4d2c7ad003
Includes patch suggested by @shuni64 which fixes half precision ABI issues Includes hipblaslt compression patch Includes configurable hipblaslt support in rocblas rocmPackages_6.hipblaslt: respect NIX_BUILD_CORES in tensilelite rocmPackages_6.hipblas: propagate hipblas-common rocmPackages_6.clr: avoid confusion with hipClangPath Co-authored-by: Gavin Zhao <git@gzgz.dev>
17 lines
831 B
Diff
17 lines
831 B
Diff
Flag -amdgpu-early-inline-all explodes memory consumption, so that build does not fit 64GB of RAM.
|
|
LLVM bug: https://github.com/llvm/llvm-project/issues/86332
|
|
--- a/CMakeLists.txt
|
|
+++ b/CMakeLists.txt
|
|
@@ -213,11 +213,6 @@ if(NOT WIN32 AND check-coerce AND ${hip_VERSION_FLAT} GREATER 600241132 AND ${hi
|
|
message("Adding the amdgpu-coerce-illegal-types=1")
|
|
add_compile_options("SHELL: -mllvm -amdgpu-coerce-illegal-types=1")
|
|
endif()
|
|
-if(NOT WIN32 AND ${hip_VERSION_FLAT} GREATER 600241132)
|
|
- message("Adding -amdgpu-early-inline-all=true and -amdgpu-function-calls=false")
|
|
- add_compile_options("SHELL: -mllvm -amdgpu-early-inline-all=true")
|
|
- add_compile_options("SHELL: -mllvm -amdgpu-function-calls=false")
|
|
-endif()
|
|
#
|
|
# Seperate linking jobs from compiling
|
|
# Too many concurrent linking jobs can break the build
|