[clang] [clang-nvlink-wrapper] Keep LTO task outputs distinct (PR #238883)
via cfe-commits
cfe-commits at lists.llvm.org
Thu Nov 5 14:00:47 PST 2026
llvmorg-github-actions[bot] wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-clang
Author: 0z5a (0z5a)
<details>
<summary>Changes</summary>
With `--save-temps` and multiple LTO tasks, the wrapper reuses the same PTX and cubin names, so later tasks overwrite earlier results and `nvlink` receives duplicate inputs. Give each task a distinct output name, serialize creation of shared temporary-file bookkeeping, and skip inactive task slots.
Fixes #<!-- -->238882
Testing:
- Full LTO two-partition and single-partition `FileCheck` regressions; Unified ThinLTO regression for the unused task slot.
- CUDA 13.2 `ptxas` and `nvlink`: successfully linked a two-kernel, two-partition image for `sm_90` and `sm_103a` with `--save-temps`. The unpatched current baseline fails with duplicate definitions.
- Loaded and ran both kernels on two GH200 GPUs and one B300 GPU; results were 111 and 222 on each device.
---
Full diff: https://github.com/llvm/llvm-project/pull/238883.diff
3 Files Affected:
- (added) clang/test/OffloadTools/clang-nvlink-wrapper/lto-save-temps.ll (+25)
- (added) clang/test/OffloadTools/clang-nvlink-wrapper/thinlto-save-temps.c (+10)
- (modified) clang/tools/clang-nvlink-wrapper/ClangNVLinkWrapper.cpp (+20-7)
``````````diff
diff --git a/clang/test/OffloadTools/clang-nvlink-wrapper/lto-save-temps.ll b/clang/test/OffloadTools/clang-nvlink-wrapper/lto-save-temps.ll
new file mode 100644
index 00000000000000..4adadb5a144858
--- /dev/null
+++ b/clang/test/OffloadTools/clang-nvlink-wrapper/lto-save-temps.ll
@@ -0,0 +1,25 @@
+; REQUIRES: nvptx-registered-target
+;
+; RUN: llvm-as %s -o %t.bc
+; RUN: mkdir -p %t.dir
+; RUN: cd %t.dir && clang-nvlink-wrapper --dry-run --save-temps --plugin-opt=lto-partitions=2 -arch sm_90 %t.bc -o multi 2>&1 | FileCheck %s --check-prefix=MULTI
+; RUN: cd %t.dir && clang-nvlink-wrapper --dry-run --save-temps -arch sm_90 %t.bc -o single 2>&1 | FileCheck %s --check-prefix=SINGLE
+;
+; MULTI: ptxas{{.*}} -c multi.0.s {{.*}} -o multi.0.cubin
+; MULTI: ptxas{{.*}} -c multi.1.s {{.*}} -o multi.1.cubin
+; MULTI: nvlink{{.*}} -o multi multi.0.cubin multi.1.cubin
+; SINGLE: ptxas{{.*}} -c single.s {{.*}} -o single.cubin
+; SINGLE: nvlink{{.*}} -o single single.cubin
+
+target datalayout = "e-p6:32:32-i64:64-i128:128-i256:256-v16:16-v32:32-n16:32:64"
+target triple = "nvptx64-nvidia-cuda"
+
+define i32 @foo(i32 %x) {
+ %r = add i32 %x, 1
+ ret i32 %r
+}
+
+define i32 @bar(i32 %x) {
+ %r = mul i32 %x, 3
+ ret i32 %r
+}
diff --git a/clang/test/OffloadTools/clang-nvlink-wrapper/thinlto-save-temps.c b/clang/test/OffloadTools/clang-nvlink-wrapper/thinlto-save-temps.c
new file mode 100644
index 00000000000000..a182700e5d9884
--- /dev/null
+++ b/clang/test/OffloadTools/clang-nvlink-wrapper/thinlto-save-temps.c
@@ -0,0 +1,10 @@
+// REQUIRES: nvptx-registered-target
+// RUN: %clang -cc1 -triple nvptx64-nvidia-cuda -flto=thin -funified-lto -emit-llvm-bc %s -o %t.bc
+// RUN: mkdir -p %t.dir
+// RUN: cd %t.dir && clang-nvlink-wrapper --dry-run --save-temps --plugin-opt=thinlto -arch sm_90 %t.bc -o thin 2>&1 | FileCheck %s
+// CHECK-NOT: ptxas{{.*}} -c -O
+// CHECK: ptxas{{.*}} -c thin.1.s {{.*}} -o thin.1.cubin
+// CHECK-NEXT: {{.*}}nvlink{{.*}} -o thin thin.1.cubin
+
+int foo(int x) { return x + 1; }
+int bar(int x) { return x * 3; }
diff --git a/clang/tools/clang-nvlink-wrapper/ClangNVLinkWrapper.cpp b/clang/tools/clang-nvlink-wrapper/ClangNVLinkWrapper.cpp
index 6550902a6a6551..36ea0a3768471e 100644
--- a/clang/tools/clang-nvlink-wrapper/ClangNVLinkWrapper.cpp
+++ b/clang/tools/clang-nvlink-wrapper/ClangNVLinkWrapper.cpp
@@ -48,6 +48,8 @@
#include "llvm/Support/TargetSelect.h"
#include "llvm/Support/WithColor.h"
+#include <mutex>
+
using namespace llvm;
using namespace llvm::opt;
using namespace llvm::object;
@@ -327,7 +329,8 @@ struct Symbol {
bool UsedInRegularObj;
};
-Expected<StringRef> runPTXAs(StringRef File, const ArgList &Args) {
+Expected<StringRef> runPTXAs(StringRef File, const ArgList &Args, size_t Task,
+ size_t MaxTasks) {
SmallVector<StringRef, 1> SearchPaths;
if (Arg *A = Args.getLastArg(OPT_cuda_path_EQ))
SearchPaths.push_back(Args.MakeArgString(A->getValue() + Twine("/bin")));
@@ -342,8 +345,11 @@ Expected<StringRef> runPTXAs(StringRef File, const ArgList &Args) {
return createStringError(
"must pass in an explicit nvptx64 gpu architecture to 'ptxas'");
- auto TempFileOrErr = createTempFile(
- Args, sys::path::stem(Args.getLastArgValue(OPT_o, "a.out")), "cubin");
+ std::string Prefix =
+ sys::path::stem(Args.getLastArgValue(OPT_o, "a.out")).str();
+ if (MaxTasks > 1)
+ Prefix += "." + std::to_string(Task);
+ auto TempFileOrErr = createTempFile(Args, Prefix, "cubin");
if (!TempFileOrErr)
return TempFileOrErr.takeError();
@@ -685,6 +691,7 @@ getInput(const cl::LibraryOptionsContext &LibraryOptions, const ArgList &Args) {
// Run the LTO job to compile the bitcode.
size_t MaxTasks = LTOBackend.getMaxTasks();
SmallVector<StringRef> LTOFiles(MaxTasks);
+ std::mutex TempFilesMutex;
auto AddStream =
[&](size_t Task,
const Twine &ModuleName) -> std::unique_ptr<CachedFileStream> {
@@ -693,8 +700,12 @@ getInput(const cl::LibraryOptionsContext &LibraryOptions, const ArgList &Args) {
if (Args.hasArg(OPT_lto_emit_asm))
TempFile = Args.getLastArgValue(OPT_o, "a.out");
else {
- auto TempFileOrErr = createTempFile(
- Args, sys::path::stem(Args.getLastArgValue(OPT_o, "a.out")), "s");
+ std::lock_guard<std::mutex> Lock(TempFilesMutex);
+ std::string Prefix =
+ sys::path::stem(Args.getLastArgValue(OPT_o, "a.out")).str();
+ if (MaxTasks > 1)
+ Prefix += "." + std::to_string(Task);
+ auto TempFileOrErr = createTempFile(Args, Prefix, "s");
if (!TempFileOrErr)
reportError(TempFileOrErr.takeError());
TempFile = Args.MakeArgString(*TempFileOrErr);
@@ -711,8 +722,10 @@ getInput(const cl::LibraryOptionsContext &LibraryOptions, const ArgList &Args) {
if (Args.hasArg(OPT_lto_emit_llvm) || Args.hasArg(OPT_lto_emit_asm))
return Files;
- for (StringRef LTOFile : LTOFiles) {
- auto FileOrErr = runPTXAs(LTOFile, Args);
+ for (auto [Task, LTOFile] : enumerate(LTOFiles)) {
+ if (LTOFile.empty())
+ continue;
+ auto FileOrErr = runPTXAs(LTOFile, Args, Task, MaxTasks);
if (!FileOrErr)
return FileOrErr.takeError();
Files.emplace_back(*FileOrErr);
``````````
</details>
https://github.com/llvm/llvm-project/pull/238883
More information about the cfe-commits
mailing list