]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
ggml-cpu: add always_inline to tinyBLAS_PPC accumulator saves (llama/20791)
authorshalinib-ibm <redacted>
Fri, 20 Mar 2026 23:11:45 +0000 (04:41 +0530)
committerGeorgi Gerganov <redacted>
Sun, 29 Mar 2026 12:04:36 +0000 (15:04 +0300)
commitca5d565dcdb677bad03f719b7c85bf5939f18e39
tree468dd8d86309a4b7761247f7bfd35003850ce092
parent49b505bcc5c76b30584a26fcc2d1d6751bcc986c
ggml-cpu: add always_inline to tinyBLAS_PPC accumulator saves (llama/20791)

Explicitly mark save_acc and add_save_Acc with always_inline
in tinyBLAS_PPC. This ensures the compiler keeps MMA accumulator
disassembly within kernel's register context, preventing un-necessary
stask spills.

Signed-off-by: Shalini Salomi Bodapati <redacted>
ggml/src/ggml-cpu/llamafile/sgemm.cpp