mirrors/tinygrad
2
0
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-06-24 02:14:17 +00:00
Code Issues Projects Releases Packages Wiki Activity

more business notes

Browse source
This commit is contained in:
George Hotz 2021-06-16 11:47:57 -07:00
commit d29b16e5b4
1 changed files with 14 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

14
fpga/README
View file

@ -15,6 +15,10 @@ Small Board (Arty A7 100T)
* 4x4x4 matmul = 64 mults, perhaps 8x8x8 matmul = 512 mults
* 6.4 GFLOPS @ 50 mhz
* Forward/backward pass of ResNet-50, EfficientNet-B2, and BERT-large in the simulator
* Train MNIST models on the real hardware
* After we've trained MNIST here, buy the big board and a Linux computer for home
Big Board (Alveo U250)
=====
* Support DMA over PCI-E. 16 GB/s
@ -24,6 +28,12 @@ Big Board (Alveo U250)
* 16x16x16 matmul = 4096 mults, perhaps 32x32x32 matmul = 32768 mults
* 4 TFLOPS @ 500 mhz
* Bring up in one Z840 with one card
* Train (with tinygrad) ResNet-50, EfficientNet-B2, and BERT-large
* Now we buy a machine with 8x cards
* Write 8x multicard training, place on https://mlcommons.org/en/training-normal-07/
* Now it's funding/kickstarter time, based on our MLPerf results on the Alveos and Cherry Two sim
Cherry Two (12nm tapeout)
=====
* Support DMA over PCI-E. 16 GB/s
@ -34,6 +44,10 @@ Cherry Two (12nm tapeout)
* Target 75W, even if underclocked. One slot, no external power.
* This card should be on par with a 3090 and sell for $1000
* Write PyTorch port to support same training while waiting for tapeout
* If we are here, we are winning the AI chip market
* Tile the core and go to a smaller process node
Cherry Three (5nm tapeout)
=====
* Support DMA over PCI-E 4.0. 32 GB/s