Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[CUDA] Update cached kernel handle when the function instance changes.
Fixes clang crash caused by a stale function pointer. The bug has been present for a pretty long time, but we were lucky not to trigger it until D140663. Differential Revision: https://reviews.llvm.org/D146448
- Loading branch information
Showing
2 changed files
with
55 additions
and
2 deletions.
There are no files selected for viewing
This file contains 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
This file contains 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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,38 @@ | ||
// RUN: echo -n "GPU binary would be here." > %t | ||
// RUN: %clang_cc1 -triple x86_64-linux-gnu -emit-llvm %s \ | ||
// RUN: -target-sdk-version=11.0 -fcuda-include-gpubinary %t -o - \ | ||
// RUN: | FileCheck %s --check-prefixes CUDA | ||
// RUN: %clang_cc1 -triple x86_64-linux-gnu -emit-llvm %s -x hip \ | ||
// RUN: -fcuda-include-gpubinary %t -o - \ | ||
// RUN: | FileCheck %s --check-prefixes HIP | ||
|
||
#include "Inputs/cuda.h" | ||
|
||
template <typename T> | ||
struct S { T t; }; | ||
|
||
template <typename T> | ||
static __global__ void Kernel(S<T>) {} | ||
|
||
// For some reason it takes three or more instantiations of Kernel to trigger a | ||
// crash during CUDA compilation. | ||
auto x = &Kernel<double>; | ||
auto y = &Kernel<float>; | ||
auto z = &Kernel<int>; | ||
|
||
// This triggers HIP-specific code path. | ||
void func (){ | ||
Kernel<short><<<1,1>>>({1}); | ||
} | ||
|
||
// CUDA-LABEL: @__cuda_register_globals( | ||
// CUDA: call i32 @__cudaRegisterFunction(ptr %0, ptr @_ZL21__device_stub__KernelIdEv1SIT_E | ||
// CUDA: call i32 @__cudaRegisterFunction(ptr %0, ptr @_ZL21__device_stub__KernelIfEv1SIT_E | ||
// CUDA: call i32 @__cudaRegisterFunction(ptr %0, ptr @_ZL21__device_stub__KernelIiEv1SIT_E | ||
// CUDA: ret void | ||
|
||
// HIP-LABEL: @__hip_register_globals( | ||
// HIP: call i32 @__hipRegisterFunction(ptr %0, ptr @_ZL6KernelIdEv1SIT_E | ||
// HIP: call i32 @__hipRegisterFunction(ptr %0, ptr @_ZL6KernelIfEv1SIT_E | ||
// HIP: call i32 @__hipRegisterFunction(ptr %0, ptr @_ZL6KernelIiEv1SIT_E | ||
// HIP: ret void |