Stockfish 13 merged on github
Moderators: hgm, Rebel, chrisw
-
Stonker
- Posts: 16
- Joined: Sun Jun 30, 2019 11:20 pm
- Full name: Michael Woolley
Re: Stockfish 13 merged on github
What a lengthy process to get to a simple yet clear result as requested. Thank you for your continued (continuing?) efforts on cpu.exe. Just tried the latest, out of curiosity but my Norton immediately vomited it back up. I know: Norton is rubbish etc etc. Oh dear... Thankfully Stockfish is presumably as superb as ever. Back to the hobby. Many cheers.
-
Ferdy
- Posts: 4833
- Joined: Sun Aug 10, 2008 3:15 pm
- Location: Philippines
-
MikeB
- Posts: 4889
- Joined: Thu Mar 09, 2006 6:34 am
- Location: Pen Argyl, Pennsylvania
Re: Stockfish 13 merged on github
If you have msys2 installed on Windows, run this on msys2 terminal windows:
cat /proc/cpuinfo
processor : 63
vendor_id : AuthenticAMD
cpu family : 23
model : 49
model name : AMD Ryzen Threadripper 3970X 32-Core Processor
stepping : 0
microcode : 0x8301039
cpu MHz : 3700.000
cache size : 131072 KB
physical id : 0
siblings : 64
core id : 31
cpu cores : 64
apicid : 63
initial apicid : 63
fpu : yes
fpu_exception : yes
cpuid level : 26
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmuldq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate sme ssbd mba sev ibpb stibp fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decode_assists pausefilter pfthreshold avic v_vmsave_vmload vgif overflow_recov succor smca
bogomips : 7400.00
TLB size : 3072 4K pages
clflush size : 64
cache_alignment : 64
address sizes : 48 bits physical, 48 bits virtual
power management: ts ttp tm hwpstate cpb eff_freq_ro
Now for me, I would never use a bmi2 compiled unless I was forced to (Threadripper )
generally speaking, you want to use the exe that has the more recent compiler options and still runs on your machine. The simple method is downloaead each exe and type "bench" on the command line after starting the exe and picking the exe with fastest bench. Make a note of which one that was , as that will generally be the fastest one for you going forward until you upgrade your CPU or computer.
A difference of 1 or 2 % is not relevant to most users ( excluding the programmers)
cat /proc/cpuinfo
processor : 63
vendor_id : AuthenticAMD
cpu family : 23
model : 49
model name : AMD Ryzen Threadripper 3970X 32-Core Processor
stepping : 0
microcode : 0x8301039
cpu MHz : 3700.000
cache size : 131072 KB
physical id : 0
siblings : 64
core id : 31
cpu cores : 64
apicid : 63
initial apicid : 63
fpu : yes
fpu_exception : yes
cpuid level : 26
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmuldq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate sme ssbd mba sev ibpb stibp fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decode_assists pausefilter pfthreshold avic v_vmsave_vmload vgif overflow_recov succor smca
bogomips : 7400.00
TLB size : 3072 4K pages
clflush size : 64
cache_alignment : 64
address sizes : 48 bits physical, 48 bits virtual
power management: ts ttp tm hwpstate cpb eff_freq_ro
Now for me, I would never use a bmi2 compiled unless I was forced to (Threadripper )
generally speaking, you want to use the exe that has the more recent compiler options and still runs on your machine. The simple method is downloaead each exe and type "bench" on the command line after starting the exe and picking the exe with fastest bench. Make a note of which one that was , as that will generally be the fastest one for you going forward until you upgrade your CPU or computer.
A difference of 1 or 2 % is not relevant to most users ( excluding the programmers)
