Dav1d 0.9.2 Released With More SSSE3, SSE4, AVX2, NEON Optimizations

[phoronix]

Phoronix: Dav1d 0.9.2 Released With More SSSE3, SSE4, AVX2, NEON Optimizations

Released at the start of August was dav1d 0.9.1 for this high performance CPU-based AV1 open-source video decoder while now another point release is available with yet more optimizations...

https://www.phoronix.com/scan.php?page=news_item&px=dav1d-0.9.2

[SteamPunker]

Thanks for benchmarking this!

Michael, would it be an interesting idea to include AWS Graviton2 EC2 instances in benchmarks like these, to test the ARM-specific optimizations such as NEON?

[Michael]

Thanks for benchmarking this!

Michael, would it be an interesting idea to include AWS Graviton2 EC2 instances in benchmarks like these, to test the ARM-specific optimizations such as NEON?

I included Ampere Altra... No plans to regularly include Graviton2 due to costs.

[SteamPunker]

Good point. Those sufficiently interested in such stats should sponsor you for it.

[schmidtbag]

I think it'd be most helpful to see benchmarks of low-end CPUs, as they're really the reason why these optimizations are necessary in the first place.

[MadeUpName]

I think it'd be most helpful to see benchmarks of low-end CPUs, as they're really the reason why these optimizations are necessary in the first place.

Low end CPUs won't have extensions like AVX2.

[brad0]

Low end CPUs won't have extensions like AVX2.

Every X86 CPU in the last 18 years has.

[MadeUpName]

Every X86 CPU in the last 18 years has.

Release date Q3 2016. No AVX.

processor : 3
vendor_id : GenuineIntel
cpu family : 6
model : 76
model name : Intel(R) Celeron(R) CPU N3160 @ 1.60GHz
stepping : 4
microcode : 0x411
cpu MHz : 514.521
cache size : 1024 KB
physical id : 0
siblings : 4
core id : 3
cpu cores : 4
apicid : 6
initial apicid : 6
fpu : yes
fpu_exception : yes
cpuid level : 11
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx e
st tm2 ssse3 cx16 xtpr pdcm sse4_1 sse4_2 movbe popcnt tsc_deadline_timer aes rdrand lahf_lm 3dnowprefetch epb pti ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid tsc_adjust smep erms dtherm ida arat md_clear
vmx flags : vnmi preemption_timer invvpid ept_x_only flexpriority tsc_offset vtpr mtf vapic ept vpid unrestricted_guest
bugs : cpu_meltdown spectre_v1 spectre_v2 mds msbds_only
bogomips : 3200.00
clflush size : 64
cache_alignment : 64
address sizes : 36 bits physical, 48 bits virtual
power management:

[brad0]

Release date Q3 2016. No AVX.

*facepalm* Has SSSE3 and SSE4. Come on keep up.

[brad0]

I think it'd be most helpful to see benchmarks of low-end CPUs, as they're really the reason why these optimizations are necessary in the first place.

That's a weird assumption.