AMD Navi 31 GPU FP32 delivers 92 TFLOPS of performance
There are recent rumors that AMD RDNA3’s flagship GPU Navi 31 may achieve FP32 performance of 92 TFLOPS, which is 28% higher than the previously rumored 75 TFLOPS. That’s four times the performance of the current RDNA2’s top-tier Navi 21 GPU ( RX 6900XT ) model.
AMD has major changes in the next-generation architecture specifications, but what exactly is still uncertain, assuming AMD retains the 60 WorkGroup Processor (WGP) and 15360 stream processor configuration, a core speed of 2995MHz is required to achieve 92 TFLOPS of FP32 single-precision computing performance. However, similar to NVIDIA’s Ada architecture, AMD may introduce a different 32bit instruction matrix to improve floating-point performance.
Also contrary to previous rumors, AMD may still keep Compute Units for its RDNA3 (GFX11) architecture. Twitter user @Kepler_L2: found that the AMD GPU driver change explained this:
AMDGPU driver, Source: Freedesktop
The AMD Radeon RX 7000 series is now expected to launch by the end of the year. The Navi 31 GPU should be the first to be released by AMD, and the possible model name is RX 7900 XT, a new consumer-grade flagship graphics card.
Via: videocardz
