Apple Silicon M1 Emulating x86 Is Still Faster Than Every Other Mac

Re:Apple Silicon M1 Emulating x86 Is Still Faster Than Every... by cromwellian on Sunday November 15, 2020 @10:42PM (#25107711)

Wait, you're comparing M1's neural engine with Ampere's tensorcores? Apple is talking TOPS, not TFLOPS, that means M1's 11 TOPs are for inference only, not training. By contrast, a tensorcore on Ampere does ~20 TFLOPS FP64, 78 TFLOPS FP16/BF16, and with GPU boost clock, up to 312 TFLOPs @ BF16.

If you want to talk TOPS, an A100 does up to 1.2 exa-ops INT8, and 2.4 exa-tops INT4. That is, an A100 is more than 1000 times more powerful than the M1 at inferencing, while also supporting up to FP32/FP64 weights, and a 3080 is more than 500 times more powerful than the M1 neural engine.

[ Parent | on HN ]

Re:Apple Silicon M1 Emulating x86 Is Still Faster Than Every... by dannyw on Monday November 16, 2020 @05:47AM (#25110269)

An A100 isn't a consumer GPU; a more valid comparison would be the RTX 3070.

[ Parent | on HN ]

Re:Apple Silicon M1 Emulating x86 Is Still Faster Than Every... by cromwellian on Monday November 16, 2020 @07:16AM (#25110739)

Even an RTC 2060 beats it, the 2060 has 52 TFLOPs worth of tensor core ops (not counting the CUDA cores), and it has >100 TOPs @ INT8, or 200+ TOPs @ INT4, so more than 10x the M1.

[ Parent | on HN ]