kate/BadFish
1
0
Fork 0
mirror of https://github.com/sockspls/badfish synced 2025-07-11 19:49:14 +00:00
Code Issues Releases Wiki Activity

Restrict avx2 hack to windows target

Browse source 
this workaround is possibly rather a windows & gcc specific problem. See e.g.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=54412#c25

on Linux with gcc 8 this patch brings roughly a 8% speedup.
However, probably needs some testing in the wild.

includes a workaround for an old msys make (3.81) installation (fixes #2984)

No functional change
This commit is contained in:
Joost VandeVondele 2020-08-11 21:11:17 +02:00
parent ee06046412
commit 992f549ae7
2 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
src/Makefile
View file

@ -569,7 +569,7 @@ help:
build: config-sanity build: config-sanity
$(MAKE) ARCH=$(ARCH) COMP=$(COMP) all $(MAKE) ARCH=$(ARCH) COMP=$(COMP) all
profile-build: config-sanity objclean profileclean net profile-build: net config-sanity objclean profileclean
@echo "" @echo ""
@echo "Step 1/4. Building instrumented executable ..." @echo "Step 1/4. Building instrumented executable ..."
$(MAKE) ARCH=$(ARCH) COMP=$(COMP) $(profile_make) $(MAKE) ARCH=$(ARCH) COMP=$(COMP) $(profile_make)

4
src/nnue/nnue_common.h
View file

@ -44,7 +44,7 @@
// compiled with older g++ crashes because the output memory is not aligned // compiled with older g++ crashes because the output memory is not aligned
// even though alignas is specified. // even though alignas is specified.
#if defined(USE_AVX2) #if defined(USE_AVX2)
#if defined(__GNUC__ ) && (__GNUC__ < 9) #if defined(__GNUC__ ) && (__GNUC__ < 9) && defined(_WIN32)
#define _mm256_loadA_si256 _mm256_loadu_si256 #define _mm256_loadA_si256 _mm256_loadu_si256
#define _mm256_storeA_si256 _mm256_storeu_si256 #define _mm256_storeA_si256 _mm256_storeu_si256
#else #else
@ -54,7 +54,7 @@
#endif #endif
#if defined(USE_AVX512) #if defined(USE_AVX512)
#if defined(__GNUC__ ) && (__GNUC__ < 9) #if defined(__GNUC__ ) && (__GNUC__ < 9) && defined(_WIN32)
#define _mm512_loadA_si512 _mm512_loadu_si512 #define _mm512_loadA_si512 _mm512_loadu_si512
#define _mm512_storeA_si512 _mm512_storeu_si512 #define _mm512_storeA_si512 _mm512_storeu_si512
#else #else