#Intel refreshed the #AVX10_2 specification to 6.0:
cdrdv2-public.intel.com/913918/36105...
#AVX10_VNNI_INT renamed to #AVX10_V1_AUX
5
0
0
0
Hashtag
#AVX10_VNNI_INT
Advertisement · 728 × 90
#AVX_VNNI_INT16 & #AVX10_VNNI_INT enable full 10-digit ASCII->int conversion (0000000000–9999999999) using only two multiplication stages, since 10^n=2^n·5^n and 2^n is just shifts. Non-AI human code
#ArrowLake #LionCove #Skymont
#PantherLake #CougarCove #Darkmont
#NovaLake #PantherCove #ArcticWolf
5
0
0
0
The Netwide Assembler 3.01 is ready and supports the full #DiamondRapids and #NovaLake instruction sets:
nasm.us
#AVX10_2 #AVX10_VNNI_INT #APX #AMX_FP8 #AMX_TF32 #AMX_COMPLEX #AMX_AVX512 #AMX_MOVRS
0
0
0
0
#VisualStudio2026 18.0.0 Insider implements the so far missing #AVX10_VNNI_INT instructions too.
#DiamondRapids #NovaLake
1
0
0
1
#Intel refreshed the #AVX10_2 specification to 5.0:
cdrdv2-public.intel.com/856721/36105...
VDPPHPS is not #AVX10_VNNI_INT, it's much more logical
1
1
0
1
#Intel #DiamondRapids new vector instructions:
#AVX10_2 #AVX10_VNNI_INT
#MOVRS #SM4 #AMX_TRANSPOSE
#AMX_AVX512 #AMX_FP8 #AMX_MOVRS #AMX_TF32
3
1
0
1
#Intel refreshed the #AVX10_2 specification to 4.0:
cdrdv2-public.intel.com/855340/36105...
CPUID.24h.ECX=1.ECX[2] = AVX10_VNNI_INT
#MOVRS #SM4 #AMX_AVX512 #AVX10_VNNI_INT are decoupled from AVX10.2
2
3
1
1