-
Notifications
You must be signed in to change notification settings - Fork 14.5k
[CUDA][HIP] capture possible ODR-used var #136645
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
Merged
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
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
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
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
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
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,135 @@ | ||
// RUN: %clang_cc1 -emit-llvm -x hip %s -o - -triple x86_64-linux-gnu \ | ||
// RUN: | FileCheck -check-prefixes=CHECK,HOST %s | ||
// RUN: %clang_cc1 -emit-llvm -x hip %s -o - -triple amdgcn-amd-amdhsa -fcuda-is-device \ | ||
// RUN: | FileCheck -check-prefixes=CHECK,DEV %s | ||
|
||
#include "Inputs/cuda.h" | ||
|
||
// CHECK: %class.anon = type { ptr, float, ptr, ptr } | ||
// CHECK: %class.anon.0 = type { ptr, float, ptr, ptr } | ||
// CHECK: %class.anon.1 = type { ptr, ptr, ptr } | ||
// CHECK: %class.anon.2 = type { ptr, float, ptr, ptr } | ||
|
||
// HOST: call void @_ZN8DevByVal21__device_stub__kernelIZNS_4testEPKfS2_PfEUljE_EEvT_(ptr noundef byval(%class.anon) | ||
// DEV: define amdgpu_kernel void @_ZN8DevByVal6kernelIZNS_4testEPKfS2_PfEUljE_EEvT_(ptr addrspace(4) noundef byref(%class.anon) | ||
|
||
// Only the device function passes arugments by value. | ||
namespace DevByVal { | ||
__device__ float fun(float x, float y) { | ||
return x; | ||
} | ||
|
||
float fun(const float &x, const float &y) { | ||
return x; | ||
} | ||
|
||
template<typename F> | ||
void __global__ kernel(F f) | ||
{ | ||
f(1); | ||
} | ||
|
||
void test(float const * fl, float const * A, float * Vf) | ||
{ | ||
float constexpr small(1.0e-25); | ||
|
||
auto lambda = [=] __device__ __host__ (unsigned int n) { | ||
float const value = fun(small, fl[0]); | ||
Vf[0] = value * A[0]; | ||
}; | ||
kernel<<<1, 1>>>(lambda); | ||
} | ||
} | ||
|
||
// HOST: call void @_ZN9HostByVal21__device_stub__kernelIZNS_4testEPKfS2_PfEUljE_EEvT_(ptr noundef byval(%class.anon.0) | ||
// DEV: define amdgpu_kernel void @_ZN9HostByVal6kernelIZNS_4testEPKfS2_PfEUljE_EEvT_(ptr addrspace(4) noundef byref(%class.anon.0) | ||
|
||
// Only the host function passes arugments by value. | ||
namespace HostByVal { | ||
float fun(float x, float y) { | ||
return x; | ||
} | ||
|
||
__device__ float fun(const float &x, const float &y) { | ||
return x; | ||
} | ||
|
||
template<typename F> | ||
void __global__ kernel(F f) | ||
{ | ||
f(1); | ||
} | ||
|
||
void test(float const * fl, float const * A, float * Vf) | ||
{ | ||
float constexpr small(1.0e-25); | ||
|
||
auto lambda = [=] __device__ __host__ (unsigned int n) { | ||
float const value = fun(small, fl[0]); | ||
Vf[0] = value * A[0]; | ||
}; | ||
kernel<<<1, 1>>>(lambda); | ||
} | ||
} | ||
|
||
// HOST: call void @_ZN9BothByVal21__device_stub__kernelIZNS_4testEPKfS2_PfEUljE_EEvT_(ptr noundef byval(%class.anon.1) | ||
// DEV: define amdgpu_kernel void @_ZN9BothByVal6kernelIZNS_4testEPKfS2_PfEUljE_EEvT_(ptr addrspace(4) noundef byref(%class.anon.1) | ||
|
||
// Both the host and device functions pass arugments by value. | ||
namespace BothByVal { | ||
float fun(float x, float y) { | ||
return x; | ||
} | ||
|
||
__device__ float fun(float x, float y) { | ||
return x; | ||
} | ||
|
||
template<typename F> | ||
void __global__ kernel(F f) | ||
{ | ||
f(1); | ||
} | ||
|
||
void test(float const * fl, float const * A, float * Vf) | ||
{ | ||
float constexpr small(1.0e-25); | ||
|
||
auto lambda = [=] __device__ __host__ (unsigned int n) { | ||
float const value = fun(small, fl[0]); | ||
Vf[0] = value * A[0]; | ||
}; | ||
kernel<<<1, 1>>>(lambda); | ||
} | ||
} | ||
|
||
// HOST: call void @_ZN12NeitherByVal21__device_stub__kernelIZNS_4testEPKfS2_PfEUljE_EEvT_(ptr noundef byval(%class.anon.2) | ||
// DEV: define amdgpu_kernel void @_ZN12NeitherByVal6kernelIZNS_4testEPKfS2_PfEUljE_EEvT_(ptr addrspace(4) noundef byref(%class.anon.2) | ||
|
||
// Neither the host nor device function passes arugments by value. | ||
namespace NeitherByVal { | ||
float fun(const float& x, const float& y) { | ||
return x; | ||
} | ||
|
||
__device__ float fun(const float& x, const float& y) { | ||
return x; | ||
} | ||
|
||
template<typename F> | ||
void __global__ kernel(F f) | ||
{ | ||
f(1); | ||
} | ||
|
||
void test(float const * fl, float const * A, float * Vf) | ||
{ | ||
float constexpr small(1.0e-25); | ||
|
||
auto lambda = [=] __device__ __host__ (unsigned int n) { | ||
float const value = fun(small, fl[0]); | ||
Vf[0] = value * A[0]; | ||
}; | ||
kernel<<<1, 1>>>(lambda); | ||
} | ||
} |
Oops, something went wrong.
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.
Uh oh!
There was an error while loading. Please reload this page.