Descripción
Compatible in all systems that accept an NVIDIA Quadro RTX 4000
| CUDA Cores | 2304 |
|---|---|
| RT Cores | 36 |
| Tensor Cores | 288 |
| RTX-OPS | 43T |
| Rays Cast | 6 Giga Rays/Sec |
| Peak Single Precision FP32 Performance | 7.1 TFLOPS |
| Peak Half Precision FP16 performance | 14.2 TFLOPS |
| Peak INT8 Performance | 28.5 TOPS |
| Deep Learning TFLOPS | 57.0 Tensor TFLOPS |
| GPU Memory | 8 GB GDDR6 |
| Memory Bandwidth | 416 GB/Secc |
| System Interface | PCI Express 3.0 x16 |
| Display Connectors | DisplayPort 1.4 (3) + VirtualLink |
| Max Power Consumption (With VirtualLink) | 125 W (160 W, Includes USB Type-C) NVIDIA Quadro Power Guidelines |
| Max Digital Resolution | 7680 x 4320 x36 bpp at 60hz NVIDIA Quadro and NVS Display Resolution Support |
NVIDIA CUDA PARALLEL PROCESSING ARCHITECTURE
- New RT (Ray Tracing) Core per SM
- Turing SM Architecture (streaming multi-processor design that delivers greater processing efficiency)
- Dynamic Parallelism (GPU dynamically spawns new threads without going back to the CPU)
- Mixed-precision (1-, 4-, 8-, 16-, 32- and 64-bit) computing
- API support includes: CUDA C, CUDA C++, DirectCompute 5.0, OpenCL, Java, Python, and Fortran
- Configurable up to 96 KB of RAM (dedicated shared memory size per SM)
Valoraciones
No hay valoraciones aún.