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

hexagon: optimize HMX matmul operations (#21071)

Browse Source 
* optimize hmx_mat_mul functions by calculating row and column tiles upfront

* refactor core_dot_chunk_fp16 to use size_t for tile counts and improve readability

* wip

* set scale outside of loop

* wip

* refactor core_mma_chunk_fp16 and mat_mul_qk_0_d16a32 to use size_t for tile counts

* wip

* wip

* refactor transfer_output_chunk_fp16_to_fp32 to use size_t for dimensions

* refactor core_dot_chunk_fp16 to use size_t for tile row stride calculation

* wip

* refactor hmx_mat_mul functions to use hvx_vec_splat_f16 for column scales initialization

* refactor hmx_mat_mul_permuted_w16a32_batched to streamline scale setting and locking

* refactor core_dot_chunk_fp16 to improve tile stride calculations for output

* refactor hmx_mat_mul functions to use Q6_V_vsplat_R for column scales initialization

* fix compiling error

* wip

* optimize row and column tile indexing in core_mma_chunk_fp16 function

* wip

* Revert "wip"

This reverts commit cde679eff79c4a28dd2d89d32f710015e09592b6.

* Add size limit check for HAP_mmap in htp_iface_mmap and drop_mmap functions

* wip
This commit is contained in:
nullname
2026-04-16 13:48:34 -07:00
committed by GitHub
parent 4fbdabdc61
commit 85dde8dc4a
3 changed files with 80 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-hexagon/htp/main.c
+30 -1
View File
@@ -118,7 +118,11 @@ AEEResult htp_iface_close(remote_handle64 handle) {
// release the mmaps (if any)
for (uint32_t i=0; i<HTP_MAX_MMAPS; i++) {
if (ctx->mmap[i].size) {
#if __HVX_ARCH__ > 73
HAP_munmap2((void *) ctx->mmap[i].base, ctx->mmap[i].size);
#else
HAP_munmap((void *) ctx->mmap[i].base, ctx->mmap[i].size);
#endif
ctx->mmap[i].size = 0;
ctx->mmap[i].base = NULL;
ctx->mmap[i].fd = -1;
@@ -173,8 +177,16 @@ AEEResult htp_iface_mmap(remote_handle64 handle, int fd, uint32_t size, uint32_t
struct htp_mmap *m = &ctx->mmap[i];
if (!m->size) {
FARF(HIGH, "mmap : fd %u size %u pinned %u", fd, size, pinned);
#if __HVX_ARCH__ > 73
void *va = HAP_mmap2(NULL, size, HAP_PROT_READ | HAP_PROT_WRITE, 0, fd, 0);
#else
if (size > HTP_MMAP_MAX_VMEM) { // HAP_mmap has a size limit of 2GB
FARF(ERROR, "mmap failed : size %u exceeds 2GB limit for HAP_mmap", (uint32_t) size);
abort(); // can't do much else at this point
}
void *va = HAP_mmap(NULL, size, HAP_PROT_READ | HAP_PROT_WRITE, 0, fd, 0);
#endif
if (va == (void*)-1) {
FARF(ERROR, "mmap failed : va %p fd %u size %u", va, fd, (uint32_t) size);
return AEE_EFAILED;
@@ -202,7 +214,11 @@ AEEResult htp_iface_munmap(remote_handle64 handle, int fd) {
struct htp_mmap *m = &ctx->mmap[i];
if (fd < 0 || m->fd == fd) {
FARF(HIGH, "unmmap : base %p fd %u size %u", (void*) m->base, m->fd, (uint32_t) m->size);
#if __HVX_ARCH__ > 73
HAP_munmap2((void *) m->base, m->size);
#else
HAP_munmap((void *) m->base, m->size);
#endif
m->size = 0;
m->base = NULL;
m->fd = -1;
@@ -526,7 +542,11 @@ static inline bool reuse_buf(struct htp_context *ctx, uint32_t *m_reuse, struct
static inline void drop_mmap(struct htp_context *ctx, struct htp_mmap *m) {
if (m->size && !m->pinned) {
FARF(HIGH, "unmap : fd %u base %p size %u pinned %u", m->fd, (void*) m->base, (uint32_t) m->size, m->pinned);
#if __HVX_ARCH__ > 73
HAP_munmap2((void *) m->base, m->size);
#else
HAP_munmap((void *) m->base, m->size);
#endif
m->size = 0;
m->base = 0;
m->fd = -1;
@@ -540,7 +560,16 @@ static inline void mmap_buf(struct htp_context *ctx, struct htp_buf_desc *b) {
for (uint32_t i=0; i < HTP_MAX_MMAPS; i++) {
struct htp_mmap *m = &ctx->mmap[i];
if (!m->size) {
#if __HVX_ARCH__ > 73
void *va = HAP_mmap2(NULL, b->size, HAP_PROT_READ | HAP_PROT_WRITE, 0, b->fd, 0);
#else
if (b->size > HTP_MMAP_MAX_VMEM) { // HAP_mmap has a size limit of 2GB
FARF(ERROR, "mmap failed : size %u exceeds 2GB limit for HAP_mmap", (uint32_t) b->size);
abort(); // can't do much else at this point
}
void *va = HAP_mmap(NULL, b->size, HAP_PROT_READ | HAP_PROT_WRITE, 0, b->fd, 0);
#endif
if (va == (void*)-1) {
FARF(ERROR, "mmap failed : va %p fd %u size %u", va, b->fd, (uint32_t) b->size);
abort(); // can't do much else at this point