Template:AMD Radeon Instinct
Jump to navigation
Jump to search
Model (codename) |
Release Date | Architecture & Fab |
Transistors & Die Size |
Core | Fillrate[lower-alpha 1][lower-alpha 2][lower-alpha 3] | Processing power[lower-alpha 1][lower-alpha 4] (GFLOPS) |
Memory | TBP | Bus interface | |||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Config[lower-alpha 5] | Clock[lower-alpha 1] (MHz) | Texture (GT/s) |
Pixel (GP/s) |
Half | Single | Double | Bus type & width |
Size (GiB) |
Clock (MT/s) |
Bandwidth (GB/s) | ||||||
Template:Rh | Radeon Instinct MI6 (Polaris 10) [1][2][3][4][5] |
December 2016 | GCN 4th gen 14 nm |
Template:Val 232 mm2 |
2304:144:32 36 CU |
1120 1233 |
177.6 | 39.46 | 5800 | 5800 | 358 | GDDR5 256-bit |
16 | 7000 | 224 | 150 W | PCIe 3.0 x16 |
Template:Rh | Radeon Instinct MI8 (Fiji XT) [1][2][3][6][7] |
GCN 3rd gen 28 nm |
Template:Val 596 mm2 |
4096:256:64 64 CU |
1000 | 256.0 | 64.0 | 8200 | 8200 | 512 | HBM 4096-bit |
4 | 1000 | 512 | 175 W | ||
Template:Rh | Radeon Instinct MI25 (Vega 10 XT)[1][2][3][8][9][10] |
GCN 5th gen 14 nm |
Template:Val 510 mm2 |
4096:256:64 64 CU |
1400 1500 |
384 | 96.0 | 24600 | 12300 | 768 | HBM2 2048-bit |
16 | 1704 | 436.2 | 300 W | ||
Template:Rh | Radeon Instinct MI25 mxgpu (Prototype, June 2017)[11] |
Unreleased | 2× Template:Val 510 mm2 |
2× 4096:256:64 64 CU |
1400 1500 |
2× 384 |
2× 96.0 |
2× 24600 |
2× 12300 |
2× 768 |
2× 16 |
2× 436.2 |
300 W | ||||
Template:Rh | Radeon Instinct MI50 (Vega 20 GL)[12][13][14][15] |
November 2018 | GCN 5th gen 7 nm |
Template:Val 331 mm2 |
3840:240:- 60 CU |
1450 1746 |
419.04 | - | 26800 | 13400 | 6700 | HBM2 4096-bit |
16 | 2000 | 1024 | 300 W | PCIe 4.0 x16 |
Template:Rh | Radeon Instinct MI60 (Vega 20 GL)[12][16][17] |
4096:256:- 64 CU |
1500 1800 |
460.8 | - | 29450 | 14725 | 7362.5 | 32 | 1024 | 300 W |
- ↑ 1.0 1.1 1.2 Boost values (if available) are stated below the base value in italic.
- ↑ Texture fillrate is calculated as the number of texture mapping units multiplied by the base (or boost) core clock speed.
- ↑ Pixel fillrate is calculated as the number of render output units multiplied by the base (or boost) core clock speed.
- ↑ Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
- ↑ Unified Shaders : Texture Mapping Units : Render Output Units and Compute Units (CU)
References
- ↑ 1.0 1.1 1.2 Smith, Ryan (12 December 2016). "AMD Announces Radeon Instinct: GPU Accelerators for Deep Learning, Coming in 2017". Anandtech. Retrieved 12 December 2016.
- ↑ 2.0 2.1 2.2 Shrout, Ryan (12 December 2016). "Radeon Instinct Machine Learning GPUs include Vega, Preview Performance". PC Per. Retrieved 12 December 2016.
- ↑ 3.0 3.1 3.2 Kampman, Jeff (12 December 2016). "AMD opens up machine learning with Radeon Instinct". TechReport. Retrieved 12 December 2016.
- ↑ "Radeon Instinct MI6". Radeon Instinct. AMD. Retrieved 22 June 2017.
- ↑ "AMD Radeon Instinct MI6 Specs". TechPowerUp.
- ↑ "Radeon Instinct MI8". Radeon Instinct. AMD. Retrieved 22 June 2017.
- ↑ "AMD Radeon Instinct MI8 Specs". TechPowerUp.
- ↑ Smith, Ryan (5 January 2017). "The AMD Vega Architecture Teaser: Higher IPC, Tiling, & More, coming in H1'2017". Anandtech.com. Retrieved 10 January 2017.
- ↑ "Radeon Instinct MI25". Radeon Instinct. AMD. Retrieved 22 June 2017.
- ↑ "AMD Radeon Instinct MI25 Specs". TechPowerUp.
- ↑ "AMD Radeon Instinct MI25 MxGPU Specs". TechPowerUp.
- ↑ 12.0 12.1 "Next Horizon – David Wang Presentation" (PDF). AMD. AMD.
- ↑ "Radeon Instinct MI50". AMD. AMD.
- ↑ "Radeon Instinct MI50 Datasheet" (PDF). AMD. AMD.
- ↑ "Hands on with the AMD Radeon VII". PC Gamer. Jarred Walton.
- ↑ "Radeon Instinct MI60". AMD. AMD.
- ↑ "Radeon Instinct MI60 Datasheet" (PDF). AMD. AMD.