llvm-project/clang/test/CodeGenCUDA
Yaxun Liu c3dfe9082b [HIP] Support attribute hip_pinned_shadow
This patch introduces support of hip_pinned_shadow variable for HIP.

A hip_pinned_shadow variable is a global variable with attribute hip_pinned_shadow.
It has external linkage on device side and has no initializer. It has internal
linkage on host side and has initializer or static constructor. It can be accessed
in both device code and host code.

This allows HIP runtime to implement support of HIP texture reference.

Differential Revision: https://reviews.llvm.org/D62738

llvm-svn: 364381
2019-06-26 03:47:37 +00:00
..
Inputs [CUDA] add support for the new kernel launch API in CUDA-9.2+. 2019-01-31 21:34:03 +00:00
address-spaces.cu [CUDA] Let device-side shared variables be initialized with undef 2018-04-02 17:38:24 +00:00
alias.cu Disable emitting static extern C aliases for amdgcn target for CUDA 2018-03-29 14:50:00 +00:00
amdgpu-hip-implicit-kernarg.cu [AMDGPU] Enable the implicit arguments for HIP (CLANG) 2019-06-14 15:54:47 +00:00
amdgpu-kernel-attrs.cu [CUDA][HIP] Allow CUDA __global__ functions to have amdgpu kernel attributes 2018-06-12 23:58:59 +00:00
amdgpu-visibility.cu [HIP] Fix visibility of `__constant__` variables. 2019-04-26 19:31:48 +00:00
builtins-amdgcn.cu Try to make builtin address space declarations not useless 2018-08-02 12:14:28 +00:00
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-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 Really fix test on windows. 2018-02-23 19:38:41 +00:00
flush-denormals.cu [HIP] Support -fcuda-flush-denormals-to-zero for amdgcn 2018-07-21 02:02:22 +00:00
fp-contract.cu Use FPContractModeKind universally 2017-03-29 21:54:24 +00:00
function-overload.cu
hip-pinned-shadow.cu [HIP] Support attribute hip_pinned_shadow 2019-06-26 03:47:37 +00:00
kernel-amdgcn.cu [CUDA] Set LLVM calling convention for CUDA kernel 2018-04-20 17:01:03 +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 [CUDA] add support for the new kernel launch API in CUDA-9.2+. 2019-01-31 21:34:03 +00:00
kernel-stub-name.cu [HIP] change kernel stub name 2019-02-27 02:02:52 +00:00
launch-bounds.cu
library-builtin.cu [CUDA] CUDA has no device-side library builtins. 2018-01-23 19:08:18 +00:00
link-device-bitcode.cu Rename -mlink-cuda-bitcode to -mlink-builtin-bitcode 2018-08-20 18:16:48 +00:00
llvm-used.cu
nothrow.cu
printf-aggregate.cu
printf.cu
propagate-metadata.cu Rename -mlink-cuda-bitcode to -mlink-builtin-bitcode 2018-08-20 18:16:48 +00:00
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
usual-deallocators.cu [CUDA] Ignore uncallable functions when we check for usual deallocators. 2018-09-21 17:29:33 +00:00