Initial cmake support of SYCL for AMD GPUs (llama/9658)

ggml/src/CMakeLists.txt

@@ -511,8 +511,8 @@ if (GGML_HIPBLAS)
 endif()
 
 if (GGML_SYCL)
-    if (NOT GGML_SYCL_TARGET MATCHES "^(INTEL|NVIDIA)$")
-        message(FATAL_ERROR "Invalid backend chosen, supported options are INTEL or NVIDIA")
+    if (NOT GGML_SYCL_TARGET MATCHES "^(INTEL|NVIDIA|AMD)$")
+        message(FATAL_ERROR "Invalid backend chosen, supported options are INTEL, NVIDIA, or AMD")
     endif()
 
     check_cxx_compiler_flag("-fsycl" SUPPORTS_SYCL)
@@ -532,6 +532,9 @@ if (GGML_SYCL)
     list(APPEND GGML_CDEF_PUBLIC GGML_USE_SYCL)
 
     if (GGML_SYCL_F16)
+        if (GGML_SYCL_TARGET STREQUAL "AMD")
+            message(WARNING "AMD target does not entirely support FP16 in the SYCL backend.")
+        endif()
         add_compile_definitions(GGML_SYCL_F16)
     endif()
 
@@ -543,6 +546,12 @@ if (GGML_SYCL)
 
     if (GGML_SYCL_TARGET STREQUAL "NVIDIA")
         add_compile_definitions(GGML_SYCL_WARP_SIZE=32)
+    elseif (GGML_SYCL_TARGET STREQUAL "AMD")
+        # INFO: Allowed Sub_group_sizes are not consistent through all
+        # hip targets. For example, 64 is used for certain models, but the backend
+        # does not support it.
+        # Target archs tested working: gfx1030, gfx1031, (Only tested sub_group_size = 32)
+        add_compile_definitions(GGML_SYCL_WARP_SIZE=32)
     else()
         add_compile_definitions(GGML_SYCL_WARP_SIZE=16)
     endif()
@@ -576,6 +585,12 @@ if (GGML_SYCL)
         elseif (GGML_SYCL_TARGET STREQUAL "NVIDIA")
             set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsycl-targets=nvptx64-nvidia-cuda")
             list(APPEND GGML_EXTRA_LIBS_PRIVATE sycl pthread m dl onemkl)
+        elseif (GGML_SYCL_TARGET STREQUAL "AMD")
+            if (GGML_SYCL_HIP_TARGET STREQUAL "")
+                message(ERROR "Can't enable SYCL hip backend, GGML_SYCL_HIP_TARGET has not been set.")
+            endif()
+            set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsycl-targets=amdgcn-amd-amdhsa -Xsycl-target-backend --offload-arch=${GGML_SYCL_HIP_TARGET}")
+            list(APPEND GGML_EXTRA_LIBS_PRIVATE sycl pthread m dl onemkl)
         endif()
     endif()
 endif()