llvm-project/clang/test/CodeGenCUDA
Yaxun (Sam) Liu 8428c75da1 [CUDA][HIP] Do not treat host var address as constant in device compilation
Currently clang treats host var address as constant in device compilation,
which causes const vars initialized with host var address promoted to
device variables incorrectly and results in undefined symbols.

This patch fixes that.

Reviewed by: Artem Belevich

Differential Revision: https://reviews.llvm.org/D118153

Fixes: SWDEV-309881

Change-Id: I0a69357063c6f8539ef259c96c250d04615f4473
2022-01-28 16:04:52 -05:00
..
Inputs [HIP] Fix linking of asanrt.bc 2021-09-27 13:25:46 -04:00
address-spaces.cu [Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default 2022-01-16 18:54:17 +09:00
alias.cu
amdgpu-alias-undef-symbols.cu [HIP] [AlwaysInliner] Disable AlwaysInliner to eliminate undefined symbols 2021-10-18 16:53:15 -06:00
amdgpu-asan-printf.cu Prevent adding module flag amdgpu_hostcall multiple times 2022-01-19 12:52:33 -05:00
amdgpu-asan.cu Emit hidden hostcall argument for sanitized kernels 2021-11-10 17:05:57 -05:00
amdgpu-atomic-ops.cu Let clang atomic builtins fetch add/sub support floating point types 2021-04-06 15:44:00 -04:00
amdgpu-func-attrs.cu [test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences 2020-12-31 00:27:11 -08:00
amdgpu-kernel-arg-pointer-type.cu [Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default 2022-01-16 18:54:17 +09:00
amdgpu-kernel-attrs.cu Relands "[HIP] Change default --gpu-max-threads-per-block value to 1024" 2021-02-12 10:53:59 -05:00
amdgpu-visibility.cu [test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences 2020-12-31 00:27:11 -08:00
amdgpu-workgroup-size.cu
atomic-ops.cu [HIP] Add atomic load, atomic store and atomic cmpxchng_weak builtin support in HIP-clang 2021-11-29 12:07:13 -07:00
atomics-remarks-gfx90a.cu [Remarks] Emit optimization remarks for atomics generating CAS loop 2021-08-16 14:56:01 -06:00
builtin-mangled-name.cu [CUDA][HIP] add __builtin_get_device_side_mangled_name 2021-03-25 15:25:29 -04:00
builtins-amdgcn.cu [Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default 2022-01-16 18:54:17 +09:00
builtins-unsafe-atomics-gfx90a.cu [HIP] Relax conditions for address space cast in builtin args 2021-10-15 15:35:52 -06:00
const-var.cu [CUDA][HIP] Do not treat host var address as constant in device compilation 2022-01-28 16:04:52 -05:00
constexpr-variables.cu [CUDA][HIP] Support accessing static device variable in host code for -fno-gpu-rdc 2020-08-05 07:57:38 -04:00
convergent.cu [Clang] [NFC] fix CHECK lines for convergent attribute tests 2021-06-29 00:21:07 +05:30
correctly-rounded-div.cu [HIP] Fix device lib selection 2021-05-01 20:31:11 -04:00
cuda-builtin-vars.cu [Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default 2022-01-16 18:54:17 +09:00
cxx-call-kernel.cpp Fix test cxx-call-kernel.cpp 2021-03-01 17:10:53 -05:00
debug-info-address-class.cu
debug-info-template.cu
deferred-diag.cu
dependent-libs.cu
device-fun-linkage.cu [test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences 2020-12-31 00:27:11 -08:00
device-init-fun.cu
device-stub.cu [HIP] Fix -fgpu-rdc for Windows 2021-12-06 16:42:23 -05:00
device-use-host-var.cu CUDA/HIP: Change device-use-host-var.cu's NOT "external" check to include variable name 2021-06-04 13:10:00 -04:00
device-var-init.cu [test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences 2020-12-31 00:27:11 -08:00
device-var-linkage.cu [CUDA] Fix static device variables with -fgpu-rdc 2021-08-25 09:31:22 +02:00
device-vtable.cu [test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences 2020-12-31 00:27:11 -08:00
dft-func-attr-skip-intrinsic.hip [Clang] [NFC] fix CHECK lines for convergent attribute tests 2021-06-29 00:21:07 +05:30
filter-decl.cu
flush-denormals.cu [CUDA][HIP] rename -fcuda-flush-denormals-to-zero 2021-04-05 00:13:51 -04:00
fp-contract.cu [HIP] Fix regressions due to fp contract change 2020-11-24 08:10:06 -05:00
function-overload.cu [test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences 2020-12-31 00:27:11 -08:00
host-used-device-var.cu [Internalize] Preserve variables externally initialized. 2021-07-08 10:48:19 -04:00
kernel-amdgcn.cu Relands "[HIP] Change default --gpu-max-threads-per-block value to 1024" 2021-02-12 10:53:59 -05:00
kernel-args-alignment.cu [Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default 2022-01-16 18:54:17 +09:00
kernel-args.cu [Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default 2022-01-16 18:54:17 +09:00
kernel-call.cu
kernel-dbg-info.cu [HIP] Emit kernel symbol 2021-03-01 16:31:40 -05:00
kernel-stub-name.cu [Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default 2022-01-16 18:54:17 +09:00
lambda-reference-var.cu [test] Make ELF tests immune to dso_local/dso_preemptable/(none) differences 2020-12-31 13:59:44 -08:00
lambda.cu [Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default 2022-01-16 18:54:17 +09:00
launch-bounds.cu
library-builtin.cu [test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences 2020-12-31 00:27:11 -08:00
link-device-bitcode.cu [test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences 2020-12-31 00:27:11 -08:00
llvm-used.cu Change some addUsedGlobal to addUsedOrCompilerUsedGlobal 2021-02-26 10:42:07 -08:00
managed-var.cu [CUDA] Fix static device variables with -fgpu-rdc 2021-08-25 09:31:22 +02:00
ms-linker-options.cu Revert "[hip][cuda] Enable extended lambda support on Windows." 2021-02-04 07:10:46 -05:00
norecurse.cu
nothrow.cu [test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences 2020-12-31 00:27:11 -08:00
openmp-target.cu
printf-aggregate.cu
printf.cu
profile-coverage-mapping.cu [PGO][CUDA][HIP] Skip generating profile on the device stub and wrong-side functions. 2020-08-10 11:01:46 -04:00
propagate-metadata.cu [clang][cli] Remove -f[no-]trapping-math from -cc1 command line 2021-01-12 10:00:23 +01:00
ptx-kernels.cu [test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences 2020-12-31 00:27:11 -08:00
redux-builtins.cu [Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default 2022-01-16 18:54:17 +09:00
static-device-var-no-rdc.cu [CUDA][HIP] Fix device template variables 2021-05-12 11:13:29 -04:00
static-device-var-rdc.cu [CUDA] Fix static device variables with -fgpu-rdc 2021-08-25 09:31:22 +02:00
surface.cu [Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default 2022-01-16 18:54:17 +09:00
texture.cu [Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default 2022-01-16 18:54:17 +09:00
types.cu [test] Add {{.*}} to make ELF tests immune to dso_local/dso_preemptable/(none) differences 2020-12-31 00:27:11 -08:00
unnamed-types.cu [Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default 2022-01-16 18:54:17 +09:00
unused-global-var.cu [Internalize] Preserve variables externally initialized. 2021-07-08 10:48:19 -04:00
usual-deallocators.cu [Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default 2022-01-16 18:54:17 +09:00
vtbl.cu [IRGen] Do not overwrite existing attributes in CGCall. 2022-01-20 13:45:19 +00:00