Joseph Huber e3d2a7d0a5 [libc] Compile the GPU functions with '-fconvergent-functions' (#70229) ...

Summary:
This patch simply adds the `-fconvergent-functions` flag to the GPU
compilation. This is in relation to the behaviour of SIMT
architectures under divergence. With the flag, we assume every function
is convergent by default and rely on the compiler's divergence analysis
to transform it if possible.

Fixes: https://github.com/llvm/llvm-project/issues/63853

2023-10-25 14:13:21 -05:00

..

cpu_features

[libc] Add AVX detectionwq

2023-04-18 13:11:33 +00:00

LibcConfig.cmake

[libc] Generate configure.rst from the JSON config information. (#65791)

2023-09-08 13:11:09 -07:00

LLVMLibCArchitectures.cmake

[libc] Start to refactor riscv platform abstraction to support both 32 and 64 bits versions

2023-09-26 12:32:25 -03:00

LLVMLibCCheckCpuFeatures.cmake

[libc] Enable missing memory tests on the GPU (#68111)

2023-10-06 08:27:36 -05:00

LLVMLibCCheckMPFR.cmake

[libc] Don't try to use MPFR with the GPU build for now

2023-02-08 08:51:47 -06:00

LLVMLibCFlagRules.cmake

[libc][RISCV] Let RISCV64 targets test implementations with and without FMA.

2023-04-06 09:23:48 -04:00

LLVMLibCHeaderRules.cmake

[libc] Propagate printf config options from a single config header library. (#66979)

2023-09-26 08:16:31 -07:00

LLVMLibCLibraryRules.cmake

[libc] Propagate printf config options from a single config header library. (#66979)

2023-09-26 08:16:31 -07:00

LLVMLibCObjectRules.cmake

[libc] Compile the GPU functions with '-fconvergent-functions' (#70229)

2023-10-25 14:13:21 -05:00

LLVMLibCRules.cmake

…

LLVMLibCTargetNameUtils.cmake

…

LLVMLibCTestRules.cmake

[libc][Obvious] Do not pass 'nolibc' and other flags to the GPU build

2023-09-29 12:57:02 -05:00

prepare_libc_gpu_build.cmake

[libc] Manually set the AMDGPU code object version (#65986)

2023-09-11 13:07:56 -05:00