From WikiChip
Difference between revisions of "baidu/kunlun"
(kunlun) |
|||
Line 4: | Line 4: | ||
| image = | | image = | ||
| caption = | | caption = | ||
− | | no image = | + | | no image = Yes |
| developer = Baidu | | developer = Baidu | ||
| manufacturer = Samsung | | manufacturer = Samsung | ||
Line 28: | Line 28: | ||
}} | }} | ||
'''Kunlun''' is a series of [[neural processors]] designed by [[Baidu]]. | '''Kunlun''' is a series of [[neural processors]] designed by [[Baidu]]. | ||
+ | |||
+ | == Overview == | ||
+ | Baidu initially started development of {{baidu|XPU|the architecture|l=arch}} in [[2011]]. All initial research and development were done on [[FPGAs]]. In July [[2018]], Baidu announced that they have designed a physical chip based on the same architecture. | ||
+ | |||
+ | == Models == | ||
+ | {{empy section}} |
Revision as of 23:51, 4 July 2018
Kunlun | |
Developer | Baidu |
Manufacturer | Samsung |
Type | Neural Processors |
Introduction | July 3, 2018 (announced) |
Architecture | Many tiny cores architecture |
µarch | XPU |
Process | 14 nm 0.014 μm
1.4e-5 mm |
Technology | CMOS |
Kunlun is a series of neural processors designed by Baidu.
Overview
Baidu initially started development of the architecture in 2011. All initial research and development were done on FPGAs. In July 2018, Baidu announced that they have designed a physical chip based on the same architecture.
Models
Facts about "Kunlun - Baidu"
designer | Baidu + |
first announced | July 3, 2018 + |
full page name | baidu/kunlun + |
instance of | integrated circuit family + |
main designer | Baidu + |
manufacturer | Samsung + |
microarchitecture | XPU + |
name | Kunlun + |
process | 14 nm (0.014 μm, 1.4e-5 mm) + |
technology | CMOS + |