HIP: force max threads per block to be 1024 (#11621)

Some old/vendor forked version of llvm still use 256. Explicitly set it to 1024 to align with upstream llvm.

Signed-off-by: fxzjshm <redacted>

diff --git a/ggml/src/ggml-hip/CMakeLists.txt b/ggml/src/ggml-hip/CMakeLists.txt
index eb03e10fa48a1b39ef444571a22c078f3213583e..f4a4683639fab51897b66beca7bb155d4da5ac53 100644 (file)
--- a/ggml/src/ggml-hip/CMakeLists.txt
+++ b/ggml/src/ggml-hip/CMakeLists.txt
@@ -46,6 +46,9 @@ endif()
 
 message(STATUS "HIP and hipBLAS found")
 
+# Workaround old compilers
+set(CMAKE_HIP_FLAGS "${CMAKE_HIP_FLAGS} --gpu-max-threads-per-block=1024")
+
 file(GLOB   GGML_HEADERS_ROCM "../ggml-cuda/*.cuh")
 list(APPEND GGML_HEADERS_ROCM "../../include/ggml-cuda.h")