OpenCL Token Generation Acceleration (#1459)

* Move back to C++ for OpenCL

* Refactor OpenCL code to work more like the CUDA code, add missing functions

* Deduplicate dequant kernels

* Add OpenCL compile options

* Use compile args for preprocessing constants

* Restore default platform + device selection by id behavior

---------

Co-authored-by: Johannes Gäßler <[email protected]>
Co-authored-by: Henri Vasserman <[email protected]>

Author: 3 people

CMakeLists.txt

@@ -201,7 +201,7 @@ if (LLAMA_CLBLAST)
     if (CLBlast_FOUND)
         message(STATUS "CLBlast found")
 
-        set(GGML_OPENCL_SOURCES ggml-opencl.c ggml-opencl.h)
+        set(GGML_OPENCL_SOURCES ggml-opencl.cpp ggml-opencl.h)
 
         add_compile_definitions(GGML_USE_CLBLAST)
 

Makefile

@@ -138,15 +138,16 @@ ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
 endif
 ifdef LLAMA_CLBLAST
 	CFLAGS  += -DGGML_USE_CLBLAST
+	CXXFLAGS  += -DGGML_USE_CLBLAST
 	# Mac provides OpenCL as a framework
 	ifeq ($(UNAME_S),Darwin)
 		LDFLAGS += -lclblast -framework OpenCL
 	else
 		LDFLAGS += -lclblast -lOpenCL
 	endif
 	OBJS    += ggml-opencl.o
-ggml-opencl.o: ggml-opencl.c ggml-opencl.h
-	$(CC) $(CFLAGS) -c $< -o $@
+ggml-opencl.o: ggml-opencl.cpp ggml-opencl.h
+	$(CXX) $(CXXFLAGS) -c $< -o $@
 endif
 ifneq ($(filter aarch64%,$(UNAME_M)),)
 	# Apple M1, M2, etc.