Index: clang/include/clang/Basic/TargetInfo.h =================================================================== --- clang/include/clang/Basic/TargetInfo.h +++ clang/include/clang/Basic/TargetInfo.h @@ -1704,6 +1704,9 @@ : std::optional(); } + /// Whether to support HIP image/texture API's. + virtual bool hasHIPImageSupport() const { return true; } + protected: /// Copy type and layout related info. void copyAuxTarget(const TargetInfo *Aux); Index: clang/lib/Basic/Targets/AMDGPU.h =================================================================== --- clang/lib/Basic/Targets/AMDGPU.h +++ clang/lib/Basic/Targets/AMDGPU.h @@ -46,6 +46,9 @@ /// Whether to use cumode or WGP mode. True for cumode. False for WGP mode. bool CUMode; + /// Whether having image instructions. + bool HasImage = false; + /// Target ID is device name followed by optional feature name postfixed /// by plus or minus sign delimitted by colon, e.g. gfx908:xnack+:sramecc-. /// If the target ID contains feature+, map it to true. @@ -450,6 +453,10 @@ CUMode = true; else if (F == "-cumode") CUMode = false; + else if (F == "+image-insts") + HasImage = true; + else if (F == "-image-insts") + HasImage = false; bool IsOn = F.front() == '+'; StringRef Name = StringRef(F).drop_front(); if (!llvm::is_contained(TargetIDFeatures, Name)) @@ -470,6 +477,8 @@ return getCanonicalTargetID(getArchNameAMDGCN(GPUKind), OffloadArchFeatures); } + + bool hasHIPImageSupport() const override { return HasImage; } }; } // namespace targets Index: clang/lib/Frontend/InitPreprocessor.cpp =================================================================== --- clang/lib/Frontend/InitPreprocessor.cpp +++ clang/lib/Frontend/InitPreprocessor.cpp @@ -583,8 +583,11 @@ Builder.defineMacro("__HIP_MEMORY_SCOPE_WORKGROUP", "3"); Builder.defineMacro("__HIP_MEMORY_SCOPE_AGENT", "4"); Builder.defineMacro("__HIP_MEMORY_SCOPE_SYSTEM", "5"); - if (LangOpts.CUDAIsDevice) + if (LangOpts.CUDAIsDevice) { Builder.defineMacro("__HIP_DEVICE_COMPILE__"); + if (!TI.hasHIPImageSupport()) + Builder.defineMacro("__HIP_NO_IMAGE_SUPPORT", "1"); + } if (LangOpts.GPUDefaultStream == LangOptions::GPUDefaultStreamKind::PerThread) Builder.defineMacro("HIP_API_PER_THREAD_DEFAULT_STREAM"); Index: clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl =================================================================== --- clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl +++ clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl @@ -693,12 +693,12 @@ // NOCPU: attributes #8 = { convergent nounwind } //. // GFX900: attributes #0 = { "objc_arc_inert" } -// GFX900: attributes #1 = { convergent norecurse nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" } -// GFX900: attributes #2 = { convergent norecurse nounwind "amdgpu-flat-work-group-size"="1,256" "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" "uniform-work-group-size"="false" } +// GFX900: attributes #1 = { convergent norecurse nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" } +// GFX900: attributes #2 = { convergent norecurse nounwind "amdgpu-flat-work-group-size"="1,256" "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" "uniform-work-group-size"="false" } // GFX900: attributes #3 = { nocallback nofree nosync nounwind willreturn memory(argmem: readwrite) } // GFX900: attributes #4 = { nocallback nofree nounwind willreturn memory(argmem: readwrite) } -// GFX900: attributes #5 = { convergent nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" } -// GFX900: attributes #6 = { convergent nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "enqueued-block" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" } +// GFX900: attributes #5 = { convergent nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" } +// GFX900: attributes #6 = { convergent nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "enqueued-block" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" } // GFX900: attributes #7 = { nocallback nofree nosync nounwind willreturn } // GFX900: attributes #8 = { nounwind } // GFX900: attributes #9 = { convergent nounwind } Index: clang/test/CodeGenOpenCL/amdgpu-features.cl =================================================================== --- clang/test/CodeGenOpenCL/amdgpu-features.cl +++ clang/test/CodeGenOpenCL/amdgpu-features.cl @@ -54,46 +54,46 @@ // NOCPU-WAVE32: "target-features"="+wavefrontsize32" // NOCPU-WAVE64: "target-features"="+wavefrontsize64" -// GFX600: "target-features"="+s-memtime-inst,+wavefrontsize64" -// GFX601: "target-features"="+s-memtime-inst,+wavefrontsize64" -// GFX602: "target-features"="+s-memtime-inst,+wavefrontsize64" -// GFX700: "target-features"="+ci-insts,+s-memtime-inst,+wavefrontsize64" -// GFX701: "target-features"="+ci-insts,+s-memtime-inst,+wavefrontsize64" -// GFX702: "target-features"="+ci-insts,+s-memtime-inst,+wavefrontsize64" -// GFX703: "target-features"="+ci-insts,+s-memtime-inst,+wavefrontsize64" -// GFX704: "target-features"="+ci-insts,+s-memtime-inst,+wavefrontsize64" -// GFX705: "target-features"="+ci-insts,+s-memtime-inst,+wavefrontsize64" -// GFX801: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" -// GFX802: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" -// GFX803: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" -// GFX805: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" -// GFX810: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" -// GFX900: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" -// GFX902: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" -// GFX904: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" -// GFX906: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" -// GFX908: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" -// GFX909: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" -// GFX90A: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" -// GFX90C: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" +// GFX600: "target-features"="+image-insts,+s-memtime-inst,+wavefrontsize64" +// GFX601: "target-features"="+image-insts,+s-memtime-inst,+wavefrontsize64" +// GFX602: "target-features"="+image-insts,+s-memtime-inst,+wavefrontsize64" +// GFX700: "target-features"="+ci-insts,+image-insts,+s-memtime-inst,+wavefrontsize64" +// GFX701: "target-features"="+ci-insts,+image-insts,+s-memtime-inst,+wavefrontsize64" +// GFX702: "target-features"="+ci-insts,+image-insts,+s-memtime-inst,+wavefrontsize64" +// GFX703: "target-features"="+ci-insts,+image-insts,+s-memtime-inst,+wavefrontsize64" +// GFX704: "target-features"="+ci-insts,+image-insts,+s-memtime-inst,+wavefrontsize64" +// GFX705: "target-features"="+ci-insts,+image-insts,+s-memtime-inst,+wavefrontsize64" +// GFX801: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" +// GFX802: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" +// GFX803: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" +// GFX805: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" +// GFX810: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" +// GFX900: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" +// GFX902: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" +// GFX904: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" +// GFX906: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" +// GFX908: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+image-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" +// GFX909: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" +// GFX90A: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+image-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" +// GFX90C: "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" // GFX940: "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-insts,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gfx940-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" // GFX941: "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-insts,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gfx940-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" // 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-insts,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gfx940-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" -// GFX1010: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1011: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1012: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1013: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1030: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1031: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1032: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1033: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1034: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1035: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1036: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" -// GFX1100: "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" -// GFX1101: "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" -// GFX1102: "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" -// 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" -// 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" +// GFX1010: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1011: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1012: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1013: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dpp,+gfx10-insts,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1030: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1031: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1032: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1033: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1034: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1035: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1036: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize32" +// GFX1100: "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,+image-insts,+wavefrontsize32" +// GFX1101: "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,+image-insts,+wavefrontsize32" +// GFX1102: "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,+image-insts,+wavefrontsize32" +// 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,+image-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,+image-insts,+wavefrontsize64" kernel void test() {} Index: clang/test/Driver/hip-macros.hip =================================================================== --- clang/test/Driver/hip-macros.hip +++ clang/test/Driver/hip-macros.hip @@ -42,3 +42,20 @@ // WARN-CUMODE-NOT: warning: ignoring '-mno-cumode' option as it is not currently supported for processor 'gfx906' [-Woption-ignored] // CUMODE-ON-DAG: #define __AMDGCN_CUMODE__ 1 // CUMODE-OFF-DAG: #define __AMDGCN_CUMODE__ 0 + +// RUN: %clang -E -dM --offload-arch=gfx90a --cuda-device-only -nogpuinc -nogpulib \ +// RUN: %s 2>&1 | FileCheck --check-prefix=IMAGE %s +// RUN: %clang -E -dM --offload-arch=gfx1100 --cuda-device-only -nogpuinc -nogpulib \ +// RUN: %s 2>&1 | FileCheck --check-prefix=IMAGE %s +// RUN: %clang -E -dM --offload-arch=gfx940 --cuda-device-only -nogpuinc -nogpulib \ +// RUN: %s 2>&1 | FileCheck --check-prefix=NOIMAGE %s +// RUN: %clang -E -dM --offload-arch=gfx941 --cuda-device-only -nogpuinc -nogpulib \ +// RUN: %s 2>&1 | FileCheck --check-prefix=NOIMAGE %s +// RUN: %clang -E -dM --offload-arch=gfx942 --cuda-device-only -nogpuinc -nogpulib \ +// RUN: %s 2>&1 | FileCheck --check-prefix=NOIMAGE %s +// RUN: %clang -E -dM --offload-arch=gfx1100 --cuda-device-only -nogpuinc -nogpulib \ +// RUN: -Xclang -target-feature -Xclang "-image-insts" %s 2>&1 | FileCheck --check-prefix=NOIMAGE %s +// RUN: %clang -E -dM --offload-arch=gfx940 --cuda-device-only -nogpuinc -nogpulib \ +// RUN: -Xclang -target-feature -Xclang "+image-insts" %s 2>&1 | FileCheck --check-prefix=IMAGE %s +// IMAGE-NOT: #define __HIP_NO_IMAGE_SUPPORT +// NOIMAGE: #define __HIP_NO_IMAGE_SUPPORT 1 Index: clang/test/OpenMP/amdgcn-attributes.cpp =================================================================== --- clang/test/OpenMP/amdgcn-attributes.cpp +++ clang/test/OpenMP/amdgcn-attributes.cpp @@ -33,11 +33,11 @@ } // DEFAULT: attributes #0 = { convergent noinline norecurse nounwind optnone "kernel" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "uniform-work-group-size"="true" } -// CPU: attributes #0 = { convergent noinline norecurse nounwind optnone "kernel" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" "uniform-work-group-size"="true" } +// CPU: attributes #0 = { convergent noinline norecurse nounwind optnone "kernel" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" "uniform-work-group-size"="true" } // NOIEEE: attributes #0 = { convergent noinline norecurse nounwind optnone "amdgpu-ieee"="false" "kernel" "no-nans-fp-math"="true" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "uniform-work-group-size"="true" } // UNSAFEATOMIC: attributes #0 = { convergent noinline norecurse nounwind optnone "amdgpu-unsafe-fp-atomics"="true" "kernel" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "uniform-work-group-size"="true" } // DEFAULT: attributes #1 = { convergent mustprogress noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" } -// CPU: attributes #1 = { convergent mustprogress noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" } +// CPU: attributes #1 = { convergent mustprogress noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+image-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" } // NOIEEE: attributes #1 = { convergent mustprogress noinline nounwind optnone "amdgpu-ieee"="false" "no-nans-fp-math"="true" "no-trapping-math"="true" "stack-protector-buffer-size"="8" } // UNSAFEATOMIC: attributes #1 = { convergent mustprogress noinline nounwind optnone "amdgpu-unsafe-fp-atomics"="true" "no-trapping-math"="true" "stack-protector-buffer-size"="8" } Index: flang/test/Lower/OpenMP/target_cpu_features.f90 =================================================================== --- flang/test/Lower/OpenMP/target_cpu_features.f90 +++ flang/test/Lower/OpenMP/target_cpu_features.f90 @@ -7,7 +7,7 @@ !CHECK: omp.target = #omp.target !CHECK-LABEL: func.func @_QPomp_target_simple() { Index: llvm/lib/TargetParser/TargetParser.cpp =================================================================== --- llvm/lib/TargetParser/TargetParser.cpp +++ llvm/lib/TargetParser/TargetParser.cpp @@ -280,6 +280,7 @@ Features["gfx10-3-insts"] = true; Features["gfx11-insts"] = true; Features["atomic-fadd-rtn-insts"] = true; + Features["image-insts"] = true; break; case GK_GFX1036: case GK_GFX1035: @@ -302,6 +303,7 @@ Features["gfx9-insts"] = true; Features["gfx10-insts"] = true; Features["gfx10-3-insts"] = true; + Features["image-insts"] = true; Features["s-memrealtime"] = true; Features["s-memtime-inst"] = true; break; @@ -323,6 +325,7 @@ Features["gfx8-insts"] = true; Features["gfx9-insts"] = true; Features["gfx10-insts"] = true; + Features["image-insts"] = true; Features["s-memrealtime"] = true; Features["s-memtime-inst"] = true; break; @@ -334,7 +337,27 @@ Features["atomic-ds-pk-add-16-insts"] = true; Features["atomic-flat-pk-add-16-insts"] = true; Features["atomic-global-pk-add-bf16-inst"] = true; - [[fallthrough]]; + Features["gfx90a-insts"] = true; + Features["atomic-buffer-global-pk-add-f16-insts"] = true; + Features["atomic-fadd-rtn-insts"] = true; + Features["dot3-insts"] = true; + Features["dot4-insts"] = true; + Features["dot5-insts"] = true; + Features["dot6-insts"] = true; + Features["mai-insts"] = true; + Features["dl-insts"] = true; + Features["dot1-insts"] = true; + Features["dot2-insts"] = true; + Features["dot7-insts"] = true; + Features["dot10-insts"] = true; + Features["gfx9-insts"] = true; + Features["gfx8-insts"] = true; + Features["16-bit-insts"] = true; + Features["dpp"] = true; + Features["s-memrealtime"] = true; + Features["ci-insts"] = true; + Features["s-memtime-inst"] = true; + break; case GK_GFX90A: Features["gfx90a-insts"] = true; Features["atomic-buffer-global-pk-add-f16-insts"] = true; @@ -382,6 +405,7 @@ case GK_GFX602: case GK_GFX601: case GK_GFX600: + Features["image-insts"] = true; Features["s-memtime-inst"] = true; break; case GK_NONE: