Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

hexagon: further improved pipeline of the core bits (L2, DMA, MM, FA) (#26049)

Browse Source 
* hex-l2: use dirty ranges for flushing

* hex-l2: simplify range based flush logic

* hex-l2: optimize dirty range scans

* hex-hvx: support for reduce_max_i32

* hex-mm: optimize fused MUL_MAT+ADD to use vtcm for bias when it fits

* hex-mmid: optimize mmid row-mapping generation

* hex-mmid: optimize mmid row-mapping generation

* hex-mmid: optimize mmid row-mapping generation (round2)

* hmx-mm: optimize output proc by tiling (col-chunking)

* hex-fa: start the next q dmas a bit earlier

* hex-fa: prefetch Q even earlier

* hvx-fa: optimize softmax to keep things in hvx registers

* hex-fa: hoist const register init in softmax loop

* hmx-fa: kick off next-qkv DMAs before o-proc

* hmx-fa: hoist various checks out of the inner loop

* hmx-fa: adjust the cost model to better balance softmax work across hvx threads

* hmx-fa: overlap diag rescale build with last HMX task

* hmx-fa: optimize idx update in output proc

* hmx-fa: unroll the softmax loops for improved perf

* hmx-fa: overlap qk-dot with softmax, double-buffer p and s tiles

* hex-trace: double the default number of trace entries

* hex-trace: add trace events for opbatch and buffer mgmt

* hex-trace: overhaul tracing to simplify runtime event handling and support opbatch stats

* hex-trace: replace ascii timeline diagram with pipeline bubbles detector

* hex-trace: handle missing start/stop events

* hex-dma: always log stop/start trace events even for dummy dmas

* hex-scripts: fix flake warnings
This commit is contained in:
Max Krasnyansky
2026-07-23 19:13:03 -07:00
committed by GitHub
parent c0bc8591e8
commit 0a50d9909a
17 changed files with 1666 additions and 761 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-hexagon/htp/main.c
+37 -27
View File
@@ -901,10 +901,8 @@ static void prep_tensor(struct htp_context *ctx, struct htp_buf_desc *bufs, stru
uint32_t offset = t->data;
uint32_t size = t->size;
uint32_t bi = t->bi;
uint32_t alias = t->alias;
t->data = (uint32_t) (bufs[bi].base + offset); // update data to the actual pointer
t->alias = (uint32_t) (tens + alias); // update alias to the actual pointer
FARF(HIGH, "prep-tensor #%u: bi %u offset %u size %u data %p : %u:%u:%u:%u", idx, t->bi, offset, t->size, (void*) t->data,
t->ne[0], t->ne[1], t->ne[3], t->ne[3]);
@@ -955,14 +953,14 @@ static int proc_op_req(struct htp_ops_context * octx, struct htp_tensor *tens, u
octx->dsts[i] = dst;
octx->dst_dma[i] = octx->ctx->dma; // FIXME: ? octx->ctx->dma_cached : octx->ctx->dma;
htp_tensor_make_dirty(dst, octx->ctx->dirty_map);
FARF(HIGH, "prep-dst[%u] #%u: data %p size %u : %u:%u:%u:%u", i, dst_idx, (void*) dst->data, dst->size,
dst->ne[0], dst->ne[1], dst->ne[2], dst->ne[3]);
}
int status = execute_op(octx);
htp_tensor_dirty_all(octx->ctx, octx->dsts, HTP_OP_MAX_OUTPUTS);
octx->src0_spad.src = NULL;
octx->src1_spad.src = NULL;
octx->src2_spad.src = NULL;
@@ -994,12 +992,6 @@ static void process_opbatch(struct htp_context * ctx, const struct htp_opbatch_r
FARF(HIGH, "processing opbatch #%u: n-bufs %u n-tensors %u n-ops %u n-traces %u : m-size %u b-size %u t-size %u o-size %u", req->id,
n_bufs, n_tens, n_ops, req->n_traces, dbuf->size, b_size, t_size, o_size);
// Clean cache at the start of the batch
// We cant trace this part because the trace buffer is setup later
qurt_mem_cache_clean((qurt_addr_t) 0, 0, QURT_MEM_CACHE_FLUSH_INVALIDATE_ALL, QURT_MEM_DCACHE);
hex_l2fetch_block(ctx, ctx->footprint);
bitmap_reset(ctx->dirty_map, HTP_OP_MAX_TENSORS);
// Setup descriptor pointers
uint8_t * m_ptr = dbuf->ptr;
struct htp_buf_desc* bufs = (struct htp_buf_desc*) m_ptr; m_ptr += b_size;
@@ -1007,13 +999,8 @@ static void process_opbatch(struct htp_context * ctx, const struct htp_opbatch_r
struct htp_op_desc* ops = (struct htp_op_desc*) m_ptr; m_ptr += o_size;
struct htp_prof_desc* pds = (struct htp_prof_desc*) m_ptr;
prep_op_bufs(ctx, bufs, n_bufs);
prep_tensors(ctx, bufs, tens, n_tens);
struct htp_ops_context *octx = &ctx->octx;
memset(octx, 0, sizeof(*octx));
octx->n_threads = ctx->n_threads;
octx->ctx = ctx;
struct profile_data batch_prof;
profile_start(HTP_PROF_BASIC, &batch_prof);
memset(ctx->trace, 0, sizeof(ctx->trace));
if (ctx->profiler == HTP_PROF_TRACE) {
@@ -1024,6 +1011,24 @@ static void process_opbatch(struct htp_context * ctx, const struct htp_opbatch_r
}
}
// Clean cache at the start of the batch
htp_trace_event_start(&ctx->trace[0], HTP_TRACE_EVT_L2FLUSH, 0);
qurt_mem_cache_clean((qurt_addr_t) 0, 0, QURT_MEM_CACHE_FLUSH_INVALIDATE_ALL, QURT_MEM_DCACHE);
hex_l2fetch_block(ctx, ctx->footprint);
memset(ctx->dirty_ranges, 0, sizeof(ctx->dirty_ranges));
htp_trace_event_stop(&ctx->trace[0], HTP_TRACE_EVT_L2FLUSH, 0);
htp_trace_event_start(&ctx->trace[0], HTP_TRACE_EVT_BUFF, 0);
prep_op_bufs(ctx, bufs, n_bufs);
htp_trace_event_stop(&ctx->trace[0], HTP_TRACE_EVT_BUFF, 0);
prep_tensors(ctx, bufs, tens, n_tens);
struct htp_ops_context *octx = &ctx->octx;
memset(octx, 0, sizeof(*octx));
octx->n_threads = ctx->n_threads;
octx->ctx = ctx;
work_queue_wakeup(ctx->work_queue);
if (ctx->hmx_queue) {
hmx_queue_wakeup(ctx->hmx_queue);
@@ -1056,13 +1061,23 @@ static void process_opbatch(struct htp_context * ctx, const struct htp_opbatch_r
}
work_queue_suspend(ctx->work_queue);
// Flush remaining dirty tensors at the end of the batch
htp_trace_event_start(&ctx->trace[0], HTP_TRACE_EVT_L2FLUSH, 0);
qurt_mem_cache_clean((qurt_addr_t) 0, 0, QURT_MEM_CACHE_FLUSH_INVALIDATE_ALL, QURT_MEM_DCACHE);
htp_trace_event_stop(&ctx->trace[0], HTP_TRACE_EVT_L2FLUSH, 0);
profile_stop(HTP_PROF_BASIC, &batch_prof);
struct htp_opbatch_rsp rsp;
memset(&rsp, 0, sizeof(rsp));
rsp.id = req->id;
rsp.status = op_status;
rsp.n_bufs = n_bufs;
rsp.n_tensors = n_tens;
rsp.n_ops = n_ops;
rsp.id = req->id;
rsp.status = op_status;
rsp.n_bufs = n_bufs;
rsp.n_tensors = n_tens;
rsp.n_ops = n_ops;
rsp.usecs = batch_prof.usecs;
rsp.cycles_start = batch_prof.cycles_start;
rsp.cycles_stop = batch_prof.cycles_stop;
if (ctx->profiler == HTP_PROF_TRACE) {
for (int t = 0; t <= HTP_MAX_NTHREADS; t++) {
@@ -1073,11 +1088,6 @@ static void process_opbatch(struct htp_context * ctx, const struct htp_opbatch_r
struct dspqueue_buffer write_dbuf = *dbuf;
write_dbuf.flags = DSPQUEUE_BUFFER_FLAG_FLUSH_SENDER | DSPQUEUE_BUFFER_FLAG_INVALIDATE_RECIPIENT;
// Flush remaining dirty tensors at the end of the batch
htp_trace_event_start(&ctx->trace[0], HTP_TRACE_EVT_L2FLUSH, 0);
qurt_mem_cache_clean((qurt_addr_t) 0, 0, QURT_MEM_CACHE_FLUSH_INVALIDATE_ALL, QURT_MEM_DCACHE);
htp_trace_event_stop(&ctx->trace[0], HTP_TRACE_EVT_L2FLUSH, 0);
err = dspqueue_write(queue, 0, 1, &write_dbuf, sizeof(rsp), (const uint8_t *) &rsp, DSPQUEUE_TIMEOUT_NONE);
if (err != 0) {
FARF(ERROR, "dspqueue_write failed: 0x%08x", (unsigned) err);