AMD Radeon R8 M365DX vs NVIDIA GRID A100B
Graphics Processor
| GPU model | Meso | GA100 |
|---|---|---|
| GPU variant | Meso XT (216-0867030) | — |
| Architecture | GCN 3.0 | Ampere |
| Foundry | TSMC | TSMC |
| Manufacturing process | 28 nm | 7 nm |
| Number of transistors | 1,550 million | 54,200 million |
| Die size | 125 mm² | 826 mm² |
Integrated Graphics
| Release date | Jun 3rd, 2015 | — |
|---|---|---|
| Generation | Crystal System (Rx M300) | — |
| Production | End-of-life | — |
| Interface | IGP | — |
Clocks
| Base clock | 900 MHz | 900 MHz |
|---|---|---|
| Boost clock | 1125 MHz | 1005 MHz |
| Memory clock | System Shared | 1215 MHz 2.4 Gbps effective |
Memory Configuration
| Memory size | System Shared | 48 GB |
|---|---|---|
| Memory type | System Shared | HBM2E |
| Memory bus width | System Shared | 6144 bit |
| Bandwidth | System Dependent | 1,866 GB/s |
Render Configuration
| Shading units | 384 | 6912 |
|---|---|---|
| TMUs | 24 | 432 |
| ROPs | 8 | 192 |
| Compute units | 6 | — |
| Cache L1 | 16 KB (per CU) | 192 KB (per SM) |
| Cache L2 | 256 KB | 48 MB |
| SM count | — | 108 |
| Tensor cores | — | 432 |
Performance
| Pixel rate | 9.000 GPixel/s | 193.0 GPixel/s |
|---|---|---|
| Texture rate | 27.00 GTexel/s | 434.2 GTexel/s |
| FP16 (half) performance | 864.0 GFLOPS (1:1) | 55.57 TFLOPS (4:1) |
| FP32 (float) performance | 864.0 GFLOPS | 13.89 TFLOPS |
| FP64 (double) performance | 54.00 GFLOPS (1:16) | 6.947 TFLOPS (1:2) |
Dimensions & Outputs
| Slot width | IGP | IGP |
|---|---|---|
| TDP | unknown | 400 W |
| Outputs | No outputs | No outputs |
| Suggested PSU | — | 800 W |
| Power connectors | — | None |
API Support & Features
| DirectX | 12 (12_0) | — |
|---|---|---|
| OpenGL | 4.6 | — |
| OpenCL | 2.0 | 3.0 |
| Vulkan | 1.2 | — |
| Shader model | 6.0 | — |
| CUDA | — | 8.0 |
Other Features
Graphics Card
| Release date | — | May 14th, 2020 |
|---|---|---|
| Generation | — | GRID |
| Production | — | Active |
| Interface | — | PCIe 4.0 x16 |
