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

hexagon : add cumsum op support (#21246)

Browse Source 
* hexagon : add cumsum op support

* hexagon: enable dma for cumsum op

* Fix line-ending

---------

Co-authored-by: Max Krasnyansky <maxk@qti.qualcomm.com>
This commit is contained in:
Todor Boinovski
2026-04-01 17:44:02 -07:00
committed by GitHub
co-authored by Max Krasnyansky
parent c30e012253
commit fbd441c379
6 changed files with 347 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-hexagon/htp/main.c
+43
View File
@@ -860,6 +860,41 @@ static void proc_ssm_conv_req(struct htp_context * ctx, struct htp_general_req *
send_htp_rsp(ctx, req->op, rsp_status, rsp_bufs, 1, &prof);
}
static void proc_cumsum_req(struct htp_context * ctx, struct htp_general_req * req, struct dspqueue_buffer * bufs) {
struct dspqueue_buffer rsp_bufs[1];
// We've written to the output buffer, we'd also need to flush it
rsp_bufs[0].fd = bufs[1].fd;
rsp_bufs[0].ptr = bufs[1].ptr;
rsp_bufs[0].offset = bufs[1].offset;
rsp_bufs[0].size = bufs[1].size;
rsp_bufs[0].flags = (DSPQUEUE_BUFFER_FLAG_FLUSH_SENDER | // Flush HTP
DSPQUEUE_BUFFER_FLAG_INVALIDATE_RECIPIENT); // Invalidate CPU
// Setup Op context
struct htp_ops_context octx = { 0 };
octx.ctx = ctx;
octx.src0 = req->src0;
octx.dst = req->dst;
octx.flags = req->flags;
octx.op = req->op;
octx.src0.data = (uint32_t) bufs[0].ptr;
octx.dst.data = (uint32_t) bufs[1].ptr;
octx.n_threads = ctx->n_threads;
struct profile_data prof;
profile_start(&prof);
uint32_t rsp_status = HTP_STATUS_INTERNAL_ERR;
if (vtcm_acquire(ctx) == AEE_SUCCESS) {
rsp_status = op_cumsum(&octx);
vtcm_release(ctx);
}
profile_stop(&prof);
send_htp_rsp(ctx, req->op, rsp_status, rsp_bufs, 1, &prof);
}
static void proc_activations_req(struct htp_context * ctx,
struct htp_general_req * req,
struct dspqueue_buffer * bufs,
@@ -1474,6 +1509,14 @@ static void htp_packet_callback(dspqueue_t queue, int error, void * context) {
proc_ssm_conv_req(ctx, &req, bufs);
break;
case HTP_OP_CUMSUM:
if (n_bufs != 2) {
FARF(ERROR, "Bad cumsum-req buffer list");
continue;
}
proc_cumsum_req(ctx, &req, bufs);
break;
default:
FARF(ERROR, "Unknown Op %u", req.op);
break;