GPU model | Raven | GF100 |
---|---|---|
Architecture | GCN 5.0 | Fermi |
Foundry | GlobalFoundries | TSMC |
Manufacturing process | 14 nm | 40 nm |
Number of transistors | 4,940 million | 3,100 million |
Die size | 210 mm² | 529 mm² |
Release date | Apr 19th, 2018 | — |
---|---|---|
Generation | Raven Ridge (Vega) | — |
Production | Active | — |
Interface | IGP | — |
Predecessor | Great Horned Owl | — |
Successor | Picasso | — |
Base clock | 300 MHz | — |
---|---|---|
Boost clock | 1251 MHz | — |
Memory clock | System Shared | 702 MHz 2.8 Gbps effective |
GPU clock | — | 475 MHz |
Shader clock | — | 950 MHz |
Memory size | System Shared | 1792 MB |
---|---|---|
Memory type | System Shared | GDDR5 |
Memory bus width | System Shared | 256 bit |
Bandwidth | System Dependent | 89.86 GB/s |
Shading units | 704 | 256 |
---|---|---|
TMUs | 44 | 32 |
ROPs | 8 | 32 |
Compute units | 11 | — |
SM count | — | 8 |
Cache L1 | — | 64 KB (per SM) |
Cache L2 | — | 512 KB |
Pixel rate | 10.01 GPixel/s | 7.600 GPixel/s |
---|---|---|
Texture rate | 55.04 GTexel/s | 15.20 GTexel/s |
FP16 (half) performance | 3.523 TFLOPS (2:1) | — |
FP32 (float) performance | 1.761 TFLOPS | 486.4 GFLOPS |
FP64 (double) performance | 110.1 GFLOPS (1:16) | 243.2 GFLOPS (1:2) |
Slot width | IGP | Dual-slot |
---|---|---|
TDP | 35 W | 142 W |
Outputs | No outputs | 1x DVI1x DisplayPort1x S-Video |
Power connectors | None | 1x 6-pin |
Length | — | 241 mm 9.5 inches |
Suggested PSU | — | 300 W |
DirectX | 12 (12_1) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 1.1 |
Vulkan | 1.2 | — |
Shader model | 6.4 | 5.1 |
CUDA | — | 2.0 |
Release date | — | Jun 12th, 2011 |
---|---|---|
Generation | — | Quadro |
Production | — | End-of-life |
Launch price | — | 1,199 USD |
Interface | — | PCIe 2.0 x16 |
Reviews | — | 26 in our database |