-
WikiChip
WikiChip
-
Architectures
Popular x86
-
Intel
- Client
- Server
- Big Cores
- Small Cores
-
AMD
Popular ARM
-
ARM
- Server
- Big
- Little
-
Cavium
-
Samsung
-
-
Chips
Popular Families
-
Ampere
-
Apple
-
Cavium
-
HiSilicon
-
MediaTek
-
NXP
-
Qualcomm
-
Renesas
-
Samsung
-
From WikiChip
Hanguang 800 - T-Head
< t-head
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Edit Values | |
Hanguang 800 | |
General Info | |
Designer | T-Head |
Manufacturer | TSMC |
Market | Server, Artificial Intelligence |
Introduction | September 26, 2019 (announced) September 26, 2019 (launched) |
General Specs | |
Family | Hanguang |
Microarchitecture | |
Process | 12 nm |
Transistors | 17,000,000,000 |
Technology | CMOS |
Hanguang 800 is a neural processor designed by Alibaba for inference acceleration in their data centers and edge servers. Introduced in September 2019, the Hanguang 800 chip is fabricated with TSMC 12 nm process. It is used exclusively in Alibaba cloud infrastructure.
This article is still a stub and needs your attention. You can help improve this article by editing this page and adding the missing information. |
Facts about "Hanguang 800 - T-Head"
designer | T-Head + |
family | Hanguang + |
first announced | September 26, 2019 + |
first launched | September 26, 2019 + |
full page name | t-head/hanguang 800 + |
instance of | microprocessor + |
ldate | September 26, 2019 + |
main image | + |
manufacturer | TSMC + |
market segment | Server + and Artificial Intelligence + |
name | Hanguang 800 + |
process | 12 nm (0.012 μm, 1.2e-5 mm) + |
technology | CMOS + |
transistor count | 17,000,000,000 + |