GPU model | DG1 | GP104 |
---|---|---|
Architecture | Generation 12.1 | Pascal |
Foundry | Intel | TSMC |
Manufacturing process | 10 nm | 16 nm |
Number of transistors | unknown | 7,200 million |
Die size | 95 mm² | 314 mm² |
GPU variant | — | GP104-150-KA-A1 |
Release date | Never Released | Never Released |
---|---|---|
Generation | Xe Graphics | GeForce 10 |
Production | Active | End-of-life |
Interface | PCIe 3.0 x4 | PCIe 3.0 x16 |
Predecessor | — | GeForce 900 |
Successor | — | GeForce 20 |
Reviews | — | 117 in our database |
Base clock | 900 MHz | 1506 MHz |
---|---|---|
Boost clock | 1550 MHz | 1709 MHz |
Memory clock | 2133 MHz 4.3 Gbps effective | 1001 MHz 8 Gbps effective |
Memory size | 4 GB | 8 GB |
---|---|---|
Memory type | LPDDR4X | GDDR5X |
Memory bus width | 128 bit | 256 bit |
Bandwidth | 68.26 GB/s | 256.3 GB/s |
Shading units | 640 | 1280 |
---|---|---|
TMUs | 40 | 80 |
ROPs | 20 | 64 |
Execution units | 80 | — |
Cache L2 | 1024 KB | 2 MB |
gpu.details.l3-cache | 16 MB | — |
SM count | — | 10 |
Cache L1 | — | 48 KB (per SM) |
Pixel rate | 31.00 GPixel/s | 109.4 GPixel/s |
---|---|---|
Texture rate | 62.00 GTexel/s | 136.7 GTexel/s |
FP16 (half) performance | 3.968 TFLOPS (2:1) | 68.36 GFLOPS (1:64) |
FP32 (float) performance | 1.984 TFLOPS | 4.375 TFLOPS |
FP64 (double) performance | 496.0 GFLOPS (1:4) | 136.7 GFLOPS (1:32) |
Slot width | Dual-slot | Dual-slot |
---|---|---|
Length | 178 mm 7 inches | 250 mm 9.8 inches |
TDP | 30 W | 120 W |
Suggested PSU | 200 W | 300 W |
Outputs | 1x HDMI3x DisplayPort | 1x DVI1x HDMI3x DisplayPort |
Power connectors | None | 1x 6-pin |
DirectX | 12 (12_1) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader model | 6.4 | 6.4 |
CUDA | — | 6.1 |