GPU model | GA104 | GP100 |
---|---|---|
GPU variant | GA104-300-A1 | GP100-893-A1 |
Architecture | Ampere | Pascal |
Foundry | Samsung | TSMC |
Manufacturing process | 8 nm | 16 nm |
Number of transistors | 17,400 million | 15,300 million |
Die size | 392 mm² | 610 mm² |
Release date | Sep 1st, 2020 | Jun 20th, 2016 |
---|---|---|
gpu.details.availability | Oct 29th, 2020 | — |
Generation | GeForce 30 | Tesla |
Predecessor | GeForce 20 | — |
Production | Active | End-of-life |
Launch price | 499 USD | 5,699 USD |
Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
Reviews | 78 in our database | — |
Base clock | 1500 MHz | 1190 MHz |
---|---|---|
Boost clock | 1725 MHz | 1329 MHz |
Memory clock | 1750 MHz 14 Gbps effective | 715 MHz 1430 Mbps effective |
Memory size | 8 GB | 16 GB |
---|---|---|
Memory type | GDDR6 | HBM2 |
Memory bus width | 256 bit | 4096 bit |
Bandwidth | 448.0 GB/s | 732.2 GB/s |
Shading units | 5888 | 3584 |
---|---|---|
TMUs | 184 | 224 |
ROPs | 96 | 96 |
SM count | 46 | 56 |
Tensor cores | 184 | — |
RT cores | 46 | — |
Cache L1 | 128 KB (per SM) | 24 KB (per SM) |
Cache L2 | 4 MB | 4 MB |
Pixel rate | 165.6 GPixel/s | 127.6 GPixel/s |
---|---|---|
Texture rate | 317.4 GTexel/s | 297.7 GTexel/s |
FP16 (half) performance | 20.31 TFLOPS (1:1) | 19.05 TFLOPS (2:1) |
FP32 (float) performance | 20.31 TFLOPS | 9.526 TFLOPS |
FP64 (double) performance | 317.4 GFLOPS (1:64) | 4.763 TFLOPS (1:2) |
Slot width | Dual-slot | Dual-slot |
---|---|---|
Length | 242 mm 9.5 inches | 267 mm 10.5 inches |
Width | 112 mm 4.4 inches | — |
TDP | 220 W | 250 W |
Suggested PSU | 550 W | 600 W |
Outputs | 1x HDMI3x DisplayPort | No outputs |
Power connectors | 1x 12-pin | 1x 8-pin |
Board number | PG142 SKU 10 | — |
DirectX | 12 Ultimate (12_2) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 8.6 | 6.0 |
Shader model | 6.6 | 6.4 |