Semiconductor & Computer Engineering
From WikiChip
Difference between revisions of "intel/dl boost"
| Line 1: | Line 1: | ||
{{intel title|DL Boost}} | {{intel title|DL Boost}} | ||
| − | '''DL Boost''' ('''deep learning boost''') is a name used by [[Intel]] to | + | '''DL Boost''' ('''deep learning boost''') is a name used by [[Intel]] to describe a set of [[x86]] technologies designed for the [[acceleration]] of AI workloads, including both inference and training. |
== Overview == | == Overview == | ||
| − | '''DL Boost''' is a term used by [[Intel]] to describe a set of features on their microprocessors designed to accelerate AI workloads. The term was first introduced with {{intel|Cascade Lake|l=arch}}. | + | '''DL Boost''' is a term used by [[Intel]] to describe a set of features on their microprocessors designed to accelerate AI workloads. The term was first introduced with {{intel|Cascade Lake|l=arch}} but has since been extended further with more capabilities in newer microarchitectures. |
| − | * {{x86|AVX512_VNNI|AVX-512 Vector Neural Network Instructions}} (AVX512_VNNI) | + | DL Boost includes the following features: |
| − | * {{x86|AVX512_BF16|AVX-512 BFloat16 Instructions}} (AVX512_BF16) | + | |
| + | * {{x86|AVX512_VNNI|AVX-512 Vector Neural Network Instructions}} (AVX512_VNNI) - an instruction set extension that introduces reduced-precision (8-bit and 16-bit) multiply-accumulate for the acceleration of inference. VNNI was first introduced with {{intel|Cascade Lake|l=arch}} (server) and {{intel|Ice Lake (Client)|Ice Lake|l=arch}} (Client) | ||
| + | * {{x86|AVX512_BF16|AVX-512 BFloat16 Instructions}} (AVX512_BF16) - an instruction set extension for converting to [[bfloat16]] and then performing multiply-accumulate on such values for the acceleration of both inference and training. BG16 was first introduced with {{intel|Cooper Lake|l=arch}}. | ||
== Implementations == | == Implementations == | ||
Revision as of 23:36, 24 June 2020
DL Boost (deep learning boost) is a name used by Intel to describe a set of x86 technologies designed for the acceleration of AI workloads, including both inference and training.
Overview
DL Boost is a term used by Intel to describe a set of features on their microprocessors designed to accelerate AI workloads. The term was first introduced with Cascade Lake but has since been extended further with more capabilities in newer microarchitectures.
DL Boost includes the following features:
- AVX-512 Vector Neural Network Instructions (AVX512_VNNI) - an instruction set extension that introduces reduced-precision (8-bit and 16-bit) multiply-accumulate for the acceleration of inference. VNNI was first introduced with Cascade Lake (server) and Ice Lake (Client)
- AVX-512 BFloat16 Instructions (AVX512_BF16) - an instruction set extension for converting to bfloat16 and then performing multiply-accumulate on such values for the acceleration of both inference and training. BG16 was first introduced with Cooper Lake.
Implementations
| Microarchitecture | AVX512_VNNI | AVX512_BF16 |
|---|---|---|
| Client | ||
| Ice Lake (Client) | ✔ | ✘ |
| Server | ||
| Cascade Lake | ✔ | ✘ |
| Cooper Lake | ✔ | ✔ |
| Ice Lake (Server) | ✔ | ✘ |
| Sapphire Rapids | ✔ | ✔ |
| Granite Rapids | TBD | TBD |
