yaxunl created this revision.
yaxunl added reviewers: b-sumner, arsenm, tra.
Herald added subscribers: kerbowa, hiraditya, jvesely.
Herald added a project: All.
yaxunl requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.
HIP texture/image support is optional as some devices
do not have image instructions. A macro `__HIP_NO_IMAGE_SUPPORT`
is defined for device not supporting images
(https://github.com/ROCm-Developer-Tools/HIP/blob/d0448aa4c4dd0f4b29ccf6a663b7f5ad9f5183e0/docs/reference/kernel_language.md?plain=1#L426
)
Currently the macro is defined by HIP header based on predefined macros
for GPU, e.g `__gfx*__` , which is error prone. This patch let clang
emit the predefined macro.
https://reviews.llvm.org/D151349
Files:
clang/include/clang/Basic/TargetInfo.h
clang/lib/Basic/Targets/AMDGPU.h
clang/lib/Frontend/InitPreprocessor.cpp
clang/test/Driver/hip-macros.hip
llvm/lib/TargetParser/TargetParser.cpp
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:
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="-image-insts" %s 2>&1 | FileCheck --check-prefix=IMAGE %s
+// RUN: %clang -E -dM --offload-arch=gfx940 --cuda-device-only -nogpuinc -nogpulib \
+// RUN: -Xclang -target-feature="+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/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/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/include/clang/Basic/TargetInfo.h
===================================================================
--- clang/include/clang/Basic/TargetInfo.h
+++ clang/include/clang/Basic/TargetInfo.h
@@ -1704,6 +1704,9 @@
: std::optional<VersionTuple>();
}
+ /// 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);
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
