(→Members) |
(→HL-1000) |
||
Line 24: | Line 24: | ||
=== Inference === | === Inference === | ||
==== HL-1000 ==== | ==== HL-1000 ==== | ||
− | {{main|habana/microarchitectures/goya|l1=Goya}}[[File: | + | {{main|habana/microarchitectures/goya|l1=Goya}}[[File:habana hl-100.jpg|right|thumb|HL-100/102 PCIe Card]] |
The '''HL-1000''' is a first-generation [[neural processor]] for inference. The HL-1000 is fabricated on [[TSMC]] [[16-nanometer]] process based on the {{habana|Goya|l=arch}} microarchitecture. This chip ships in a number of products in a [[PCIe cards]] form factor. | The '''HL-1000''' is a first-generation [[neural processor]] for inference. The HL-1000 is fabricated on [[TSMC]] [[16-nanometer]] process based on the {{habana|Goya|l=arch}} microarchitecture. This chip ships in a number of products in a [[PCIe cards]] form factor. | ||
Line 30: | Line 30: | ||
* '''Mem''' Dual-channel DDR4-2667 | * '''Mem''' Dual-channel DDR4-2667 | ||
* '''I/O''' x16 PCIe Gen 4.0 | * '''I/O''' x16 PCIe Gen 4.0 | ||
+ | * '''TDP''' 200 W | ||
+ | |||
{| class="wikitable | {| class="wikitable | ||
Line 39: | Line 41: | ||
| '''HL-102''' || 200 W || 4/8/16 GiB || PCIe Card; Dual-slot, active cooling | | '''HL-102''' || 200 W || 4/8/16 GiB || PCIe Card; Dual-slot, active cooling | ||
|} | |} | ||
+ | |||
=== Training === | === Training === | ||
==== HL-2000 ==== | ==== HL-2000 ==== |
Revision as of 03:02, 15 December 2019
HL Series | |
Developer | Habana |
Manufacturer | TSMC |
Type | NPU |
Introduction | 2017 (announced) 2018 (launch) |
µarch | Goya, Gaudi |
Process | 16 nm 0.016 μm
1.6e-5 mm |
Technology | CMOS |
HL-x is a series of neural processors designed by Habana for the data center market.
Overview
HL-x is a series of neural processors designed by Habana for both training and inference in the data center. There are two distinct products based on two separate microarchitectures - one for inference and one for training. Both designs share common unified architecture, simplifying software development.
Members
Inference
HL-1000
- Main article: Goya
The HL-1000 is a first-generation neural processor for inference. The HL-1000 is fabricated on TSMC 16-nanometer process based on the Goya microarchitecture. This chip ships in a number of products in a PCIe cards form factor.
- Proc 16 nm
- Mem Dual-channel DDR4-2667
- I/O x16 PCIe Gen 4.0
- TDP 200 W
Model | TDP | Memory | Type |
---|---|---|---|
HL-100 | 200 W | 4/8/16 GiB | PCIe Card; Dual-slot, passive cooling |
HL-102 | 200 W | 4/8/16 GiB | PCIe Card; Dual-slot, active cooling |
Training
HL-2000
- Main article: Gaudi
The HL-2000 is a first-generation neural processor for training. The HL-1000 is fabricated on TSMC 16-nanometer process based on the Gaudi microarchitecture. This chip ships in a number of products in both a PCIe card and an OCP OAM form factors.
Model | TDP | Memory | Scale-Out | Type |
---|---|---|---|---|
HL-200 | 200 W | 32 GiB | 8x100 GbE | PCIe Card; passive cooling |
HL-202 | 200 W | 32 GiB | 8x100 GbE | PCIe Card; active cooling |
HL-205 | 300 W | 32 GiB | 10x100 GbE | OCP-OAM |
See also
designer | Habana + |
first announced | 2017 + |
first launched | 2018 + |
full page name | habana/hl + |
instance of | integrated circuit family + |
main designer | Habana + |
manufacturer | TSMC + |
microarchitecture | Goya + and Gaudi + |
name | HL Series + |
process | 16 nm (0.016 μm, 1.6e-5 mm) + |
technology | CMOS + |