GPU model | Navi 10 | TU104 |
---|---|---|
Architecture | RDNA 1.0 | Turing |
Foundry | TSMC | TSMC |
Manufacturing process | 7 nm | 12 nm |
Number of transistors | 10,300 million | 13,600 million |
Die size | 251 mm² | 545 mm² |
GPU variant | — | TU104-850-A1 |
Release date | Nov 19th, 2019 | Nov 13th, 2018 |
---|---|---|
Generation | Radeon Pro | Quadro |
Production | Active | Active |
Launch price | 799 USD | 899 USD |
Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
Base clock | 1400 MHz | 1005 MHz |
---|---|---|
Boost clock | 1880 MHz | 1545 MHz |
Memory clock | 1750 MHz 14 Gbps effective | 1625 MHz 13 Gbps effective |
Memory size | 8 GB | 8 GB |
---|---|---|
Memory type | GDDR6 | GDDR6 |
Memory bus width | 256 bit | 256 bit |
Bandwidth | 448.0 GB/s | 416.0 GB/s |
Shading units | 2304 | 2304 |
---|---|---|
TMUs | 144 | 144 |
ROPs | 64 | 64 |
Compute units | 36 | — |
Cache L2 | 4 MB | 4 MB |
SM count | — | 36 |
Tensor cores | — | 288 |
RT cores | — | 36 |
Cache L1 | — | 64 KB (per SM) |
Pixel rate | 120.3 GPixel/s | 98.88 GPixel/s |
---|---|---|
Texture rate | 270.7 GTexel/s | 222.5 GTexel/s |
FP16 (half) performance | 17.33 TFLOPS (2:1) | 14.24 TFLOPS (2:1) |
FP32 (float) performance | 8.663 TFLOPS | 7.119 TFLOPS |
FP64 (double) performance | 541.4 GFLOPS (1:16) | 222.5 GFLOPS (1:32) |
Slot width | Dual-slot | Single-slot |
---|---|---|
Length | 267 mm 10.5 inches | 241 mm 9.5 inches |
Width | 111 mm 4.4 inches | 111 mm 4.4 inches |
TDP | 205 W | 160 W |
Suggested PSU | 550 W | 450 W |
Outputs | 5x mini-DisplayPort1x USB Type-C | 3x DisplayPort1x USB Type-C |
Power connectors | 1x 6-pin + 1x 8-pin | 1x 8-pin |
DirectX | 12 (12_1) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader model | 6.5 | 6.6 |
CUDA | — | 7.5 |