Pranav DhinakarandMax Krasnyansky b46812de78 Feature hexagon l2 norm (#22816) ...

* L2_NORM Updates

* Addressed PR Comments

* ggml-hexagon: add L2_NORM HVX kernel for Hexagon backend

* hex-unary: remove supported_unary_nc since the outer loop is the same for all unary ops

---------

Co-authored-by: Max Krasnyansky <maxk@qti.qualcomm.com>

2026-05-08 13:41:40 -07:00

..

act-ops.c

hexagon: improved Op queuing, buffer and cache management (#21705)

2026-04-10 15:47:43 -07:00

argsort-ops.c

hexagon: improved Op queuing, buffer and cache management (#21705)

2026-04-10 15:47:43 -07:00

binary-ops.c

hexagon: improved Op queuing, buffer and cache management (#21705)

2026-04-10 15:47:43 -07:00

cmake-toolchain.cmake

hexagon: hmx flash attention (#22347)

2026-05-01 20:29:13 -07:00

CMakeLists.txt

hexagon: hmx flash attention (#22347)

2026-05-01 20:29:13 -07:00

cpy-ops.c

hexagon: improved Op queuing, buffer and cache management (#21705)

2026-04-10 15:47:43 -07:00

cumsum-ops.c

hexagon: improved Op queuing, buffer and cache management (#21705)

2026-04-10 15:47:43 -07:00

diag-ops.c

Hexagon: DAIG op (#22195)

2026-04-21 14:16:04 -07:00

fill-ops.c

hexagon: add support for FILL op (#22198)

2026-04-21 16:24:20 -07:00

flash-attn-ops.c

hexagon: hmx flash attention (#22347)

2026-05-01 20:29:13 -07:00

get-rows-ops.c

hexagon: improved Op queuing, buffer and cache management (#21705)

2026-04-10 15:47:43 -07:00

hex-dma.c

hexagon: general DMA and Binary Op fixes for large strides (#20918)

2026-03-23 15:33:49 -07:00

hex-dma.h

hexagon: dma optimizations (mostly fixing regressions) (#21137)

2026-03-29 06:40:13 -07:00

hex-dump.h

hexagon: general DMA and Binary Op fixes for large strides (#20918)

2026-03-23 15:33:49 -07:00

hex-fastdiv.h

hexagon: support for OP_CPY, host buffers now optional, hvx-utils refactoring and optimizations (#18822)

2026-01-14 21:46:12 -08:00

hex-utils.h

hexagon: hmx flash attention (#22347)

2026-05-01 20:29:13 -07:00

hmx-flash-attn-ops.c

hexagon: hmx flash attention (#22347)

2026-05-01 20:29:13 -07:00

hmx-matmul-ops.c

Hexagon: Process M-tail rows on HMX instead of HVX (#22724)

2026-05-05 09:43:03 -07:00

hmx-ops.h

hexagon: hmx flash attention (#22347)

2026-05-01 20:29:13 -07:00

hmx-profile.h

hexagon: add Matrix Extensions (HMX) for Hexagon NPU backend (#20693)

2026-03-19 09:11:06 -07:00

hmx-queue.c

hexagon: optimization for HMX mat_mul (#21554)

2026-04-14 14:09:03 -07:00

hmx-queue.h

hexagon: optimization for HMX mat_mul (#21554)

2026-04-14 14:09:03 -07:00

hmx-utils.h

hexagon: hmx flash attention (#22347)

2026-05-01 20:29:13 -07:00

htp_iface.idl

hexagon: make vmem and buffer-size configurable (#22487)

2026-04-29 11:51:21 -07:00

htp-ctx.h

hexagon: make vmem and buffer-size configurable (#22487)

2026-04-29 11:51:21 -07:00

htp-ops.h

Feature hexagon l2 norm (#22816)

2026-05-08 13:41:40 -07:00

hvx-arith.h

hexagon: add fp16 support for binary ops: add,sub,mul,div (#20139)

2026-03-05 18:29:13 -08:00

hvx-base.h

hexagon: hmx flash attention (#22347)

2026-05-01 20:29:13 -07:00

hvx-copy.h

hexagon: hmx flash attention (#22347)

2026-05-01 20:29:13 -07:00

hvx-div.h

hexagon: improve RMS_NORM and DIV accuracy (#21251)

2026-04-01 08:43:08 -07:00

hvx-dump.h

ggml-hexagon: flash-attention and reduce-sum optimizations (#19141)

2026-01-30 21:14:20 -08:00

hvx-exp.h

hexagon: enable non-contiguous row tensor support for unary ops (#22574)

2026-05-01 10:09:23 -07:00

hvx-floor.h

hexagon: support for OP_CPY, host buffers now optional, hvx-utils refactoring and optimizations (#18822)

2026-01-14 21:46:12 -08:00

hvx-inverse.h

hexagon: add fp16 support for binary ops: add,sub,mul,div (#20139)

2026-03-05 18:29:13 -08:00

hvx-reduce.h

hexagon: Flash Attention optimizations (dma, mpyacc, multi-row) and MatMul updates (#20118)

2026-03-04 21:55:29 -08:00

hvx-scale.h

hexagon: support for OP_CPY, host buffers now optional, hvx-utils refactoring and optimizations (#18822)

2026-01-14 21:46:12 -08:00

hvx-sigmoid.h

hexagon: add neg, exp, sigmoid, softplus ops, cont, repeat ops (#20701)

2026-03-17 15:34:36 -07:00

hvx-sqrt.h

hexagon: Add ARGSORT, DIV, SQR, SQRT, SUM_ROWS, GEGLU (#19406)

2026-02-10 23:21:12 -08:00

hvx-types.h

hexagon: support for OP_CPY, host buffers now optional, hvx-utils refactoring and optimizations (#18822)

2026-01-14 21:46:12 -08:00

hvx-utils.h

hexagon: general DMA and Binary Op fixes for large strides (#20918)

2026-03-23 15:33:49 -07:00

main.c

Feature hexagon l2 norm (#22816)

2026-05-08 13:41:40 -07:00

matmul-ops.c

Hexagon: Process M-tail rows on HMX instead of HVX (#22724)

2026-05-05 09:43:03 -07:00

repeat-ops.c

hexagon: improved Op queuing, buffer and cache management (#21705)

2026-04-10 15:47:43 -07:00

rope-ops.c

hexagon: improved Op queuing, buffer and cache management (#21705)

2026-04-10 15:47:43 -07:00

set-rows-ops.c

hexagon: improved Op queuing, buffer and cache management (#21705)

2026-04-10 15:47:43 -07:00

softmax-ops.c

hexagon: improved Op queuing, buffer and cache management (#21705)

2026-04-10 15:47:43 -07:00

solve-tri-ops.c

hexagon: add SOLVE_TRI op (#21974)

2026-04-23 18:39:13 -07:00

ssm-conv.c

hexagon: improved Op queuing, buffer and cache management (#21705)

2026-04-10 15:47:43 -07:00

sum-rows-ops.c

hexagon: improved Op queuing, buffer and cache management (#21705)

2026-04-10 15:47:43 -07:00

unary-ops.c

Feature hexagon l2 norm (#22816)

2026-05-08 13:41:40 -07:00

vtcm-utils.h

hexagon: hmx flash attention (#22347)

2026-05-01 20:29:13 -07:00

worker-pool.c

chore : correct typos [no ci] (#20041)

2026-03-05 08:50:21 +01:00

worker-pool.h

Add experimental ggml-hexagon backend for the Hexagon NPU (#16547)

2025-10-22 13:47:09 -07:00