GPU model | Vega 20 | GA102 |
---|---|---|
GPU variant | Vega 20 XT | GA102-350-A1 |
Architecture | GCN 5.1 | Ampere |
Foundry | TSMC | Samsung |
Manufacturing process | 7 nm | 8 nm |
Number of transistors | 13,230 million | 28,300 million |
Die size | 331 mm² | 628 mm² |
Release date | Feb 7th, 2019 | Unknown |
---|---|---|
Generation | Vega II | GeForce 30 |
Production | Active | Unreleased |
Launch price | 699 USD | 1,699 USD |
Current price | Amazon / Newegg | — |
Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
Predecessor | Vega | GeForce 20 |
Successor | Navi | — |
gpu.details.availability | — | 2022 |
Reviews | — | 55 in our database |
Base clock | 1400 MHz | 1560 MHz |
---|---|---|
Boost clock | 1750 MHz | 1860 MHz |
Peak clock | 1802 MHz | — |
Memory clock | 1000 MHz 2 Gbps effective | 1325 MHz 21.2 Gbps effective |
Memory size | 16 GB | 24 GB |
---|---|---|
Memory type | HBM2 | GDDR6X |
Memory bus width | 4096 bit | 384 bit |
Bandwidth | 1,024 GB/s | 1,018 GB/s |
Shading units | 3840 | 10752 |
---|---|---|
TMUs | 240 | 336 |
ROPs | 64 | 112 |
Compute units | 60 | — |
Cache L1 | 16 KB (per CU) | 128 KB (per SM) |
Cache L2 | 4 MB | 6 MB |
SM count | — | 84 |
Tensor cores | — | 336 |
RT cores | — | 84 |
Pixel rate | 112.0 GPixel/s | 208.3 GPixel/s |
---|---|---|
Texture rate | 420.0 GTexel/s | 625.0 GTexel/s |
FP16 (half) performance | 26.88 TFLOPS (2:1) | 40.00 TFLOPS (1:1) |
FP32 (float) performance | 13.44 TFLOPS | 40.00 TFLOPS |
FP64 (double) performance | 3.360 TFLOPS (1:4) | 625.0 GFLOPS (1:64) |
Slot width | Dual-slot | Triple-slot |
---|---|---|
Length | 280 mm 11 inches | 336 mm 13.2 inches |
Width | 125 mm 4.9 inches | 140 mm 5.5 inches |
Height | 40 mm 1.6 inches | 61 mm 2.4 inches |
TDP | 295 W | 450 W |
Suggested PSU | 600 W | 850 W |
Outputs | 1x HDMI3x DisplayPort | 1x HDMI3x DisplayPort |
Power connectors | 2x 8-pin | 1x 12-pin |
Board number | 109-D36037-00_04 | PG132 SKU |
gpu.details.bios-number | 113-D3600200-105 | — |
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 | 6.4 | 6.6 |
CUDA | — | 8.6 |