GPU model | GA104 | GP102 |
---|---|---|
Architecture | Ampere | Pascal |
Foundry | Samsung | TSMC |
Manufacturing process | 8 nm | 16 nm |
Number of transistors | 17,400 million | 11,800 million |
Die size | 392 mm² | 471 mm² |
Release date | Unknown | — |
---|---|---|
Generation | GeForce 30 Mobile | — |
Predecessor | GeForce 20 Mobile | — |
Production | Unreleased | — |
Interface | PCIe 4.0 x16 | — |
Base clock | 915 MHz | 1303 MHz |
---|---|---|
Boost clock | 1410 MHz | 1531 MHz |
Memory clock | 1750 MHz 14 Gbps effective | 1808 MHz 14.5 Gbps effective |
Memory size | 8 GB | 24 GB |
---|---|---|
Memory type | GDDR6 | GDDR5X |
Memory bus width | 256 bit | 384 bit |
Bandwidth | 448.0 GB/s | 694.3 GB/s |
Shading units | 5632 | 3840 |
---|---|---|
TMUs | 176 | 240 |
ROPs | 80 | 96 |
SM count | 44 | 30 |
Tensor cores | 176 | — |
RT cores | 44 | — |
Cache L1 | 128 KB (per SM) | 48 KB (per SM) |
Cache L2 | 4 MB | 3 MB |
Pixel rate | 112.8 GPixel/s | 147.0 GPixel/s |
---|---|---|
Texture rate | 248.2 GTexel/s | 367.4 GTexel/s |
FP16 (half) performance | 15.88 TFLOPS (1:1) | 183.7 GFLOPS (1:64) |
FP32 (float) performance | 15.88 TFLOPS | 11.76 TFLOPS |
FP64 (double) performance | 248.2 GFLOPS (1:64) | 367.4 GFLOPS (1:32) |
TDP | 115 W | 250 W |
---|---|---|
Outputs | No outputs | No outputs |
Power connectors | None | 1x 6-pin + 1x 8-pin |
Slot width | — | Dual-slot |
Length | — | 267 mm 10.5 inches |
Width | — | 111 mm 4.4 inches |
Suggested PSU | — | 600 W |
Board number | — | PG610 SKU 200 |
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 | 6.1 |
Shader model | 6.6 | 6.4 |
Release date | — | Sep 13th, 2016 |
---|---|---|
Generation | — | Tesla |
Production | — | End-of-life |
Launch price | — | 5,699 USD |
Interface | — | PCIe 3.0 x16 |