From 7296c961d9303010a2b98379f738da2a8a55aa1b Mon Sep 17 00:00:00 2001 From: 0cc4m Date: Fri, 28 Apr 2023 16:57:16 +0200 Subject: ggml : add CLBlast support (#1164) * Allow use of OpenCL GPU-based BLAS using ClBlast instead of OpenBLAS for context processing * Improve ClBlast implementation, avoid recreating buffers, remove redundant transfers * Finish merge of ClBlast support * Move CLBlast implementation to separate file Add buffer reuse code (adapted from slaren's cuda implementation) * Add q4_2 and q4_3 CLBlast support, improve code * Double CLBlast speed by disabling OpenBLAS thread workaround Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com> Co-authored-by: slaren <2141330+slaren@users.noreply.github.com> * Fix device selection env variable names * Fix cast in opencl kernels * Add CLBlast to CMakeLists.txt * Replace buffer pool with static buffers a, b, qb, c Fix compile warnings * Fix typos, use GGML_TYPE defines, improve code * Improve btype dequant kernel selection code, add error if type is unsupported * Improve code quality * Move internal stuff out of header * Use internal enums instead of CLBlast enums * Remove leftover C++ includes and defines * Make event use easier to read Co-authored-by: Henri Vasserman * Use c compiler for opencl files * Simplify code, fix include * First check error, then release event * Make globals static, fix indentation * Rename dequant kernels file to conform with other file names * Fix import cl file name --------- Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com> Co-authored-by: slaren <2141330+slaren@users.noreply.github.com> Co-authored-by: Henri Vasserman Co-authored-by: Georgi Gerganov --- ggml-opencl.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) create mode 100644 ggml-opencl.h (limited to 'ggml-opencl.h') diff --git a/ggml-opencl.h b/ggml-opencl.h new file mode 100644 index 00000000..7bcc603e --- /dev/null +++ b/ggml-opencl.h @@ -0,0 +1,24 @@ +#pragma once + +#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, +}; + +enum ggml_blas_op { + GGML_BLAS_OP_N = 111, + GGML_BLAS_OP_T = 112, + GGML_BLAS_OP_C = 113, +}; + +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); + +#ifdef __cplusplus +} +#endif -- cgit v1.2.3