llvm

llvm copied to clipboard

This commit changes the CMake for the IPC unittests to check for C++20 support before enabling the tests.

steffenlarsen

[SYCL][NFC] Remove redundant __imf_fsigm* declarations

1

We have declared __imf_fsigm* in https://github.com/intel/llvm/pull/20873/files#diff-8da594ced8852cd2e62e9d1fcd013ca0b2256b88b3745b30a239bb01aa7b2011R251 So, the declarations at the begining is redundant, just remove them.

jinge90

[CUDA] update default CUDA sm ver to 75

2

This pull request updates the default NVIDIA GPU architecture used for CUDA from `SM_50` to `SM_75`, as the newest CUDA 13 no longer supports `SM_50`. It also updates several tests:...

bratpiorka

AlexeySachkov

[SYCL] Implement free function kernel enqueue functions

1

Implement the new enqueue functions for free function kernels that were added in #19995

lbushi25

[NewOffloadModel] Pass link-time options through device-compiler and device-linker argument for ClangLinkerWrapper

1

In another patch https://github.com/intel/llvm/pull/19579, compilation and linking options used in ClangLinkerWrapper are changed to be consumed from the `SYCLImage`, instead of `sycl_backend_compile_options_EQ` and `sycl_target_link_options_EQ` that are passed as argument to...

YixingZhang007

[Driver][SYCL] Compile source file for integration header generation

5

When compiler for preprocessing only, the preprocessing step that occurs does not generate the integration header/footer information that is used during the host compilation step. To generate the integration information...

mdtoguchi

[SYCL] Implement structs that contains special types as parameters to free function kernels

2

Add support for structs containing special types as free function kernel parameters.

lbushi25

The fix allows to use of _v1 and _v2 to select the l0 adapter and the use of arch to select the GPU, eg.: `llvm-lit --param "sycl_devices=level_zero_v2:arch-intel_gpu_mtl_u"` Necessary to run...

mateuszpn

AlexeySachkov