[clang] [AMDGPU] Correctly pass the target-id to `ld.lld` (PR #101037)
via cfe-commits
cfe-commits at lists.llvm.org
Mon Jul 29 09:33:04 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Joseph Huber (jhuber6)
<details>
<summary>Changes</summary>
Summary:
The `ld.lld` linker handles LTO, but it does not understand the
target-id syntax some AMDGPU targets use. This patch parses the
target-id and passes the processor name in `-mcpu` and features in
`-mattr`.
---
Full diff: https://github.com/llvm/llvm-project/pull/101037.diff
2 Files Affected:
- (modified) clang/lib/Driver/ToolChains/AMDGPU.cpp (+11-1)
- (modified) clang/test/Driver/amdgpu-toolchain.c (+3-3)
``````````diff
diff --git a/clang/lib/Driver/ToolChains/AMDGPU.cpp b/clang/lib/Driver/ToolChains/AMDGPU.cpp
index f796c31af8f67..92183ae377516 100644
--- a/clang/lib/Driver/ToolChains/AMDGPU.cpp
+++ b/clang/lib/Driver/ToolChains/AMDGPU.cpp
@@ -634,7 +634,17 @@ void amdgpu::Linker::ConstructJob(Compilation &C, const JobAction &JA,
C.getDriver().getLTOMode() == LTOK_Thin);
else if (Args.hasArg(options::OPT_mcpu_EQ))
CmdArgs.push_back(Args.MakeArgString(
- "-plugin-opt=mcpu=" + Args.getLastArgValue(options::OPT_mcpu_EQ)));
+ "-plugin-opt=mcpu=" +
+ getProcessorFromTargetID(getToolChain().getTriple(),
+ Args.getLastArgValue(options::OPT_mcpu_EQ))));
+
+ // Always pass the target-id features to the LTO job.
+ std::vector<StringRef> Features;
+ getAMDGPUTargetFeatures(C.getDriver(), getToolChain().getTriple(), Args,
+ Features);
+ if (!Features.empty())
+ CmdArgs.push_back(
+ Args.MakeArgString("-plugin-opt=-mattr=" + llvm::join(Features, ",")));
addGPULibraries(getToolChain(), Args, CmdArgs);
diff --git a/clang/test/Driver/amdgpu-toolchain.c b/clang/test/Driver/amdgpu-toolchain.c
index ebd1158b63074..b60d31bae6270 100644
--- a/clang/test/Driver/amdgpu-toolchain.c
+++ b/clang/test/Driver/amdgpu-toolchain.c
@@ -18,12 +18,12 @@
// AS_LINK_UR: "-cc1as"
// AS_LINK_UR: ld.lld{{.*}} "--no-undefined"{{.*}} "--unresolved-symbols=ignore-all"
-// RUN: %clang -### --target=amdgcn-amd-amdhsa -mcpu=gfx906 -nogpulib \
+// RUN: %clang -### --target=amdgcn-amd-amdhsa -mcpu=gfx90a:xnack+:sramecc- -nogpulib \
// RUN: -L. -flto -fconvergent-functions %s 2>&1 | FileCheck -check-prefixes=LTO,MCPU %s
-// RUN: %clang -### --target=amdgcn-amd-amdhsa -mcpu=gfx906 -nogpulib \
+// RUN: %clang -### --target=amdgcn-amd-amdhsa -mcpu=gfx90a:xnack+:sramecc- -nogpulib \
// RUN: -L. -fconvergent-functions %s 2>&1 | FileCheck -check-prefix=MCPU %s
// LTO: clang{{.*}} "-flto=full"{{.*}}"-fconvergent-functions"
-// MCPU: ld.lld{{.*}}"-L."{{.*}}"-plugin-opt=mcpu=gfx906"
+// MCPU: ld.lld{{.*}}"-L."{{.*}}"-plugin-opt=mcpu=gfx90a"{{.*}}"-plugin-opt=-mattr=-sramecc,+xnack"
// RUN: %clang -### --target=amdgcn-amd-amdhsa -mcpu=gfx906 -nogpulib \
// RUN: -fuse-ld=ld %s 2>&1 | FileCheck -check-prefixes=LD %s
``````````
</details>
https://github.com/llvm/llvm-project/pull/101037
More information about the cfe-commits
mailing list