News
IndustryTSMC’s grip on advanced chipmaking will face competitionIndustryCadence joins European Chip Design Platform to support semiconductor startups and SMEsMaking chipsMarc Hijink on ASML’s Culture, Supply Chain, and GeopoliticsProcessorsIntel's post-Nova Lake CPUs take shape as Razor Lake desktop and laptop variants surfaceAI chipsHow Google’s New AI Chip Software Helps It Battle NvidiaIndiaMore IC Packaging Plants Emerge In IndiaIndustryUS Tightens China AI Chip Access as Nvidia, TSMC and Semiconductor Stocks SlideDesignAxelera AI moves into HPC with TitaniaMaking chipsChinese envoy says chip equipment export curbs threaten EU-China trade thawIndiaSEMICON India 2026 Day 2 Sees 25 MoUs, Strategic Collaborations Across Semiconductor Value ChainIndustryTSMC’s grip on advanced chipmaking will face competitionIndustryCadence joins European Chip Design Platform to support semiconductor startups and SMEsMaking chipsMarc Hijink on ASML’s Culture, Supply Chain, and GeopoliticsProcessorsIntel's post-Nova Lake CPUs take shape as Razor Lake desktop and laptop variants surfaceAI chipsHow Google’s New AI Chip Software Helps It Battle NvidiaIndiaMore IC Packaging Plants Emerge In IndiaIndustryUS Tightens China AI Chip Access as Nvidia, TSMC and Semiconductor Stocks SlideDesignAxelera AI moves into HPC with TitaniaMaking chipsChinese envoy says chip equipment export curbs threaten EU-China trade thawIndiaSEMICON India 2026 Day 2 Sees 25 MoUs, Strategic Collaborations Across Semiconductor Value Chain
EveryChip

SIMD

Single instruction, multiple data: one instruction that does the same operation on many numbers at once, used for graphics, media and AI.

Also: single instruction, multiple data, vector instructions, SSE, AVX, NEON

With SIMD, one instruction might add eight pairs of numbers held in a wide register in one go, instead of looping eight times. Vector supercomputers such as the Cray-1 of 1976 used a related idea. On PCs, Intel added MMX in 1997, SSE in 1999 and AVX in 2011, with AVX-512 registers 512 bits wide; Arm has NEON and the scalable SVE, and RISC-V has its vector extension. GPUs take the idea further, running one instruction across many threads in step, an approach Nvidia calls SIMT.

See also

Find chips that mention SIMD

The weekly digest

Every Monday: the chip of the day, new pages on EveryChip, and the conferences and anniversaries of the week ahead.