The official source reports this update: b10687: opencl: use a better matmul path on two Adreno GPU generations. opencl: use a better matmul path on two Adreno GPU generations ( #27640 ) opencl: default the Adreno xmem F16xF32 GEMM on for X2E kernel_mul_mm_f16_f32_l4_lm is the slowest matmul this backend has on Adreno: on the X2-90 it runs the gpt-oss-20b attention projections at roughly a quarter of what the tuned dense q4_0 GEMM reaches on the same device. That matters for any model whose non-expert weights stay f16 -- the stock gpt-oss-20b release is exactly that, and its prefill spends 40.8% of GPU time in that one kernel.
Canonical AI event
Adreno GPU generations see improved matrix multiplication performance.
The Adreno X2-90 GPU's gpt-oss-20b attention projections run 25% faster with the new OpenCL path.
29 Aug 20261 verified claims1 sources1 observations
This official update documents a development concerning b10687: opencl: use a better matmul path on two Adreno GPU generations. Its practical significance depends on the scope and evidence stated by the source.
Read the official source update and verify its stated scope, evidence and timing before acting on it.
Connected knowledge
Entities affected by this event
Evidence trail
Sources behind the event
Editorial presentation
Open story