url/colibri
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #444 from cdhdt/perf/idot-avxvnni-accumulators

Browse Source 
idot: independent accumulators on the AVX-VNNI int8/int4 dot kernels (x86 parity with the NEON path)
This commit is contained in:
Vincenzo Fornaro
2026-07-20 18:11:09 +02:00
committed by GitHub
parent 73badea697 c4b2cf6db0
commit 04ed0049a4
3 changed files with 138 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
c/Makefile
+5
View File
@@ -360,6 +360,11 @@ tests/test_dsa_select$(EXE): tests/test_dsa_select.c colibri.c st.h uring.h json
tests/bench_dsa_select$(EXE): tests/bench_dsa_select.c colibri.c st.h uring.h json.h tok.h tok_unicode.h compat.h grammar.h tier.h quant.h sample.h kv_persist.h telemetry.h
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
# bench_idot: microbenchmark (single-acc vs independent-acc AVX-VNNI idot), NOT a test gate.
# Build on demand on an AVX-VNNI CPU: make tests/bench_idot ARCH=native
tests/bench_idot$(EXE): tests/bench_idot.c colibri.c st.h uring.h json.h tok.h tok_unicode.h compat.h grammar.h tier.h quant.h sample.h kv_persist.h telemetry.h
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
tests/test_uring$(EXE): tests/test_uring.c colibri.c st.h uring.h json.h tok.h tok_unicode.h compat.h grammar.h tier.h quant.h sample.h kv_persist.h telemetry.h
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)