Max KrasnyanskyandGitHub
8be759e6f7
* hex-mm: new weight layout and fusion updates * hvx-mm: unroll the new tiled vec_dots to optimize hvx register util * hex-mm: optimize dyn.quant format for q8_0 and q8_1 to reduce overhead in vec_dots. * hvx-mm: parallel quantizer per block for large rows * hvx-mm: simplify and futher optimize dyn.quant and vec_dots * hvx-mm: keep intermediate per tile accumulators in fp16 * hmx-mm: optimize weight dequant by aligning the repacked tiles with the DMA * hmx-mm: remove qweight scratch and just use vtcm_weight * hmx-mm: remove all unused and obsolete code * hmx-mm: the new tiled repack format is here to stay -- rename all x4x2 to _tiled * hmx-mm: improve activation processing with dma prefetch * hex-mm: fix hmx/hvx fallback logic and MUL_MAT_ID allocation (unbreaks OLMoE) * hex-mm: align the weight tiles with dma just like we did in hmx-mm * hex-mm: factor out common mm bits into htp/matmul-ops.h * hex-mm: start moving mm kernel selection to the host * hex-mm: move all of the matmul param compute into the host * hmx-mm: restore pipelined mode * hmx-mm: unroll the dequant functions to optimize register usage * hmx-mm: further improve activation process * hex-mm: use vtcm_seq_alloc for all vtcm allocations and define more common functions * hex-mm: improve mm optimizer to acount for number of activation threads * hex-mm: fix matmul-id kernel params selection (unbreaks OLMoE and LFM) * hexagon: remove support for arch < v73 since HMX is now required for most use-cases * hex-mm: cleanup naming for consistency * hex-mm: make sure matmul fusion accounts for vtcm allocation * hex-mm: minor cleanup for kernel_params definition * hex-mm: replace hardcoded limits with proper checks for vtcm requirements * hex-mm: add support for non-tiled mm as a fallback option and factor out hvx kernels into separate header * hex-mm: remove unused functions * hex-mm: add shorthand for MM_SELECT in run-tool script * hvx-mm: factor out hvx/hmx microkernels and unify matmul entry and dispatch * hex-mm: further cleanup matmul fallback path * hex-mm: refactor matmul entry point and dispatch a bit further * hexagon: update cmake build to enable hmx for everything * hex-ops: optimize kernel_param updates and include summary in the logs * hex-mm: add support for GGML_HEXAGON_MM_SELECT * hex-mm: add hex-common header * hex-mm: pass correct number of tasks to workpool * hex-mm: add proper checks for no-work in dyn.quant tasks * hex-mm: convert all quantizers into a macro * hex-mm: fix hvx-flat fallback to pass all MUL_MAT tests * hex-mm: vectorize q8_1 quantizer * hex-mm: improve fused ffn mm stride handling * hex-mm: consistent use of n_threads and pipeline in kernel_params * hexagon: minor formatting * hex-mm: update MUL_MAT_ID kernel_param handling to make sure host/npu are in sync * hvx-mm: go back to accumulating in fp32 in tiled hvx kernels, more accurate and same perf * hvx-mm: unroll the loops and remove masking that is not needed for tiled accums * hmx-mm: optimize activation processing (slit loops, some unrolling, etc) * hmx-mm: minor optimization for output processing * hex-mm: consistent use of uint32_t and size_t in mm kernels * hex-mm: remove legacy restrictions for rows to be multiple of 256 * hexagon: replace sprintf with snprintf * hex-mm: relax hardcoded nrows checks and rely on VTCM size requirements * hexagon: minor alignment fix * hexagon: fix trailing spaces * hex-mm: relax padding from 256 to 128 (leftovers) * hex-mm: remove redundant checks for weight align to 128 we always use 2D dma for the weights and align them properly * hmx-mm: MUL_MAT_ID better work distribution between hvx threads and hmx tracing * hex-mm: specialize per-token mmid activation handling * hex-profile: update python scripts to handle kernel-params section in the logging output * hex-mm: move n_prefetch (aka dma_depth) into kernel params and remove unused fields * hex-trace: use easier to parse format, simply and fix post-proc scripts * hmx-mm: relax 32 row limit for output processing which helps utilization * hmx-mm: use start-chunk idx for tracing info * hmx-mm: parameterize activation dma pipeline * hexagon: add support for simple graph caching to avoid recomputing kernel-params * hex-mm: remove left-over repack functions * hex-mm: tighten n_prefetch asserts * hex-mm: remove duplicate round/align_up helper * hexagon: cleanup common header used in host/npu * hexagon: update early wakeup threshold * hmx-mm: define cost constants and update solver to assume that repacked ne[1] is padded to 32 * hmx-mm: make precompute_matmul a bit more readable (split into smaller functions, etc) * hex-mm: remove n_threads constraint * hex-mm: minor formatting updates * hex-mm: remove obsolete profiling logs * hex-mm: restore hardcode gate to refuse lm-head to avoid repacking that tensor
127 lines
3.8 KiB
C
127 lines
3.8 KiB
C
#ifndef HTP_CTX_H
|
|
#define HTP_CTX_H
|
|
|
|
#include "hex-dma.h"
|
|
#include "hmx-queue.h"
|
|
#include "htp-ops.h"
|
|
#include "hex-profile.h"
|
|
#include "worker-pool.h"
|
|
|
|
#include <assert.h>
|
|
#include <dspqueue.h>
|
|
#include <stdatomic.h>
|
|
#include <stdint.h>
|
|
#include <stdbool.h>
|
|
|
|
#ifndef HTP_MAX_NTHREADS
|
|
#define HTP_MAX_NTHREADS 10
|
|
#endif
|
|
#define HTP_MAX_MMAPS 16
|
|
|
|
// Memory mapping
|
|
struct htp_mmap {
|
|
uint64_t size;
|
|
uint64_t base;
|
|
uint32_t fd;
|
|
uint32_t reserved;
|
|
};
|
|
|
|
// Scratchpad state
|
|
struct htp_spad {
|
|
const struct htp_tensor * src; // original src of the data (for reuse)
|
|
uint8_t * data; // pointer to an area in vtcm
|
|
uint32_t stride; // stride used inside this spad
|
|
uint32_t size; // total size
|
|
uint32_t size_per_thread; // size per thread
|
|
};
|
|
|
|
struct htp_context;
|
|
|
|
// Context while processing an Op
|
|
// TODO: fold this into the main context
|
|
struct htp_ops_context {
|
|
struct htp_context * ctx;
|
|
|
|
enum htp_op_code op; // FIXME: rename to opcode
|
|
int32_t op_params[HTP_OP_MAX_PARAMS];
|
|
int32_t kernel_params[HTP_OP_MAX_KERN_PARAMS];
|
|
|
|
const struct htp_tensor * src[HTP_OP_MAX_INPUTS];
|
|
union {
|
|
const struct htp_tensor * dst;
|
|
const struct htp_tensor * dsts[HTP_OP_MAX_OUTPUTS];
|
|
};
|
|
|
|
// TODO convert these to an array
|
|
struct htp_spad src0_spad;
|
|
struct htp_spad src1_spad;
|
|
struct htp_spad src2_spad;
|
|
struct htp_spad src3_spad;
|
|
struct htp_spad dst_spad;
|
|
|
|
uint32_t n_threads;
|
|
uint32_t flags;
|
|
};
|
|
|
|
// Main context for htp DSP backend
|
|
struct htp_context {
|
|
dspqueue_t queue;
|
|
dma_queue * dma[HTP_MAX_NTHREADS];
|
|
struct htp_mmap mmap[HTP_MAX_MMAPS];
|
|
worker_pool_context_t worker_pool;
|
|
uint32_t n_threads;
|
|
|
|
int thread_id;
|
|
int thread_prio;
|
|
|
|
bool hmx_enabled;
|
|
bool etm;
|
|
uint32_t profiler;
|
|
struct htp_thread_trace trace[HTP_MAX_NTHREADS + 1];
|
|
|
|
uint8_t * vtcm_base;
|
|
size_t vtcm_size;
|
|
uint32_t vtcm_rctx;
|
|
atomic_bool vtcm_valid;
|
|
atomic_bool vtcm_needs_release;
|
|
|
|
uint64_t max_vmem;
|
|
|
|
// Persistent DDR scratchpad for MUL_MAT_ID mappings
|
|
void * ddr_spad_base;
|
|
size_t ddr_spad_size;
|
|
|
|
struct htp_ops_context octx;
|
|
|
|
struct hmx_queue * hmx_queue; // Async HMX queue for pipeline overlap
|
|
};
|
|
|
|
int op_matmul(struct htp_ops_context * octx);
|
|
int op_matmul_id(struct htp_ops_context * octx);
|
|
int op_matmul_qkv(struct htp_ops_context * octx);
|
|
int op_matmul_ffn(struct htp_ops_context * octx);
|
|
int op_binary(struct htp_ops_context * octx);
|
|
int op_unary(struct htp_ops_context * octx);
|
|
int op_sum_rows(struct htp_ops_context * octx);
|
|
int op_activations(struct htp_ops_context * octx);
|
|
int op_softmax(struct htp_ops_context * octx);
|
|
int op_add_id(struct htp_ops_context * octx);
|
|
int op_rope(struct htp_ops_context * octx);
|
|
int op_flash_attn_ext(struct htp_ops_context * octx);
|
|
int op_set_rows(struct htp_ops_context * octx);
|
|
int op_get_rows(struct htp_ops_context * octx);
|
|
int op_cpy(struct htp_ops_context * octx);
|
|
int op_repeat(struct htp_ops_context * octx);
|
|
int op_argsort(struct htp_ops_context * octx);
|
|
int op_ssm_conv(struct htp_ops_context * octx);
|
|
int op_cumsum(struct htp_ops_context * octx);
|
|
int op_fill(struct htp_ops_context * octx);
|
|
int op_concat(struct htp_ops_context * octx);
|
|
int op_diag(struct htp_ops_context * octx);
|
|
int op_solve_tri(struct htp_ops_context * octx);
|
|
int op_gated_delta_net(struct htp_ops_context * octx);
|
|
int op_tri(struct htp_ops_context * octx);
|
|
int op_pad(struct htp_ops_context * octx);
|
|
|
|
#endif /* HTP_CTX_H */
|