GPU model | Picasso | GP104 |
---|---|---|
Architecture | GCN 5.0 | Pascal |
Foundry | GlobalFoundries | TSMC |
Manufacturing process | 14 nm | 16 nm |
Number of transistors | 4,940 million | 7,200 million |
Die size | 210 mm² | 314 mm² |
GPU variant | — | N17E-Q1-A1 |
Release date | Apr 8th, 2019 | — |
---|---|---|
Generation | Picasso (Vega Mobile) | — |
Production | Active | — |
Interface | IGP | — |
Predecessor | Raven Ridge | — |
Successor | Renoir | — |
Base clock | 300 MHz | 1088 MHz |
---|---|---|
Boost clock | 1200 MHz | 1215 MHz |
Memory clock | System Shared | 1753 MHz 7 Gbps effective |
Memory size | System Shared | 6 GB |
---|---|---|
Memory type | System Shared | GDDR5 |
Memory bus width | System Shared | 192 bit |
Bandwidth | System Dependent | 168.3 GB/s |
Shading units | 512 | 1280 |
---|---|---|
TMUs | 32 | 80 |
ROPs | 8 | 48 |
Compute units | 8 | — |
SM count | — | 10 |
Cache L1 | — | 48 KB (per SM) |
Cache L2 | — | 1536 KB |
Pixel rate | 9.600 GPixel/s | 58.32 GPixel/s |
---|---|---|
Texture rate | 38.40 GTexel/s | 97.20 GTexel/s |
FP16 (half) performance | 2.458 TFLOPS (2:1) | 48.60 GFLOPS (1:64) |
FP32 (float) performance | 1,229 GFLOPS | 3.110 TFLOPS |
FP64 (double) performance | 76.80 GFLOPS (1:16) | 97.20 GFLOPS (1:32) |
Slot width | IGP | MXM Module |
---|---|---|
TDP | 15 W | 75 W |
Outputs | No outputs | No outputs |
Power connectors | — | None |
DirectX | 12 (12_1) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader model | 6.4 | 6.4 |
CUDA | — | 6.1 |
Release date | — | Jan 11th, 2017 |
---|---|---|
Generation | — | Quadro Mobile (Px000) |
Production | — | End-of-life |
Interface | — | MXM-B (3.0) |