,+image-insts,+vmem-to-lds-load-insts"
 // GFX942: "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,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+fp8-conversion-insts,+fp8-insts,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gfx940-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,+xf32-insts"
 // GFX1100: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot12-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-buffer-pk-add-bf16-inst,+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,+dot11-insts,+dot12-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+gws,+wavefrontsize32"
+// GFX1200: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+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,+dot11-insts,+dot12-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"