NVIDIA CMP 90HX vs AMD Radeon Pro Vega 64
What is the difference between NVIDIA CMP 90HX and AMD Radeon Pro Vega 64. Find out which graphics card has better performance.
Graphics Processor (GPU)
| GA102 | GPU Name | Vega 10 |
| GA102-100-A1 | Model number | Vega 10 XT (215-0894200) |
| Ampere | Architecture | GCN 5.0 |
| Samsung | Foundry | GlobalFoundries |
| 8 nm | Process Size | 14 nm |
| 28,300 million | Transistors | 12,500 million |
| 628 mm² | Die Size | 495 mm² |
Graphics Card
| 2021 | Release Date | Jun 27th, 2017 |
| Mining GPUs | Family | Radeon Pro Mac (Vega Series) |
| Unreleased | Production | Active |
| PCIe 4.0 x16 | Bus Interface | PCIe 3.0 x16 |
Memory
| 10 GB | Memory Size | 16 GB |
| GDDR6X | Memory Type | HBM2 |
| 320 bit | Memory Bus | 2048 bit |
| 760.3 GB/s | Bandwidth | 402.4 GB/s |
Performance
| 136.8 GPixel/s | Pixel fillrate | 86.40 GPixel/s |
| 342.0 GTexel/s | Texture fillrate | 345.6 GTexel/s |
| 21.89 TFLOPS (1:1) | FP16 (half) performance | 22.12 TFLOPS (2:1) |
| 21.89 TFLOPS | FP32 (float) performance | 11.06 TFLOPS |
| 342.0 GFLOPS (1:64) | FP64 (double) performance | 691.2 GFLOPS (1:16) |
Clock Speeds
| 1440 MHz | Base Clock | 1250 MHz |
| 1710 MHz | Boost Clock | 1350 MHz |
| 1188 MHz 19 Gbps effective | Memory Clock | 786 MHz 1572 Mbps effective |
Render Config
| 6400 | Shading Units | 4096 |
| 200 | TMUs | 256 |
| 80 | ROPs | 64 |
| 128 KB (per SM) | L1 Cache | 16 KB (per CU) |
| 5 MB | L2 Cache | 4 MB |
Board Design
| Dual-slot | Slot Width | IGP |
| 320 W | Thermal design power (TDP) | 250 W |
| No outputs | Display Connectors | No outputs |
| 2x 8-pin | Power Connectors | None |
API support
| 12 Ultimate (12_2) | DirectX | 12 (12_1) |
| 4.6 | OpenGL | 4.6 |
| 3.0 | OpenCL | 2.1 |
| 1.2 | Vulkan | 1.2 |
| 6.6 | Shader Model | 6.4 |