Max Krasnyansky
192067b72d
* hexagon: use non-host bufs by default and make the backend fully async * hex-hb: remove optional hostbuf support and fix async copy * hex-unary: relax supported unary check * hex-bufs: use same get_alignment for host bufs * snapdragon: bump android_platform to 34 * hex-rows: super hacky get/set rows for q8_0 * hex-get-rows: fix q8_0 * hex-get-rows: supprot for f16 and cleanup for q8_0 * hex-get-rows: generic macros and specialized thread funcs * hex-get-rows: add DMA pipeline, vtcm_layout and kernel params * hex-set-rows: fix q8_0 support, add dma and tracing * hex-tests: override nmse threshold for HTP of Q8_0 quants * hex-fa: add support for Q8_0 with inplace dequantizers * hex-get-rows: simplify type dispatch * hex-rows: simplify GET/SET_ROWS DMA pipeline * hex-async: add events, set/get-tensor-async and rest of the async api support * hex-repack: use slice instead of expert in repack functions * hex-cpy: update event/async-cpy logging * hex-set-rows: optimize smaller tensors * hex-geglu: fix perf regression with larger tensors * hex-get-rows: add missing header * hex-set-rows: add missing header * hex-bufs: ressurect GGML_HEXAGON_HOSTBUF but disable it by default * hexagon: do not reject ops with non-heaxon buffers * hex-get-rows: apply >=32 restriction only for q8_0 * hex-res: bump vtcm acquire timeout to 10 seconds * hex-bufs: add support for cloning buffers between sessions to speed up tensor copies * hex-async: rework event recording and batch flushing and integrate with meta backend * hex-bufs: improved handling of repacked tensors * hex-repack: handle get_tensor_2d offsets * hex-dev: add support for devices with multiple NPUs * hex-sync: add support for sync tokens to synchronize npu devices for async splits * hex-mmap: cleanup mmap calls and add a retry for robustness * hex-sync: add failsafe if sync wait gets stuck * hex-sync: use sync_seq to check for completed events * hex-sync: rotate tokens for extra robustness * hex-devs: add supprot for legacy device names for now * hex-bufs: add support for auto-cloning buffers from diff sessions * hex-fusion: simplify and optimize htp-opnode fusion handling * hex-sync: override opnode name so that it shows up in the profiles * hex-trace: update scripts to handle multiple devices * hex-sync: bump the size of the opbatch queue and number of sync tokens * hex-cpy-sync: do not explicitly flush opbatches in cpy_tensor_async and add support for cpy-dma * hex-sync: add graph-flush threshold to avoid single op batches * hex-sync: add sync_peer so that we can flush peers we depend on during cross-device ops * hex-bufs: introduce tensor->extra and shadow_bufs for repacking * hex-l2: flush tiny tensors inline * hex-sync: use explicit l2flush for sync tokens * hex-extra: track weight flags via tensor extra * hex-fence: rename sync to fence * hex-repack: proper handling of set-tensor-2d in the shadow_buf * hex-trace: remove obsolete opstage mask that we used for profiling * hex-env: remove obsolete use_hmx variable * hexagon: new unified run.py and build.py and updated docs * snapdragon: update run script to auto-escapt test-backend-op -p argument * hex-scripts: fix trailing spaces * hex-scripts: fix flake8 warnings * snapdragon: cleanup dst lib/bin dirs before copying new build * hex-ops: add support for allreduce * hex-ar: improved allreduce with dma pipeline * hex-ar: align macros * hex-ar: consistent use of fence_seq * hex-ar: add AR_SELECT env var to select ALLREDUCE kernel or fallback * hex-ar: add proper synchronize handling for ALLREDUCE * hex-opbatch: looks like we now just rely on backend.synchronise to flush the batches, no need to flush them by threshold * hex-ar: bump block size to improve dma efficiency * hex-ar: fused ALLREDUCE+ADD * hex-ar: cleaner fence buffer management * hex-ar: futher allreduce tweaking to remove race conditions * hex-ar: add simple solver and remove non-dma kernels * hex-ar: add row-broadcast to fuse with bias ADD * hex-fence: pass seq numbers via op_params * hex-ar: allow for both entry/exit seq for completing entry wait * hex-ar: align macros * hex-ar: do not refetch broadcast row * hex-fusion: move all fusion into opbatch::add_op for consistency with ALLREDUCE and things * hex-fusion: fix incorrect MUL_MAT reordering * hex-mm: make fused 2x and 3x matmuls more generic * hex-fusion: move tensor fusion tagging to graph_compute * hexagon: make sure to copy tensor->extra by value * hex-get-rows: fix offset calc with row-chunking * hex-repack: get_tensor_2d fixes for non-zero offsets * snapdragon: make profile/trace scripts more robust and donot mix stdout/stderr by default * hex-devices: use legacy device nameing by default to ease the transition * hex-devices: hardcode CDSP domain IDs for current devices for now * hex-optrace: improve multi-NPU timestamp alignment and overall handling of cycle values * hex-optrace: more robust handling of the fence events
75 lines
2.1 KiB
C
75 lines
2.1 KiB
C
#ifndef HTP_SET_ROWS_OPS_H
|
|
#define HTP_SET_ROWS_OPS_H
|
|
|
|
#include "hex-fastdiv.h"
|
|
|
|
struct htp_set_rows_kernel_params {
|
|
int32_t n_threads;
|
|
int32_t total_tasks;
|
|
int32_t tasks_per_thread;
|
|
int32_t vtcm_size;
|
|
|
|
// Fastdiv helpers
|
|
struct fastdiv_values div_ne11;
|
|
struct fastdiv_values div_ne12;
|
|
struct fastdiv_values div_tasks_per_thread;
|
|
struct fastdiv_values div_ne02;
|
|
};
|
|
|
|
struct htp_set_rows_vtcm_layout {
|
|
size_t total_bytes;
|
|
size_t off_src0;
|
|
size_t off_dst;
|
|
|
|
size_t src0_bytes_per_thread;
|
|
size_t dst_bytes_per_thread;
|
|
|
|
size_t src0_spad_half_size;
|
|
size_t dst_spad_half_size;
|
|
};
|
|
|
|
static inline void htp_set_rows_vtcm_layout_build(
|
|
struct htp_set_rows_vtcm_layout * vtcm_layout,
|
|
int dst_type,
|
|
uint32_t ne00,
|
|
uint32_t n_threads) {
|
|
|
|
size_t src0_row_size = ne00 * 4;
|
|
size_t dst_row_size = 0;
|
|
switch (dst_type) {
|
|
case 0: // HTP_TYPE_F32
|
|
dst_row_size = ne00 * 4;
|
|
break;
|
|
case 1: // HTP_TYPE_F16
|
|
dst_row_size = ne00 * 2;
|
|
break;
|
|
case 8: // HTP_TYPE_Q8_0
|
|
dst_row_size = (ne00 / 32) * 34;
|
|
break;
|
|
default:
|
|
dst_row_size = 0;
|
|
break;
|
|
}
|
|
|
|
size_t src0_row_size_aligned = (src0_row_size + 255) & ~255;
|
|
size_t dst_row_size_aligned = (dst_row_size + 255) & ~255;
|
|
|
|
vtcm_layout->src0_spad_half_size = src0_row_size_aligned;
|
|
vtcm_layout->dst_spad_half_size = dst_row_size_aligned;
|
|
|
|
vtcm_layout->src0_bytes_per_thread = src0_row_size_aligned * 2;
|
|
vtcm_layout->dst_bytes_per_thread = dst_row_size_aligned * 2;
|
|
|
|
vtcm_layout->off_src0 = 0;
|
|
vtcm_layout->off_dst = vtcm_layout->off_src0 + vtcm_layout->src0_bytes_per_thread * n_threads;
|
|
vtcm_layout->total_bytes = vtcm_layout->off_dst + vtcm_layout->dst_bytes_per_thread * n_threads;
|
|
}
|
|
|
|
#if defined(__cplusplus)
|
|
static_assert(sizeof(struct htp_set_rows_kernel_params) <= 128, "htp_set_rows_kernel_params is too large for kernel_params blob");
|
|
#else
|
|
_Static_assert(sizeof(struct htp_set_rows_kernel_params) <= 128, "htp_set_rows_kernel_params is too large for kernel_params blob");
|
|
#endif
|
|
|
|
#endif // HTP_SET_ROWS_OPS_H
|