Support for CPY kernel (ggml-org#14)

* Add HSA backend to GPT-2 example

* Remove CPU backend from HSA

* Returning that it is host buffer for NPU memory

* Adding CPY kernels and factoring out kernel code

* Formatting, comments

* Temporary storage for cpy

* Extracting supports_op conditions

* Renaming function

examples/gpt-2/main-sched.cpp

@@ -15,6 +15,11 @@
 #include "ggml-blas.h"
 #endif
 
+#ifdef GGML_USE_HSA
+#include "ggml-hsa.h"
+#endif
+
+
 #include "common.h"
 #include "common-ggml.h"
 
@@ -145,6 +150,18 @@ void init_backends(gpt2_model & model, const gpt_params & params) {
     }
 #endif
 
+#ifdef GGML_USE_HSA
+    if (params.n_gpu_layers > 0) {
+        fprintf(stderr, "%s: using HSA backend\n", __func__);
+        ggml_backend_t hsa_backend = ggml_backend_hsa_init(0);
+        if (!hsa_backend) {
+            fprintf(stderr, "%s: ggml_backend_hsa_init() failed\n", __func__);
+        } else {
+            model.backends.push_back(hsa_backend);
+        }
+    }
+#endif
+
     // always add the CPU backend as a fallback
     ggml_backend_t cpu_backend = ggml_backend_cpu_init();
     ggml_backend_cpu_set_n_threads(cpu_backend, params.n_threads);

src/ggml-hsa/CMakeLists.txt

@@ -20,7 +20,11 @@ find_package(hsa-runtime64 1.0 REQUIRED)
 message(STATUS "HSA found")
 
 set(GGML_HEADERS_HSA ../../include/ggml-hsa.h)
-set(GGML_SOURCES_HSA ggml-hsa.cpp)
+set(GGML_SOURCES_HSA
+    ggml-hsa.cpp
+    cpy.cpp
+    mul_mat.cpp
+    )
 
 ggml_add_backend_library(ggml-hsa
                          ${GGML_HEADERS_HSA}
@@ -33,7 +37,7 @@ target_include_directories(ggml-hsa PRIVATE . ..)
 find_package(Eigen3 3.3 REQUIRED)
 target_link_libraries(ggml-hsa PRIVATE Eigen3::Eigen)
 
-target_sources(ggml-hsa PRIVATE common.hpp)
+target_sources(ggml-hsa PRIVATE common.hpp kernels.hpp)
 
 set_source_files_properties(${GGML_SOURCES_ROCM} PROPERTIES LANGUAGE CXX)