mirror of
https://github.com/ggml-org/whisper.cpp.git
synced 2026-10-04 05:21:27 +02:00
Daniel Bevenius
76da3529d9
* scripts : add initial profiling script (wip) * src : add precompile headers (PCH) for models.h * common : add common.h as PCH * ggml : add PCH for ggml-impl.h * mtmd : use PCH for models.h * scripts : add script to build with Server/Tools/Tests * server : add PCH for common.h * docs: add profiling progress notes (wip) * ggml : add exclude for GCC + SVE on ARM Refs: https://github.com/ggml-org/llama.cpp/actions/runs/33393906061/job/99493756214?pr=28091 * ggml : attempt to fix use of std::hardware_destructive_inference_size Refs: https://github.com/ggml-org/llama.cpp/actions/runs/33396221677/job/99501265689?pr=28091 * squash! ggml : attempt to fix use of std::hardware_destructive_inference_size Add a version check for GCC 12 to conditionally apply the `-Winterference-size` pragma. * editorconfig : exclude profiling reports dir This directory will not be included in the merge later and this commit can be ignore at that point. Just fixing to keep CI happy. * ggml : skip PCH for gcc on non-x86 architectures * tests : add PCH for peg-parser/tests.h There are 7 peg-parser tests that can share one PCH instead of then each parsing the full tests.h. * common : add PCH for chat.h * docs : update linux build profiling full results Just updating after a number of PCH additions. These are not exact figures and will vary a bit from run to run, but they give a general idea of the performance impact of PCH. * cmake : introduce unity build for models This commit introduces a unity build for the models to improve compilation time. The improvements were roughly the following: ```console +------------------------+-----+------------+------------+------------+ | Build | TUs | Frontend | Backend | Total | +------------------------+-----+------------+------------+------------+ | Full, master | 396 | 811.0 s | 692.2 s | 1,503.2 s | | Full, with PCH | 405 | 380.0 s | 664.7 s | 1,044.7 s | | Full, with PCH + UB | 264 | 357.7 s | 635.7 s | 993.4 s | +------------------------+-----+------------+------------+------------+ TU = Translation Unit. Full = includes Server, Tools, and Tests. PCH = precompiled headers. UB = unity build for models. ``` * docs : update linux profiling table with unitiy build results * docs : update mac profiling results to include unity build [no ci] * docs: remove profiling reports * scripts : merge build profile scripts into one script I was lazy before and just copied the first script to enable Tests, Server, and Tools. This now merges them into a single script. * Revert "editorconfig : exclude profiling reports dir" [no ci] This reverts commit 2922a12118a0730d2f7632bcba265b44a0856c59. * src : rename ggml_view_2d_slice to gemma3n_view_2d_slice This is to be consistent with the rename in gemma4.cpp which was required to avoid a name clash. * cmake : add build profile script for windows [no ci] This commit adds a port of the scripts/build-profile.sh script to windows powershell. This was developed on Windows on ARM but should work on X64 as well but needs to be tested there as well.
133 lines
10 KiB
C++
133 lines
10 KiB
C++
#pragma once
|
|
|
|
#include "ggml.h"
|
|
|
|
//
|
|
// cache line
|
|
//
|
|
|
|
#if defined(__cpp_lib_hardware_interference_size)
|
|
#define CACHE_LINE_SIZE std::hardware_destructive_interference_size
|
|
#else
|
|
#if defined(__POWER9_VECTOR__)
|
|
#define CACHE_LINE_SIZE 128
|
|
#elif defined(__VXE__) || defined(__VXE2__)
|
|
#define CACHE_LINE_SIZE 256
|
|
#else
|
|
#define CACHE_LINE_SIZE 64
|
|
#endif
|
|
#endif
|
|
|
|
// -Winterference-size was introduced in GCC 12
|
|
#if defined(__cplusplus) && defined(__GNUC__) && !defined(__clang__) && __GNUC__ >= 12
|
|
#pragma GCC diagnostic push
|
|
#pragma GCC diagnostic ignored "-Winterference-size"
|
|
#endif
|
|
static const size_t CACHE_LINE_SIZE_F32 = CACHE_LINE_SIZE/sizeof(float);
|
|
#if defined(__cplusplus) && defined(__GNUC__) && !defined(__clang__) && __GNUC__ >= 12
|
|
#pragma GCC diagnostic pop
|
|
#endif
|
|
|
|
// Work buffer size for im2col operations in CONV2D
|
|
#define GGML_IM2COL_WORK_SIZE (16 * 1024 * 1024)
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
void ggml_compute_forward_dup(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_add(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_add_id(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_add1(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_acc(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_sum(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_sum_rows(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_cumsum(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_mean(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_argmax(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_count_equal(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_repeat(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_repeat_back(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_concat(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_silu_back(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_norm(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_rms_norm(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_rms_norm_mul_fused(const struct ggml_compute_params * params, struct ggml_tensor * dst_rms_norm, struct ggml_tensor * dst_mul);
|
|
void ggml_compute_forward_rms_norm_back(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_group_norm(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_l2_norm(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_out_prod(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_scale(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_set(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_cpy(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_cont(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_get_rows(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_get_rows_back(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_set_rows(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_diag(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_diag_mask_inf(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_diag_mask_zero(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_soft_max(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_soft_max_ext_back(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_rope(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_rope_back(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_clamp(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_conv_transpose_1d(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_im2col(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_im2col_back_f32(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_im2col_3d(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_col2im_1d(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_conv_2d(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_conv_3d(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_conv_transpose_2d(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_conv_2d_dw(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_pool_1d(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_pool_2d(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_pool_2d_back(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_upscale(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_pad(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_pad_reflect_1d(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_roll(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_arange(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_timestep_embedding(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_argsort(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_top_k(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_leaky_relu(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_tri(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_fill(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_flash_attn_ext(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_flash_attn_back(
|
|
const struct ggml_compute_params * params,
|
|
const bool masked,
|
|
struct ggml_tensor * dst);
|
|
void ggml_compute_forward_ssm_conv(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_ssm_scan(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_win_part(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_win_unpart(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_unary(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_glu(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_get_rel_pos(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_add_rel_pos(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_rwkv_wkv6(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_rwkv_wkv7(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_solve_tri(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_gla(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_gated_delta_net(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_lightning_indexer(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_dsv4_hc_comb(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_dsv4_hc_pre(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_dsv4_hc_post(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_map_custom1(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_map_custom2(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_map_custom3(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_custom(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_cross_entropy_loss(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_cross_entropy_loss_back(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_opt_step_adamw(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_mul_mat(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_fwht(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_opt_step_sgd(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|