maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[OpenCL] Adjust diagnostic for subgroup support. 

OpenCL C 3.0 __opencl_c_subgroups feature is slightly different
then other equivalent features and extensions (fp64 and 3d image writes):
OpenCL C 3.0 device can support the extension but not the feature.
cl_khr_subgroups requires subgroup independent forward progress.

This patch adjusts the check which is used when translating language
builtins to check either the extension or feature is supported.

Reviewed By: Anastasia

Differential Revision: https://reviews.llvm.org/D118999
This commit is contained in:
Anton Zabaznov 2022-02-11 15:54:55 +03:00
parent 8fee667d31
commit bfb1a33bec
2 changed files with 11 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
clang/lib/Sema/SemaChecking.cpp
View File

@ -1042,9 +1042,15 @@ static bool checkOpenCLBlockArgs(Sema &S, Expr *BlockArg) {
}
static bool checkOpenCLSubgroupExt(Sema &S, CallExpr *Call) {
if (!S.getOpenCLOptions().isSupported("cl_khr_subgroups", S.getLangOpts())) {
// OpenCL device can support extension but not the feature as extension
// requires subgroup independent forward progress, but subgroup independent
// forward progress is optional in OpenCL C 3.0 __opencl_c_subgroups feature.
if (!S.getOpenCLOptions().isSupported("cl_khr_subgroups", S.getLangOpts()) &&
!S.getOpenCLOptions().isSupported("__opencl_c_subgroups",
S.getLangOpts())) {
S.Diag(Call->getBeginLoc(), diag::err_opencl_requires_extension)
<< 1 << Call->getDirectCallee() << "cl_khr_subgroups";
<< 1 << Call->getDirectCallee()
<< "cl_khr_subgroups or __opencl_c_subgroups";
return true;
}
return false;

6
clang/test/SemaOpenCL/cl20-device-side-enqueue.cl
View File

@ -4,7 +4,7 @@
// RUN: %clang_cc1 %s -cl-std=CL2.0 -triple "spir64-unknown-unknown" -verify -pedantic -fsyntax-only -Wconversion -DWCONV -DQUALS=
// RUN: %clang_cc1 %s -cl-std=CL2.0 -triple "spir64-unknown-unknown" -verify -pedantic -fsyntax-only -Wconversion -DWCONV -DQUALS="const volatile"
// RUN: %clang_cc1 %s -cl-std=CL3.0 -triple "spir-unknown-unknown" -verify -pedantic -fsyntax-only -DB32 -DQUALS=
// RUN: %clang_cc1 %s -cl-std=CL3.0 -triple "spir-unknown-unknown" -verify -pedantic -fsyntax-only -DB32 -DQUALS= -cl-ext=-cl_khr_subgroups
// RUN: %clang_cc1 %s -cl-std=CL3.0 -triple "spir-unknown-unknown" -verify -pedantic -fsyntax-only -DB32 -DQUALS= -cl-ext=-cl_khr_subgroups,-__opencl_c_subgroups
// RUN: %clang_cc1 %s -cl-std=CL3.0 -triple "spir-unknown-unknown" -verify -pedantic -fsyntax-only -DB32 -DQUALS="const volatile"
// RUN: %clang_cc1 %s -cl-std=CL3.0 -triple "spir64-unknown-unknown" -verify -pedantic -fsyntax-only -Wconversion -DWCONV -DQUALS=
// RUN: %clang_cc1 %s -cl-std=CL3.0 -triple "spir64-unknown-unknown" -verify -pedantic -fsyntax-only -Wconversion -DWCONV -DQUALS="const volatile"
@ -241,12 +241,12 @@ kernel void bar(global unsigned int *buf)
kernel void foo1(global unsigned int *buf)
{
ndrange_t n;
buf[0] = get_kernel_max_sub_group_size_for_ndrange(n, ^(){}); // expected-error {{use of declaration 'get_kernel_max_sub_group_size_for_ndrange' requires cl_khr_subgroups support}}
buf[0] = get_kernel_max_sub_group_size_for_ndrange(n, ^(){}); // expected-error {{use of declaration 'get_kernel_max_sub_group_size_for_ndrange' requires cl_khr_subgroups or __opencl_c_subgroups support}}
}
kernel void bar1(global unsigned int *buf)
{
ndrange_t n;
buf[0] = get_kernel_sub_group_count_for_ndrange(n, ^(){}); // expected-error {{use of declaration 'get_kernel_sub_group_count_for_ndrange' requires cl_khr_subgroups support}}
buf[0] = get_kernel_sub_group_count_for_ndrange(n, ^(){}); // expected-error {{use of declaration 'get_kernel_sub_group_count_for_ndrange' requires cl_khr_subgroups or __opencl_c_subgroups support}}
}
#endif // ifdef cl_khr_subgroups