GPU model | GP104 | GV100 |
---|---|---|
GPU variant | GP104-200-A1 | GV100-875-A1 |
Architecture | Pascal | Volta |
Foundry | TSMC | TSMC |
Manufacturing process | 16 nm | 12 nm |
Number of transistors | 7,200 million | 21,100 million |
Die size | 314 mm² | 815 mm² |
Release date | Jun 10th, 2016 | Mar 27th, 2018 |
---|---|---|
Generation | GeForce 10 | Quadro |
Predecessor | GeForce 900 | — |
Successor | GeForce 20 | — |
Production | End-of-life | End-of-life |
Launch price | 379 USD | 8,999 USD |
Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Reviews | 125 in our database | — |
Base clock | 1506 MHz | 1132 MHz |
---|---|---|
Boost clock | 1683 MHz | 1627 MHz |
Memory clock | 2002 MHz 8 Gbps effective | 848 MHz 1696 Mbps effective |
Memory size | 8 GB | 32 GB |
---|---|---|
Memory type | GDDR5 | HBM2 |
Memory bus width | 256 bit | 4096 bit |
Bandwidth | 256.3 GB/s | 868.4 GB/s |
Shading units | 1920 | 5120 |
---|---|---|
TMUs | 120 | 320 |
ROPs | 64 | 128 |
SM count | 15 | 80 |
Cache L1 | 48 KB (per SM) | 128 KB (per SM) |
Cache L2 | 2 MB | 6 MB |
Tensor cores | — | 640 |
Pixel rate | 107.7 GPixel/s | 208.3 GPixel/s |
---|---|---|
Texture rate | 202.0 GTexel/s | 520.6 GTexel/s |
FP16 (half) performance | 101.0 GFLOPS (1:64) | 33.32 TFLOPS (2:1) |
FP32 (float) performance | 6.463 TFLOPS | 16.66 TFLOPS |
FP64 (double) performance | 202.0 GFLOPS (1:32) | 8.330 TFLOPS (1:2) |
Slot width | Dual-slot | Dual-slot |
---|---|---|
Length | 267 mm 10.5 inches | 267 mm 10.5 inches |
Width | 112 mm 4.4 inches | 111 mm 4.4 inches |
Height | 40 mm 1.6 inches | — |
TDP | 150 W | 250 W |
Suggested PSU | 450 W | 600 W |
Outputs | 1x DVI1x HDMI3x DisplayPort | 4x DisplayPort |
Power connectors | 1x 8-pin | 8-pin EPS |
Board number | PG411 SKU 20 | PG500 SKU 500 |
DirectX | 12 (12_1) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 6.1 | 7.0 |
Shader model | 6.4 | 6.6 |