diff options
author | Georgi Gerganov <ggerganov@gmail.com> | 2023-07-24 14:46:21 +0300 |
---|---|---|
committer | GitHub <noreply@github.com> | 2023-07-24 14:46:21 +0300 |
commit | 5b2b2dc6ae8086bff7c9b3c17fb435cf319b7185 (patch) | |
tree | db5cf0288472b4fc0ef88217bfcbddf4d18c2a03 /ggml-metal.m | |
parent | 42f70cb2f6a8089e0a0560a459e4ba317bac4d49 (diff) |
ggml : sync (unary ops refactor, static-correctness) (#2370)
* ggml : sync (unary ops, tests)
ggml-ci
* tests : remove unnecessary funcs
Diffstat (limited to 'ggml-metal.m')
-rw-r--r-- | ggml-metal.m | 96 |
1 files changed, 53 insertions, 43 deletions
diff --git a/ggml-metal.m b/ggml-metal.m index bf3f68f..1fd6e85 100644 --- a/ggml-metal.m +++ b/ggml-metal.m @@ -519,48 +519,56 @@ void ggml_metal_graph_compute( [encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)]; } break; - case GGML_OP_SILU: - { - if (encoder == nil) { - encoder = [command_buffer computeCommandEncoder]; - } - - [encoder setComputePipelineState:ctx->pipeline_silu]; - [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0]; - [encoder setBuffer:id_dst offset:offs_dst atIndex:1]; - - const int64_t n = ggml_nelements(dst); - - [encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)]; - } break; - case GGML_OP_RELU: - { - if (encoder == nil) { - encoder = [command_buffer computeCommandEncoder]; - } - - [encoder setComputePipelineState:ctx->pipeline_relu]; - [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0]; - [encoder setBuffer:id_dst offset:offs_dst atIndex:1]; - - const int64_t n = ggml_nelements(dst); - - [encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)]; + case GGML_OP_UNARY: + switch (ggml_get_unary_op(gf->nodes[i])) { + case GGML_UNARY_OP_SILU: + { + if (encoder == nil) { + encoder = [command_buffer computeCommandEncoder]; + } + + [encoder setComputePipelineState:ctx->pipeline_silu]; + [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0]; + [encoder setBuffer:id_dst offset:offs_dst atIndex:1]; + + const int64_t n = ggml_nelements(dst); + + [encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)]; + } break; + case GGML_UNARY_OP_RELU: + { + if (encoder == nil) { + encoder = [command_buffer computeCommandEncoder]; + } + + [encoder setComputePipelineState:ctx->pipeline_relu]; + [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0]; + [encoder setBuffer:id_dst offset:offs_dst atIndex:1]; + + const int64_t n = ggml_nelements(dst); + + [encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)]; + } break; + case GGML_UNARY_OP_GELU: + { + if (encoder == nil) { + encoder = [command_buffer computeCommandEncoder]; + } + + [encoder setComputePipelineState:ctx->pipeline_gelu]; + [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0]; + [encoder setBuffer:id_dst offset:offs_dst atIndex:1]; + + const int64_t n = ggml_nelements(dst); + + [encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)]; + } break; + default: + { + fprintf(stderr, "%s: node %3d, op = %8s not implemented\n", __func__, i, ggml_op_name(dst->op)); + GGML_ASSERT(false); + } } break; - case GGML_OP_GELU: - { - if (encoder == nil) { - encoder = [command_buffer computeCommandEncoder]; - } - - [encoder setComputePipelineState:ctx->pipeline_gelu]; - [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0]; - [encoder setBuffer:id_dst offset:offs_dst atIndex:1]; - - const int64_t n = ggml_nelements(dst); - - [encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)]; - } break; case GGML_OP_SOFT_MAX: { if (encoder == nil) { @@ -979,8 +987,10 @@ void ggml_metal_graph_compute( [encoder dispatchThreadgroups:MTLSizeMake(ne01, ne02, ne03) threadsPerThreadgroup:MTLSizeMake(nth, 1, 1)]; } break; default: - fprintf(stderr, "%s: node %3d, op = %8s not implemented\n", __func__, i, ggml_op_name(dst->op)); - GGML_ASSERT(false); + { + fprintf(stderr, "%s: node %3d, op = %8s not implemented\n", __func__, i, ggml_op_name(dst->op)); + GGML_ASSERT(false); + } } } |