Intel AVX2

E165095

SIMD instruction set instruction set extension x86 extension

Intel AVX2 is an x86 instruction set extension from Intel that enhances performance for integer-heavy and vectorized workloads through wider SIMD operations and new vector instructions.

Try in SPARQL Jump to: Surface forms Statements Referenced by

All labels observed (4)

Label	Occurrences
Intel AVX2 canonical	3
AVX2	2
Intel AVX2 instruction set	1
Intel Advanced Vector Extensions	1

Statements (47)

Predicate	Object
instanceOf	SIMD instruction set ⓘ instruction set extension ⓘ x86 extension ⓘ
alsoImplementedBy	AMD processors ⓘ
architecture	x86 ⓘ x86-64 ⓘ
availableOn	many Intel Core processors ⓘ many Intel Xeon processors ⓘ
backwardCompatibleWith	Intel AVX ⓘ
dataTypeSupport	double-precision floating-point vectors ⓘ integer vectors ⓘ single-precision floating-point vectors ⓘ
definedIn	Intel Architecture Software Developer’s Manual ⓘ surface form: Intel 64 and IA-32 Architectures Software Developer’s Manual
developer	Intel Corporation ⓘ surface form: Intel
extends	Intel AVX ⓘ surface form: Intel AVX 256-bit SIMD model
featureFlag	AVX2 CPUID bit ⓘ
firstSupportedBy	Intel Haswell microarchitecture ⓘ
follows	Intel AVX ⓘ
improvesPerformanceFor	cryptographic workloads ⓘ image processing applications ⓘ integer-heavy workloads ⓘ media encoding and decoding ⓘ scientific computing workloads ⓘ signal processing applications ⓘ vectorized workloads ⓘ
introducedIn	2013 ⓘ
partOf	Intel AVX2 self-linksurface differs ⓘ surface form: Intel Advanced Vector Extensions
precedes	AVX-512 ⓘ surface form: Intel AVX-512
registerWidth	256 bits ⓘ
requires	XSAVE/XRESTORE support for extended registers ⓘ operating system support for YMM state saving ⓘ
standardizedAs	part of x86-64 ISA extensions ⓘ
supports	256-bit integer SIMD operations ⓘ 256-bit vector integer arithmetic ⓘ Fused Multiply-Add via FMA3 (with separate feature flag) ⓘ gather instructions ⓘ mask-based operations ⓘ vector bitwise operations ⓘ vector blend instructions ⓘ vector compare instructions ⓘ vector insert and extract instructions ⓘ vector integer multiply instructions ⓘ vector permute instructions ⓘ vector shift instructions ⓘ
targetDomain	data-parallel applications ⓘ high-performance computing ⓘ
usesRegisterFile	YMM registers ⓘ

Referenced by (7)

Full triples — surface form annotated when it differs from this entity's canonical label.

Intel Xeon → supportsFeature → Intel AVX2 ⓘ

Intel AVX2 → partOf → Intel AVX2 self-linksurface differs ⓘ

this entity surface form: Intel Advanced Vector Extensions

Intel processors → supportsInstructionSet → Intel AVX2 ⓘ

this entity surface form: AVX2

Gracemont → supportsInstructionSetExtension → Intel AVX2 ⓘ

this entity surface form: AVX2

Intel AVX → successor → Intel AVX2 ⓘ

Intel AVX → relatedStandard → Intel AVX2 ⓘ

Intel Fortran Compiler → optimizedFor → Intel AVX2 ⓘ

this entity surface form: Intel AVX2 instruction set