caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[HIP][HIPSTDPAR] Re-work allocation interposition for hipstdpar (#138790)

Browse Source 
The allocation interposition mode had a number of issues, which are
primarily addressed in the library component via
<https://github.com/ROCm/rocThrust/pull/543>. However, it is necessary
to interpose some additional symbols, which this patch does.
Furthermore, to implement this in a compatible way, we guard the new
implementation under a V1 macro, which is defined in addition to the
existing `__HIPSTDPAR_INTERPOSE_ALLOC__` one.
This commit is contained in:
Alex Voicu
2025-05-07 14:14:25 +01:00
committed by GitHub
parent 5dd1421da6
commit 3feb8b42e9
5 changed files with 92 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
clang/docs/HIPSupport.rst
View File

@@ -518,7 +518,7 @@ Predefined Macros
* - ``__HIPSTDPAR__``
- Defined when Clang is compiling code in algorithm offload mode, enabled
with the ``--hipstdpar`` compiler option.
* - ``__HIPSTDPAR_INTERPOSE_ALLOC__``
* - ``__HIPSTDPAR_INTERPOSE_ALLOC__`` / ``__HIPSTDPAR_INTERPOSE_ALLOC_V1__``
- Defined only when compiling in algorithm offload mode, when the user
enables interposition mode with the ``--hipstdpar-interpose-alloc``
compiler option, indicating that all dynamic memory allocation /

4
clang/lib/Frontend/InitPreprocessor.cpp
View File

@@ -618,8 +618,10 @@ static void InitializeStandardPredefinedMacros(const TargetInfo &TI,
Builder.defineMacro("__HIP_MEMORY_SCOPE_SYSTEM", "5");
if (LangOpts.HIPStdPar) {
Builder.defineMacro("__HIPSTDPAR__");
if (LangOpts.HIPStdParInterposeAlloc)
if (LangOpts.HIPStdParInterposeAlloc) {
Builder.defineMacro("__HIPSTDPAR_INTERPOSE_ALLOC__");
Builder.defineMacro("__HIPSTDPAR_INTERPOSE_ALLOC_V1__");
}
}
if (LangOpts.CUDAIsDevice) {
Builder.defineMacro("__HIP_DEVICE_COMPILE__");

3
clang/test/Preprocessor/predefined-macros.c
View File

@@ -304,11 +304,13 @@
// RUN: %clang_cc1 %s -E -dM -o - -x hip --hipstdpar -triple x86_64-unknown-linux-gnu \
// RUN: | FileCheck -match-full-lines %s --check-prefix=CHECK-HIPSTDPAR
// CHECK-HIPSTDPAR: #define __HIPSTDPAR__ 1
// CHECK-HIPSTDPAR-NOT: #define __HIPSTDPAR_INTERPOSE_ALLOC_V1__ 1
// CHECK-HIPSTDPAR-NOT: #define __HIPSTDPAR_INTERPOSE_ALLOC__ 1
// RUN: %clang_cc1 %s -E -dM -o - -x hip --hipstdpar --hipstdpar-interpose-alloc \
// RUN: -triple x86_64-unknown-linux-gnu | FileCheck -match-full-lines %s \
// RUN: --check-prefix=CHECK-HIPSTDPAR-INTERPOSE
// CHECK-HIPSTDPAR-INTERPOSE: #define __HIPSTDPAR_INTERPOSE_ALLOC_V1__ 1
// CHECK-HIPSTDPAR-INTERPOSE: #define __HIPSTDPAR_INTERPOSE_ALLOC__ 1
// CHECK-HIPSTDPAR-INTERPOSE: #define __HIPSTDPAR__ 1
@@ -316,4 +318,5 @@
// RUN: -triple amdgcn-amd-amdhsa -fcuda-is-device | FileCheck -match-full-lines \
// RUN: %s --check-prefix=CHECK-HIPSTDPAR-INTERPOSE-DEV-NEG
// CHECK-HIPSTDPAR-INTERPOSE-DEV-NEG: #define __HIPSTDPAR__ 1
// CHECK-HIPSTDPAR-INTERPOSE-DEV-NEG-NOT: #define __HIPSTDPAR_INTERPOSE_ALLOC_V1__ 1
// CHECK-HIPSTDPAR-INTERPOSE-DEV-NEG-NOT: #define __HIPSTDPAR_INTERPOSE_ALLOC__ 1

105
llvm/lib/Transforms/HipStdPar/HipStdPar.cpp
View File

@@ -231,45 +231,55 @@ PreservedAnalyses
}
static constexpr std::pair<StringLiteral, StringLiteral> ReplaceMap[]{
{"aligned_alloc", "__hipstdpar_aligned_alloc"},
{"calloc", "__hipstdpar_calloc"},
{"free", "__hipstdpar_free"},
{"malloc", "__hipstdpar_malloc"},
{"memalign", "__hipstdpar_aligned_alloc"},
{"posix_memalign", "__hipstdpar_posix_aligned_alloc"},
{"realloc", "__hipstdpar_realloc"},
{"reallocarray", "__hipstdpar_realloc_array"},
{"_ZdaPv", "__hipstdpar_operator_delete"},
{"_ZdaPvm", "__hipstdpar_operator_delete_sized"},
{"_ZdaPvSt11align_val_t", "__hipstdpar_operator_delete_aligned"},
{"_ZdaPvmSt11align_val_t", "__hipstdpar_operator_delete_aligned_sized"},
{"_ZdlPv", "__hipstdpar_operator_delete"},
{"_ZdlPvm", "__hipstdpar_operator_delete_sized"},
{"_ZdlPvSt11align_val_t", "__hipstdpar_operator_delete_aligned"},
{"_ZdlPvmSt11align_val_t", "__hipstdpar_operator_delete_aligned_sized"},
{"_Znam", "__hipstdpar_operator_new"},
{"_ZnamRKSt9nothrow_t", "__hipstdpar_operator_new_nothrow"},
{"_ZnamSt11align_val_t", "__hipstdpar_operator_new_aligned"},
{"_ZnamSt11align_val_tRKSt9nothrow_t",
"__hipstdpar_operator_new_aligned_nothrow"},
{"aligned_alloc", "__hipstdpar_aligned_alloc"},
{"calloc", "__hipstdpar_calloc"},
{"free", "__hipstdpar_free"},
{"malloc", "__hipstdpar_malloc"},
{"memalign", "__hipstdpar_aligned_alloc"},
{"mmap", "__hipstdpar_mmap"},
{"munmap", "__hipstdpar_munmap"},
{"posix_memalign", "__hipstdpar_posix_aligned_alloc"},
{"realloc", "__hipstdpar_realloc"},
{"reallocarray", "__hipstdpar_realloc_array"},
{"_ZdaPv", "__hipstdpar_operator_delete"},
{"_ZdaPvm", "__hipstdpar_operator_delete_sized"},
{"_ZdaPvSt11align_val_t", "__hipstdpar_operator_delete_aligned"},
{"_ZdaPvmSt11align_val_t", "__hipstdpar_operator_delete_aligned_sized"},
{"_ZdlPv", "__hipstdpar_operator_delete"},
{"_ZdlPvm", "__hipstdpar_operator_delete_sized"},
{"_ZdlPvSt11align_val_t", "__hipstdpar_operator_delete_aligned"},
{"_ZdlPvmSt11align_val_t", "__hipstdpar_operator_delete_aligned_sized"},
{"_Znam", "__hipstdpar_operator_new"},
{"_ZnamRKSt9nothrow_t", "__hipstdpar_operator_new_nothrow"},
{"_ZnamSt11align_val_t", "__hipstdpar_operator_new_aligned"},
{"_ZnamSt11align_val_tRKSt9nothrow_t",
"__hipstdpar_operator_new_aligned_nothrow"},
{"_Znwm", "__hipstdpar_operator_new"},
{"_ZnwmRKSt9nothrow_t", "__hipstdpar_operator_new_nothrow"},
{"_ZnwmSt11align_val_t", "__hipstdpar_operator_new_aligned"},
{"_ZnwmSt11align_val_tRKSt9nothrow_t",
"__hipstdpar_operator_new_aligned_nothrow"},
{"__builtin_calloc", "__hipstdpar_calloc"},
{"__builtin_free", "__hipstdpar_free"},
{"__builtin_malloc", "__hipstdpar_malloc"},
{"__builtin_operator_delete", "__hipstdpar_operator_delete"},
{"__builtin_operator_new", "__hipstdpar_operator_new"},
{"__builtin_realloc", "__hipstdpar_realloc"},
{"__libc_calloc", "__hipstdpar_calloc"},
{"__libc_free", "__hipstdpar_free"},
{"__libc_malloc", "__hipstdpar_malloc"},
{"__libc_memalign", "__hipstdpar_aligned_alloc"},
{"__libc_realloc", "__hipstdpar_realloc"}
};
{"_Znwm", "__hipstdpar_operator_new"},
{"_ZnwmRKSt9nothrow_t", "__hipstdpar_operator_new_nothrow"},
{"_ZnwmSt11align_val_t", "__hipstdpar_operator_new_aligned"},
{"_ZnwmSt11align_val_tRKSt9nothrow_t",
"__hipstdpar_operator_new_aligned_nothrow"},
{"__builtin_calloc", "__hipstdpar_calloc"},
{"__builtin_free", "__hipstdpar_free"},
{"__builtin_malloc", "__hipstdpar_malloc"},
{"__builtin_operator_delete", "__hipstdpar_operator_delete"},
{"__builtin_operator_new", "__hipstdpar_operator_new"},
{"__builtin_realloc", "__hipstdpar_realloc"},
{"__libc_calloc", "__hipstdpar_calloc"},
{"__libc_free", "__hipstdpar_free"},
{"__libc_malloc", "__hipstdpar_malloc"},
{"__libc_memalign", "__hipstdpar_aligned_alloc"},
{"__libc_realloc", "__hipstdpar_realloc"}};
static constexpr std::pair<StringLiteral, StringLiteral> HiddenMap[]{
// hidden_malloc and hidden_free are only kept for backwards compatibility /
// legacy purposes, and we should remove them in the future
{"__hipstdpar_hidden_malloc", "__libc_malloc"},
{"__hipstdpar_hidden_free", "__libc_free"},
{"__hipstdpar_hidden_memalign", "__libc_memalign"},
{"__hipstdpar_hidden_mmap", "mmap"},
{"__hipstdpar_hidden_munmap", "munmap"}};
PreservedAnalyses
HipStdParAllocationInterpositionPass::run(Module &M, ModuleAnalysisManager&) {
@@ -299,19 +309,14 @@ HipStdParAllocationInterpositionPass::run(Module &M, ModuleAnalysisManager&) {
}
}
if (auto F = M.getFunction("__hipstdpar_hidden_malloc")) {
auto LibcMalloc = M.getOrInsertFunction(
"__libc_malloc", F->getFunctionType(), F->getAttributes());
F->replaceAllUsesWith(LibcMalloc.getCallee());
for (auto &&HR : HiddenMap) {
if (auto F = M.getFunction(HR.first)) {
auto R = M.getOrInsertFunction(HR.second, F->getFunctionType(),
F->getAttributes());
F->replaceAllUsesWith(R.getCallee());
eraseFromModule(*F);
}
if (auto F = M.getFunction("__hipstdpar_hidden_free")) {
auto LibcFree = M.getOrInsertFunction("__libc_free", F->getFunctionType(),
F->getAttributes());
F->replaceAllUsesWith(LibcFree.getCallee());
eraseFromModule(*F);
eraseFromModule(*F);
}
}
return PreservedAnalyses::none();

32
llvm/test/Transforms/HipStdPar/allocation-interposition.ll
View File

@@ -16,6 +16,16 @@ declare void @__hipstdpar_hidden_free(ptr)
declare ptr @__hipstdpar_hidden_malloc(i64)
declare ptr @__hipstdpar_hidden_memalign(i64, i64)
declare ptr @__hipstdpar_hidden_mmap(ptr, i64, i32, i32, i32, i64)
declare i32 @__hipstdpar_hidden_munmap(ptr, i64)
declare ptr @__hipstdpar_mmap(ptr, i64, i32, i32, i32, i64)
declare i32 @__hipstdpar_munmap(ptr, i64)
declare ptr @__hipstdpar_realloc(ptr, i64)
declare ptr @__hipstdpar_realloc_array(ptr, i64, i64)
@@ -171,7 +181,21 @@ define dso_local noundef i32 @allocs() {
; CHECK: call void @__hipstdpar_free(ptr noundef %28)
call void @__libc_free(ptr noundef %28)
ret i32 0
; CHECK: %29 = call ptr @__libc_malloc(i64 noundef 8)
%29 = call ptr @__hipstdpar_hidden_malloc(i64 noundef 8)
; CHECK: call void @__libc_free(ptr noundef %29)
call void @__hipstdpar_hidden_free(ptr noundef %29)
; CHECK: %30 = call ptr @__libc_memalign(i64 noundef 8, i64 noundef 4)
%30 = call ptr @__hipstdpar_hidden_memalign(i64 noundef 8, i64 noundef 4)
; CHECK: %31 = call ptr @mmap(ptr %30, i64 8, i32 0, i32 0, i32 0, i64 0)
%31 = call ptr @__hipstdpar_hidden_mmap(ptr %30, i64 8, i32 0, i32 0, i32 0, i64 0)
; CHECK: %32 = call i32 @munmap(ptr %31, i64 8)
%32 = call i32 @__hipstdpar_hidden_munmap(ptr %31, i64 8)
; CHECK: call void @__libc_free(ptr noundef %30)
call void @__hipstdpar_hidden_free(ptr noundef %30)
ret i32 %32
}
declare noalias ptr @aligned_alloc(i64 noundef, i64 noundef)
@@ -220,4 +244,8 @@ declare void @__libc_free(ptr noundef)
declare ptr @__libc_malloc(i64 noundef)
declare ptr @__libc_memalign(i64 noundef, i64 noundef)
declare ptr @__libc_memalign(i64 noundef, i64 noundef)
declare ptr @mmap(ptr noundef, i64 noundef, i32 noundef, i32 noundef, i32 noundef, i64 noundef)
declare i32 @munmap(ptr noundef, i64 noundef)