Qeravio
Canonical AI event

spacemit fixes int16 data transpose bug in permute_transpose_impl

The bug caused 14 out of 16 positions to be corrupted in a 4x4 int16 matrix. The fix uses the correct function already present in the codebase.

16 Sept 20261 verified claims1 sources1 observations
What happened

The official source reports this update: b11001: spacemit : fix wrong transpose function for int16 data. spacemit : fix wrong transpose function for int16 data ( #25161 ) The sizeof(int16_t) branch in permute_transpose_impl calls rvv_transposed_s32_mn_to_nm instead of rvv_transposed_s16_mn_to_nm . This is a copy-paste bug from the sizeof(int32_t) branch above it. The s32 function uses 32-bit segment load/stores ( vssseg8e32.v ) on 16-bit data, reading 2x bytes per element and producing completely wrong transposition results -- 14 out of 16 positions are corrupted for a 4x4 int16 matrix.

Why it matters

This official update documents a development concerning b11001: spacemit : fix wrong transpose function for int16 data. Its practical significance depends on the scope and evidence stated by the source.

What to watch next

Read the official source update and verify its stated scope, evidence and timing before acting on it.

Connected knowledge

Entities affected by this event

Continue this topic
Evidence trail

Sources behind the event