Difference between revisions of "Blackwell (microarchitecture)"
Jump to navigation
Jump to search
Tags: Mobile web edit, Mobile edit |
(Nvidia claims 20 petaflops of FP4 compute with the dual GB100 die B100 accelerator) Tags: Mobile web edit, Mobile edit |
||
| Line 3: | Line 3: | ||
* Blackwell adds support for [[FP4]] and [[FP6]] data types with eighth precision floating point processing | * Blackwell adds support for [[FP4]] and [[FP6]] data types with eighth precision floating point processing | ||
| + | Nvidia claims 20 [[petaflops]] of FP4 compute with the dual GB100 die B100 accelerator | ||
* [[GTC]] | * [[GTC]] | ||
{{NVLink}} | {{NVLink}} | ||
Latest revision as of 04:07, 6 May 2024
Advertising:
