[AMDGPU] Correctly pass the target-id to ld.lld
#101037
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
jhuber6
requested review from
arsenm,
doru1004,
JonChesterfield,
shiltian and
yxsamliu
llvmbot
added
clang
|
@llvm/pr-subscribers-clang @llvm/pr-subscribers-backend-amdgpu Author: Joseph Huber (jhuber6) ChangesSummary: Full diff: https://github.com/llvm/llvm-project/pull/101037.diff 2 Files Affected:
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
|
arsenm
reviewed
Jul 29, 2024
| @@ -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)) | |||
| std::vector<StringRef> Features; | ||
| getAMDGPUTargetFeatures(C.getDriver(), getToolChain().getTriple(), Args, | ||
| Features); | ||
| if (!Features.empty()) |
There was a problem hiding this comment.
I thought the LLVM style removed braces on single line if statements?
There was a problem hiding this comment.
I figured this qualifies for the outline in https://llvm.org/docs/CodingStandards.html#don-t-use-braces-on-simple-single-statement-bodies-of-if-else-loop-statements
There was a problem hiding this comment.
I guess it's up to interpretation, but I've rarely seen code get braces even if it is formatted into a separate line. I can add it if you think it's important
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`.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary:
The
ld.lldlinker handles LTO, but it does not understand thetarget-id syntax some AMDGPU targets use. This patch parses the
target-id and passes the processor name in
-mcpuand features in-mattr.