llvm-project/clang/test/CodeGenCUDA
Yaxun (Sam) Liu 22c457a869 [HIP] Fix device stub name
HIP emits a device stub function for each kernel in host code.

The HIP debugger requires device stub function to have a different unmangled name as the kernel.

Currently the name of the device stub function is the mangled name with a postfix .stub. However,
this does not work with the HIP debugger since the unmangled name is the same as the kernel.

This patch adds prefix __device__stub__ to the unmangled name of the device stub before mangling,
therefore the device stub function has a valid mangled name which is different than the device kernel
name. The device side kernel name is kept unchanged. kernels with extern "C" also gets the prefix added
to the corresponding device stub function.

Differential Revision: https://reviews.llvm.org/D68578
2020-03-09 16:40:05 -04:00
..
Inputs [HIP] Support new kernel launching API 2019-09-24 19:16:40 +00:00
address-spaces.cu
alias.cu
amdgpu-hip-implicit-kernarg.cu [AMDGPU] Increased the number of implicit argument bytes for both OpenCL and HIP (CLANG). 2019-07-10 15:10:08 +00:00
amdgpu-kernel-arg-pointer-type.cu [HIP] Fix device stub name 2020-03-09 16:40:05 -04:00
amdgpu-kernel-attrs.cu [HIP] Add option --gpu-max-threads-per-block=n 2020-01-07 11:18:00 -05:00
amdgpu-visibility.cu [HIP] Fix visibility for 'extern' device variables. 2019-11-05 14:19:32 -05:00
builtins-amdgcn.cu Make __builtin_amdgcn_dispatch_ptr dereferenceable and align at 4 2020-02-25 13:58:20 -05:00
convergent.cu [FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests 2018-07-11 20:26:20 +00:00
cuda-builtin-vars.cu
debug-info-address-class.cu [DEBUG_INFO][NVPTX] Generate correct data about variable address class. 2019-02-05 19:45:57 +00:00
debug-info-template.cu [CUDA][HIP][DebugInfo] Skip reference device function 2019-03-06 21:16:27 +00:00
dependent-libs.cu Fix failure of lit test dependent-libs.cu 2019-05-29 01:34:44 +00:00
device-init-fun.cu [HIP] Add option -fgpu-allow-device-init 2019-10-22 16:06:20 -04:00
device-stub.cu [HIP-Clang] Fat binary should not be produced for non GPU code 2 2019-04-02 20:49:41 +00:00
device-var-init.cu [CUDA][HIP] Skip setting `externally_initialized` for static device variables. 2019-05-29 17:23:27 +00:00
device-vtable.cu [CUDA][HIP] Do not emit type info when compiling for device 2018-06-05 15:11:02 +00:00
filter-decl.cu
flush-denormals.cu Assume ieee behavior without denormal-fp-math attribute 2020-03-07 12:10:56 -05:00
fp-contract.cu
function-overload.cu
hip-pinned-shadow.cu [HIP] Make sure, unused hip-pinned-shadow global var is kept within device code 2020-03-04 10:54:26 +05:30
kernel-amdgcn.cu [AMDGPU] Set default flat work group size to (1,256) for HIP 2019-09-03 18:50:24 +00:00
kernel-args-alignment.cu LLVM IR: Generate new-style byval-with-Type from Clang 2019-06-05 21:12:14 +00:00
kernel-args.cu LLVM IR: Generate new-style byval-with-Type from Clang 2019-06-05 21:12:14 +00:00
kernel-call.cu [HIP] Support new kernel launching API 2019-09-24 19:16:40 +00:00
kernel-stub-name.cu [HIP] Fix device stub name 2020-03-09 16:40:05 -04:00
launch-bounds.cu
library-builtin.cu
link-device-bitcode.cu Rename -mlink-cuda-bitcode to -mlink-builtin-bitcode 2018-08-20 18:16:48 +00:00
llvm-used.cu
ms-linker-options.cu [CUDA][HIP] Disable emitting llvm.linker.options in device compilation 2019-11-04 23:21:39 -05:00
norecurse.cu [OpenCL][CUDA][HIP][SYCL] Add norecurse 2020-02-16 20:41:00 -05:00
nothrow.cu
openmp-target.cu [CUDA][HIP] Fix host/device check with -fopenmp 2019-10-09 23:54:10 +00:00
printf-aggregate.cu
printf.cu
propagate-metadata.cu Assume ieee behavior without denormal-fp-math attribute 2020-03-07 12:10:56 -05:00
ptx-kernels.cu
types.cu Do not copy long double and 128-bit fp format from aux target for AMDGPU 2019-01-31 21:57:51 +00:00
unnamed-types.cu [HIP] Fix device stub name 2020-03-09 16:40:05 -04:00
usual-deallocators.cu IR: print value numbers for unnamed function arguments 2019-08-03 14:28:34 +00:00