GPU model | GP102 | GA102 |
---|---|---|
GPU variant | GP102-350-K1-A1 | GA102-350-A1 |
Architecture | Pascal | Ampere |
Foundry | TSMC | Samsung |
Manufacturing process | 16 nm | 8 nm |
Number of transistors | 11,800 million | 28,300 million |
Die size | 471 mm² | 628 mm² |
Release date | Mar 10th, 2017 | Unknown |
---|---|---|
Generation | GeForce 10 | GeForce 30 |
Predecessor | GeForce 900 | GeForce 20 |
Successor | GeForce 20 | — |
Production | End-of-life | Unreleased |
Launch price | 699 USD | 1,699 USD |
Current price | Amazon / Newegg | — |
Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
Reviews | 149 in our database | 55 in our database |
gpu.details.availability | — | 2022 |
Base clock | 1481 MHz | 1560 MHz |
---|---|---|
Boost clock | 1582 MHz | 1860 MHz |
Memory clock | 1376 MHz 11 Gbps effective | 1325 MHz 21.2 Gbps effective |
Memory size | 11 GB | 24 GB |
---|---|---|
Memory type | GDDR5X | GDDR6X |
Memory bus width | 352 bit | 384 bit |
Bandwidth | 484.4 GB/s | 1,018 GB/s |
Shading units | 3584 | 10752 |
---|---|---|
TMUs | 224 | 336 |
ROPs | 88 | 112 |
SM count | 28 | 84 |
Cache L1 | 48 KB (per SM) | 128 KB (per SM) |
Cache L2 | 2.75 MB | 6 MB |
Tensor cores | — | 336 |
RT cores | — | 84 |
Pixel rate | 139.2 GPixel/s | 208.3 GPixel/s |
---|---|---|
Texture rate | 354.4 GTexel/s | 625.0 GTexel/s |
FP16 (half) performance | 177.2 GFLOPS (1:64) | 40.00 TFLOPS (1:1) |
FP32 (float) performance | 11.34 TFLOPS | 40.00 TFLOPS |
FP64 (double) performance | 354.4 GFLOPS (1:32) | 625.0 GFLOPS (1:64) |
Slot width | Dual-slot | Triple-slot |
---|---|---|
Length | 267 mm 10.5 inches | 336 mm 13.2 inches |
Width | 112 mm 4.4 inches | 140 mm 5.5 inches |
Height | 40 mm 1.6 inches | 61 mm 2.4 inches |
TDP | 250 W | 450 W |
Suggested PSU | 600 W | 850 W |
Outputs | 1x HDMI3x DisplayPort | 1x HDMI3x DisplayPort |
Power connectors | 1x 6-pin + 1x 8-pin | 1x 12-pin |
Board number | PG611 SKU 50 | PG132 SKU |
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 |