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 <johannesg@5d6.de>
Co-authored-by: Henri Vasserman <henv@hot.ee>

1 files changed, 8 insertions, 10 deletions

diff --git a/ggml-opencl.h b/ggml-opencl.h
index 7bcc603..5a1a500 100644
--- a/ggml-opencl.h
+++ b/ggml-opencl.h
@@ -1,23 +1,21 @@
 #pragma once
 
+#include "ggml.h"
+
 #ifdef  __cplusplus
 extern "C" {
 #endif
 
 void ggml_cl_init(void);
 
-enum ggml_blas_order {
-    GGML_BLAS_ORDER_ROW_MAJOR = 101,
-    GGML_BLAS_ORDER_COLUMN_MAJOR = 102,
-};
+bool   ggml_cl_can_mul_mat(const struct ggml_tensor * src0, const struct ggml_tensor * src1, struct ggml_tensor * dst);
+size_t ggml_cl_mul_mat_get_wsize(const struct ggml_tensor * src0, const struct ggml_tensor * src1, struct ggml_tensor * dst);
+void   ggml_cl_mul_mat(const struct ggml_tensor * src0, const struct ggml_tensor * src1, struct ggml_tensor * dst, void * wdata, size_t wsize);
 
-enum ggml_blas_op {
-    GGML_BLAS_OP_N = 111,
-    GGML_BLAS_OP_T = 112,
-    GGML_BLAS_OP_C = 113,
-};
+void * ggml_cl_host_malloc(size_t size);
+void   ggml_cl_host_free(void * ptr);
 
-void ggml_cl_sgemm_wrapper(const enum ggml_blas_order order, const enum ggml_blas_op trans_a, const enum ggml_blas_op trans_b, const int m, const int n, const int k, const float alpha, const void *host_a, const int lda, const float *host_b, const int ldb, const float beta, float *host_c, const int ldc, const int btype);
+void ggml_cl_transform_tensor(struct ggml_tensor * tensor);
 
 #ifdef  __cplusplus
 }