Skip to content

Switch to SPIRV APIs from internal built-in APIs #255

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 6 commits into
base: sycl-develop
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions cmake/FindDPCPP.cmake
Original file line number Diff line number Diff line change
Expand Up @@ -62,8 +62,11 @@ endif()
if("${DPCPP_SYCL_TARGET}" STREQUAL "intel_gpu_pvc" OR
"${DPCPP_SYCL_TARGET}" STREQUAL "spir64" OR
"${DPCPP_SYCL_TARGET}" STREQUAL "intel_gpu_bmg_g21")
list(APPEND DPCPP_FLAGS "-Xspirv-translator;-spirv-ext=+SPV_INTEL_split_barrier")

if (CMAKE_CXX_COMPILER_ID MATCHES "IntelLLVM" AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS 2025.2)
list(APPEND DPCPP_FLAGS "-Xspirv-translator;-spirv-ext=+SPV_INTEL_split_barrier")
else()
list(APPEND DPCPP_FLAGS "-Xspirv-translator;-spirv-ext=+SPV_INTEL_split_barrier,+SPV_INTEL_2d_block_io,+SPV_INTEL_subgroup_matrix_multiply_accumulate")
endif()
if(DPCPP_DISABLE_ITT_FOR_CUTLASS)
list(APPEND DPCPP_FLAGS "-fno-sycl-instrument-device-code")
endif()
Expand Down
7 changes: 1 addition & 6 deletions include/cute/arch/copy_xe.hpp
Original file line number Diff line number Diff line change
Expand Up @@ -33,11 +33,6 @@
#include <cute/arch/xe_copy_2B.hpp>
#include <cute/arch/xe_copy_4B.hpp>
#include <cute/arch/xe_copy_8B.hpp>
#ifdef __SYCL_DEVICE_ONLY__
#define SYCL_DEVICE_BUILTIN(x) SYCL_EXTERNAL extern "C" x
#else
#define SYCL_DEVICE_BUILTIN(x) inline x { assert(false); }
#endif

// prefetch
SYCL_DEVICE_BUILTIN(void __builtin_IB_lsc_prefetch_global_uchar(
Expand Down Expand Up @@ -70,7 +65,7 @@ SYCL_DEVICE_BUILTIN(void __builtin_IB_lsc_prefetch_global_ulong4(
SYCL_DEVICE_BUILTIN(void __builtin_IB_lsc_prefetch_global_ulong8(
const __attribute__((opencl_global)) uint64_t *base, int immElemOff,
enum CacheControl cacheOpt));
#undef SYCL_DEVICE_BUILTIN


#ifdef __SYCL_DEVICE_ONLY__
SYCL_EXTERNAL __attribute__((convergent)) void __spirv_ControlBarrierWaitINTEL(int execution_scope, int memory_scope, int memory_semantics);
Expand Down
Loading