GPU model | GP104 | GA106 |
---|---|---|
GPU variant | GP104-150-KA-A1 | — |
Architecture | Pascal | Ampere |
Foundry | TSMC | Samsung |
Manufacturing process | 16 nm | 8 nm |
Number of transistors | 7,200 million | 13,250 million |
Die size | 314 mm² | 276 mm² |
Release date | Oct 18th, 2018 | — |
---|---|---|
Generation | GeForce 10 | — |
Predecessor | GeForce 900 | — |
Successor | GeForce 20 | — |
Production | End-of-life | — |
Interface | PCIe 3.0 x16 | — |
Reviews | 117 in our database | — |
Base clock | 1506 MHz | 735 MHz |
---|---|---|
Boost clock | 1709 MHz | 1035 MHz |
Memory clock | 1001 MHz 8 Gbps effective | 1500 MHz 12 Gbps effective |
Memory size | 6 GB | 4 GB |
---|---|---|
Memory type | GDDR5X | GDDR6 |
Memory bus width | 192 bit | 128 bit |
Bandwidth | 192.2 GB/s | 192.0 GB/s |
Shading units | 1280 | 2560 |
---|---|---|
TMUs | 80 | 80 |
ROPs | 48 | 48 |
SM count | 10 | 20 |
Cache L1 | 48 KB (per SM) | 128 KB (per SM) |
Cache L2 | 1536 KB | 2 MB |
Tensor cores | — | 80 |
RT cores | — | 20 |
Pixel rate | 82.03 GPixel/s | 49.68 GPixel/s |
---|---|---|
Texture rate | 136.7 GTexel/s | 82.80 GTexel/s |
FP16 (half) performance | 68.36 GFLOPS (1:64) | 5.299 TFLOPS (1:1) |
FP32 (float) performance | 4.375 TFLOPS | 5.299 TFLOPS |
FP64 (double) performance | 136.7 GFLOPS (1:32) | 82.80 GFLOPS (1:64) |
Slot width | Dual-slot | IGP |
---|---|---|
Length | 250 mm 9.8 inches | — |
TDP | 120 W | 75 W |
Suggested PSU | 300 W | — |
Outputs | 1x DVI1x HDMI3x DisplayPort | No outputs |
Power connectors | 1x 6-pin | None |
DirectX | 12 (12_1) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 6.1 | 8.6 |
Shader model | 6.4 | 6.6 |
Release date | — | May 11th, 2021 |
---|---|---|
gpu.details.availability | — | 2021 |
Generation | — | GeForce 30 Mobile |
Predecessor | — | GeForce 20 Mobile |
Production | — | Active |
Interface | — | PCIe 4.0 x16 |