- 精华
- 0
- 帖子
- 6793
- 威望
- 0 点
- 积分
- 6937 点
- 种子
- 593 点
- 注册时间
- 2012-5-29
- 最后登录
- 2024-11-16
|
发表于 2021-3-18 21:24 · 广西
|
显示全部楼层
RDNA supports down to eight 4-bit parallel ops and mixed-precision FMA for machine learning tasks.
AMD’s Graphics Core Next (GCN) architecture, the precursor to RDNA, is also particularly strong at machine learning (ML) workloads. AI, as we know, is now a big deal in smartphone processors and is only likely to become more common over the next five years.
RDNA retains high-performance machine learning credentials, with support for 64, 32, 16, 8, and even 4-bit integer math in parallel. RDNA’s Vector ALUs are twice as wide as the previous generation, for faster number crunching and also perform fused multiply-accumulate (FMA) operations with less power consumption than previous generations. FMA math is common in machine learning applications, so much so that there’s a dedicated hardware block for it inside Arm’s Mali-G77. |
|