From WikiChip
Editing x86/amx

Warning: You are not logged in. Your IP address will be publicly visible if you make any edits. If you log in or create an account, your edits will be attributed to your username, along with other benefits.

The edit can be undone. Please check the comparison below to verify that this is what you want to do, and then save the changes below to finish undoing the edit.

This page supports semantic in-text annotations (e.g. "[[Is specified as::World Heritage Site]]") to build structured and queryable content provided by Semantic MediaWiki. For a comprehensive description on how to use annotations or the #ask parser function, please have a look at the getting started, in-text annotation, or inline queries help pages.

Latest revision Your text
Line 1: Line 1:
 
{{x86 title|Advanced Matrix Extension (AMX)}}{{x86 isa main}}
 
{{x86 title|Advanced Matrix Extension (AMX)}}{{x86 isa main}}
'''Advanced Matrix Extension''' ('''AMX''') is an [[x86]] {{x86|extension}} that introduces a matrix register file and new instructions for operating on matrices.
+
'''Advanced Matrix Extension''' ('''AMX''') is an [[x86]] extension that introduces an asynchronous accelerator framework for operating on matrices.
  
 
== Overview ==
 
== Overview ==
[[File:amx architecture.svg|thumb|right|AMX Architecture]]
+
The Advanced Matrix Extension (AMX) is an [[x86]] extension that introduces a new programming framework for working with matrices. AMX introduces two new components - a 2-dimensional register file called 'Tiles' and a set of [[accelerators]] that are able to operate on those tiles.
The Advanced Matrix Extension (AMX) is an [[x86]] extension that introduces a new programming framework for working with matrices (rank-2 tensors). The extensions introduce two new components: a 2-dimensional [[register file]] with registers called 'tiles' and a set of [[accelerators]] that are able to operate on those tiles. The tiles represent a sub-array portion from a large 2-dimensional memory image. AMX instructions are synchronous in the [[instruction stream]] with memory load/store operations by tiles being coherent with the host's memory accesses. AMX instructions may be freely interleaved with traditional x86 code and execute in parallel with other extensions (e.g., [[AVX512]]) with special tile loads and stores and accelerator commands being sent over to the accelerator for execution.
 
 
 
=== Palettes ===
 
Determining the kind of operations available on specific hardware can be done by enumerating a palette of options.
 
 
 
Currently, 2 palettes exist:
 
 
 
* Palette 0 - initialized state
 
* Palette 1 - an 8-tile register file with each register being 16 rows x 64-byte (1 KiB) for a total register file of 8 KiB.
 
 
 
A programmer can configure the size of the register file by configuring tiles of smaller dimensions to suit their algorithm. Tiles may be configured in rows and bytes_per_row which are stored as metadata for the accelerator to operate on. Information pertaining to the palette is stored in a tile control register (TILECFG) and is accessible via the palette_table CPUID leaf 1DH. The TILECFG is programmed using the <code>LDTILECFG </code> instruction.
 
 
 
=== Accelerators ===
 
AMX supports a set of accelerators that can operate on tiles. Currently, just one accelerator is defined.
 
==== Tile matrix multiply unit (TMUL) ====
 
The '''Tile Matrix Multiply''' ('''TMUL''') Unit is an accelerator as part of AMX comprising a grid of fused multiply-add units capable of operating on tiles. Its existence is defined by the ''AMX-INT8'' and ''AMX-BF16'' sub-extensions. The TMUL unit instruction set computes Tile<sub>C</sub>[M][N] += Tile<sub>A</sub>[M][K] * Tile<sub>B</sub>[K][N].
 
 
 
The TMUL unit comes with a number of parameters supported including the maximum height (<code>tmul_maxk</code>) and maximum SIMD dimension (<code>tmul_maxn</code>). Those parameters are dynamically read by the TMUL unit upon execution.
 
 
 
== Instructions ==
 
[[File:amx dot product of tiles.svg|thumb|right|2 x 3 Dot Product]]
 
AMX introduces 12 new instructions:
 
 
 
Configuration:
 
* <code>LDTILECFG</code> - Load tile configuration, loads the tile configuration from the 64-byte memory location specified.
 
* <code>STTILECFG</code> - Store tile configuration, stores the tile configuration in the 64-byte memory location specified.
 
 
 
Data:
 
* <code>TILELOADD</code>/<code>TILELOADDT1</code> - Load tile
 
* <code>TILESTORED</code> - Store tile
 
* <code>TILERELEASE</code> - Release tile, returns TILECFG and TILEDATA to the INIT state
 
* <code>TILEZERO</code> - Zero tile, zeroes the destination tile
 
 
 
Operation:
 
* <code>TDPBF16PS</code> - Perform a dot-product of [[BF16]] tiles and accumulate the result. Packed Single Accumulation.
 
* <code>TDPB[XX]D</code> - Perform a dot-product of [[Int8]] tiles and accumulate the result. Dword Accumulation.
 
** Where ''XX'' can be: ''SU'' = Signed/Unsigned, ''US'' = Unsigned/Signed, ''SS'' = Signed/Signed, and ''UU'' = Unsigned/Unsigned pairs.
 
 
 
=== Feature set ===
 
Not all hardware implementations support all operations. The AMX extension comprises three sub-extensions: '''AMX-TILE''', '''AMX-INT8''', and '''AMX-BF16'''.
 
 
 
{| class="wikitable"
 
|-
 
! rowspan="3" | Instruction !! colspan="3" | Feature Set
 
|-
 
|-
 
! Base || colspan="2" | [[#TMUL|TMUL]]
 
|-
 
! AMX-TILE !! AMX-INT8 !! AMX-BF16
 
|-
 
| <code>LDTILECFG</code> || {{tchk|yes}} || ||
 
|-
 
| <code>STTILECFG</code> || {{tchk|yes}} || ||
 
|-
 
| <code>TILELOADD</code><br><code>TILELOADDT1</code> || {{tchk|yes}} || ||
 
|-
 
| <code>TILESTORED</code> || {{tchk|yes}} || ||
 
|-
 
| <code>TILERELEASE</code> || {{tchk|yes}} || ||
 
|-
 
| <code>TILEZERO</code> || {{tchk|yes}} || ||
 
|-
 
| <code>TDPBSSD</code><br>
 
<code>TDPBSUD</code><br>
 
<code>TDPBUSD</code><br>
 
<code>TDPBUUD</code>
 
| || {{tchk|yes}} ||
 
|-
 
| <code>TDPBF16PS</code> || || || {{tchk|yes}}
 
|}
 
 
 
== Detection ==
 
{| class="wikitable"
 
! colspan="2" | {{x86|CPUID}} !! rowspan="2" | Instruction Set
 
|-
 
! Input !! Output
 
|-
 
| rowspan="3" | EAX=07H, ECX=0 || EDX[bit 22] || AMX-BF16
 
|-
 
| EDX[bit 24] || AMX-TILE
 
|-
 
| EDX[bit 25] || AMX-INT8
 
|}
 
 
 
 
 
== Microarchitecture support ==
 
[[File:intel server roadmap (2020) with amx.png|thumb|right|AMX was first planned for {{intel|Sapphire Rapids|l=arch}}.]]
 
{| class="wikitable"
 
|-
 
! Microarchitecture !! AMX-TILE !! AMX-INT8 !! AMX-BF16
 
|-
 
| {{intel|Sapphire Rapids|l=arch}} || {{tchk|yes}} || {{tchk|yes}} || {{tchk|yes}}
 
|}
 
 
 
== Intrinsic functions ==
 
<source lang=asm>
 
</source>
 
 
 
== Bibliography ==
 
* ''Intel Architecture Instruction Set Extensions and Future Features Programming Reference'', Revision 40. (Ref #319433-040)
 
 
 
[[Category:x86_extensions]]
 

Please note that all contributions to WikiChip may be edited, altered, or removed by other contributors. If you do not want your writing to be edited mercilessly, then do not submit it here.
You are also promising us that you wrote this yourself, or copied it from a public domain or similar free resource (see WikiChip:Copyrights for details). Do not submit copyrighted work without permission!

Cancel | Editing help (opens in new window)