.. |
Inputs
|
7fd15a3b66
[HIP] Support new kernel launching API
|
5 years ago |
address-spaces.cu
|
b691ac6db3
[CUDA] Let device-side shared variables be initialized with undef
|
7 years ago |
alias.cu
|
8a1c33e1b7
Disable emitting static extern C aliases for amdgcn target for CUDA
|
7 years ago |
amdgpu-hip-implicit-kernarg.cu
|
31644ca03b
[AMDGPU] Increased the number of implicit argument bytes for both OpenCL and HIP (CLANG).
|
6 years ago |
amdgpu-kernel-attrs.cu
|
078d5aacfa
[CUDA][HIP] Allow CUDA __global__ functions to have amdgpu kernel attributes
|
7 years ago |
amdgpu-visibility.cu
|
3bbed5ed96
[HIP] Fix visibility of `__constant__` variables.
|
6 years ago |
builtins-amdgcn.cu
|
0d48a00a81
[clang] Preserve names of addrspacecast'ed values.
|
6 years ago |
convergent.cu
|
9c70ef5a9d
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests
|
7 years ago |
cuda-builtin-vars.cu
|
204eb55522
[CUDA] Rename cuda_builtin_vars.h to __clang_cuda_builtin_vars.h.
|
8 years ago |
debug-info-address-class.cu
|
cac247a1b8
[DEBUG_INFO][NVPTX] Generate correct data about variable address class.
|
6 years ago |
debug-info-template.cu
|
13ddb5b2d0
[CUDA][HIP][DebugInfo] Skip reference device function
|
6 years ago |
dependent-libs.cu
|
5240ba5698
Fix failure of lit test dependent-libs.cu
|
6 years ago |
device-stub.cu
|
b984bff221
[HIP-Clang] Fat binary should not be produced for non GPU code 2
|
6 years ago |
device-var-init.cu
|
ced275ae4a
[CUDA][HIP] Skip setting `externally_initialized` for static device variables.
|
6 years ago |
device-vtable.cu
|
571a2502f2
[CUDA][HIP] Do not emit type info when compiling for device
|
7 years ago |
filter-decl.cu
|
f8a103739e
Really fix test on windows.
|
7 years ago |
flush-denormals.cu
|
e72aad6948
[HIP] Support -fcuda-flush-denormals-to-zero for amdgcn
|
7 years ago |
fp-contract.cu
|
922e16babe
Use FPContractModeKind universally
|
8 years ago |
function-overload.cu
|
534b63721a
[CUDA] Disallow overloading destructors.
|
9 years ago |
hip-pinned-shadow.cu
|
8d068d6ad4
[HIP] Support attribute hip_pinned_shadow
|
6 years ago |
kernel-amdgcn.cu
|
9678410799
[AMDGPU] Set default flat work group size to (1,256) for HIP
|
6 years ago |
kernel-args-alignment.cu
|
5f8238ecfe
LLVM IR: Generate new-style byval-with-Type from Clang
|
6 years ago |
kernel-args.cu
|
5f8238ecfe
LLVM IR: Generate new-style byval-with-Type from Clang
|
6 years ago |
kernel-call.cu
|
7fd15a3b66
[HIP] Support new kernel launching API
|
5 years ago |
kernel-stub-name.cu
|
2e53b8068e
[HIP] change kernel stub name
|
6 years ago |
launch-bounds.cu
|
ed12690047
[CUDA] Improve target attribute checking for function templates.
|
8 years ago |
library-builtin.cu
|
639c532fba
[CUDA] CUDA has no device-side library builtins.
|
7 years ago |
link-device-bitcode.cu
|
fef69ae4fb
Rename -mlink-cuda-bitcode to -mlink-builtin-bitcode
|
7 years ago |
llvm-used.cu
|
f39158f96e
When generating llvm.used, we may need an addrspacecast instead of a bitcast.
|
10 years ago |
nothrow.cu
|
a85c03256c
[CUDA] Add missing ':' to noexcept.cu test.
|
9 years ago |
openmp-target.cu
|
e619d987e2
[CUDA][HIP] Fix host/device check with -fopenmp
|
5 years ago |
printf-aggregate.cu
|
05d90e2b08
[CUDA] Don't crash when trying to printf a non-scalar object.
|
9 years ago |
printf.cu
|
494843ae42
[CUDA] Generate CUDA's printf alloca in its function's entry block.
|
9 years ago |
propagate-metadata.cu
|
fef69ae4fb
Rename -mlink-cuda-bitcode to -mlink-builtin-bitcode
|
7 years ago |
ptx-kernels.cu
|
56a9798df3
[CUDA] Give templated device functions internal linkage, templated kernels external linkage.
|
9 years ago |
types.cu
|
453a2ffd48
Do not copy long double and 128-bit fp format from aux target for AMDGPU
|
6 years ago |
unnamed-types.cu
|
3e0834ac1f
[hip][cuda] Fix the extended lambda name mangling issue.
|
5 years ago |
usual-deallocators.cu
|
635dc81659
IR: print value numbers for unnamed function arguments
|
6 years ago |