llvm-project/clang/test/CodeGenCUDA
Matt Arsenault a3c814d234 Separately track input and output denormal mode
AMDGPU and x86 at least both have separate controls for whether
denormal results are flushed on output, and for whether denormals are
implicitly treated as 0 as an input. The current DAGCombiner use only
really cares about the input treatment of denormals.
2020-02-04 12:59:21 -05:00
..
Inputs [HIP] Support new kernel launching API 2019-09-24 19:16:40 +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] 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] Enable pointer argument lowering through coercing type. 2019-11-05 13:05:05 -05:00
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 [clang] Preserve names of addrspacecast'ed values. 2019-07-10 17:10:05 +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-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 Really fix test on windows. 2018-02-23 19:38:41 +00:00
flush-denormals.cu Separately track input and output denormal mode 2020-02-04 12:59:21 -05:00
fp-contract.cu
function-overload.cu
hip-pinned-shadow.cu [HIP] Support attribute hip_pinned_shadow 2019-06-26 03:47:37 +00:00
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] change kernel stub name 2019-02-27 02:02:52 +00:00
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
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 Separately track input and output denormal mode 2020-02-04 12:59:21 -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][cuda] Fix the extended lambda name mangling issue. 2019-10-19 00:15:19 +00:00
usual-deallocators.cu IR: print value numbers for unnamed function arguments 2019-08-03 14:28:34 +00:00