GPU model | Picasso | GA103 |
---|---|---|
Architecture | GCN 5.0 | Ampere |
Foundry | GlobalFoundries | Samsung |
Manufacturing process | 14 nm | 8 nm |
Number of transistors | 4,940 million | unknown |
Die size | 210 mm² | unknown |
GPU variant | — | GA103S |
Release date | Jan 6th, 2019 | — |
---|---|---|
Generation | Picasso (Vega Mobile) | — |
Production | Active | — |
Interface | IGP | — |
Predecessor | Raven Ridge | — |
Successor | Renoir | — |
Base clock | 300 MHz | 975 MHz |
---|---|---|
Boost clock | 1200 MHz | 1395 MHz |
Memory clock | System Shared | 2000 MHz 16 Gbps effective |
Memory size | System Shared | 16 GB |
---|---|---|
Memory type | System Shared | GDDR6 |
Memory bus width | System Shared | 256 bit |
Bandwidth | System Dependent | 512.0 GB/s |
Shading units | 384 | 7424 |
---|---|---|
TMUs | 24 | 232 |
ROPs | 8 | 96 |
Compute units | 6 | — |
SM count | — | 58 |
Tensor cores | — | 232 |
RT cores | — | 58 |
Cache L1 | — | 128 KB (per SM) |
Cache L2 | — | 4 MB |
Pixel rate | 9.600 GPixel/s | 133.9 GPixel/s |
---|---|---|
Texture rate | 28.80 GTexel/s | 323.6 GTexel/s |
FP16 (half) performance | 1.843 TFLOPS (2:1) | 20.71 TFLOPS (1:1) |
FP32 (float) performance | 921.6 GFLOPS | 20.71 TFLOPS |
FP64 (double) performance | 57.60 GFLOPS (1:16) | 323.6 GFLOPS (1:64) |
Slot width | IGP | — |
---|---|---|
TDP | 15 W | 175 W |
Outputs | No outputs | No outputs |
Power connectors | — | None |
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 | 6.5 |
CUDA | — | 8.6 |
Release date | — | 2022 |
---|---|---|
gpu.details.availability | — | — |
Generation | — | GeForce 30 Mobile |
Predecessor | — | GeForce 20 Mobile |
Production | — | Unreleased |
Interface | — | PCIe 4.0 x16 |