NVIDIA GeForce GTX 960 OEM vs NVIDIA Tesla P100 SXM2
Graphics Processor
| GPU model | GM204 | GP100 |
|---|---|---|
| GPU variant | GTX 960 OEM | GP100-890-A1 |
| Architecture | Maxwell 2.0 | Pascal |
| Foundry | TSMC | TSMC |
| Manufacturing process | 28 nm | 16 nm |
| Number of transistors | 5,200 million | 15,300 million |
| Die size | 398 mm² | 610 mm² |
Graphics Card
| Release date | Nov 26th, 2015 | Apr 5th, 2016 |
|---|---|---|
| Generation | GeForce 900 | Tesla |
| Production | End-of-life | End-of-life |
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Predecessor | GeForce 700 | — |
| Successor | GeForce 10 | — |
Clocks
| GPU clock | 924 MHz | — |
|---|---|---|
| Memory clock | 1253 MHz 5 Gbps effective | 715 MHz 1430 Mbps effective |
| Base clock | — | 1328 MHz |
| Boost clock | — | 1480 MHz |
Memory Configuration
| Memory size | 3 GB | 16 GB |
|---|---|---|
| Memory type | GDDR5 | HBM2 |
| Memory bus width | 192 bit | 4096 bit |
| Bandwidth | 120.3 GB/s | 732.2 GB/s |
Render Configuration
| Shading units | 1280 | 3584 |
|---|---|---|
| TMUs | 80 | 224 |
| ROPs | 48 | 96 |
| SMM count | 10 | — |
| Cache L1 | 48 KB (per SMM) | 24 KB (per SM) |
| Cache L2 | 1536 KB | 4 MB |
| SM count | — | 56 |
Performance
| Pixel rate | 44.35 GPixel/s | 142.1 GPixel/s |
|---|---|---|
| Texture rate | 73.92 GTexel/s | 331.5 GTexel/s |
| FP32 (float) performance | 2.365 TFLOPS | 10.61 TFLOPS |
| FP64 (double) performance | 73.92 GFLOPS (1:32) | 5.304 TFLOPS (1:2) |
| FP16 (half) performance | — | 21.22 TFLOPS (2:1) |
Dimensions & Outputs
| Slot width | Dual-slot | — |
|---|---|---|
| TDP | unknown | 300 W |
| Suggested PSU | 200 W | 700 W |
| Outputs | No outputs | No outputs |
| Power connectors | None | None |
API Support & Features
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.1 | 1.2 |
| CUDA | 5.2 | 6.0 |
| Shader model | 6.4 | 6.4 |
