NVIDIA Tesla P100 PCIe 16 GB vs NVIDIA Tesla P4
Graphics Processor
| GPU model | GP100 | GP104 |
|---|---|---|
| GPU variant | GP100-893-A1 | GP104-895-A1 |
| Architecture | Pascal | Pascal |
| Foundry | TSMC | TSMC |
| Manufacturing process | 16 nm | 16 nm |
| Number of transistors | 15,300 million | 7,200 million |
| Die size | 610 mm² | 314 mm² |
Graphics Card
| Release date | Jun 20th, 2016 | Sep 13th, 2016 |
|---|---|---|
| Generation | Tesla | Tesla |
| Production | End-of-life | End-of-life |
| Launch price | 5,699 USD | — |
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Clocks
| Base clock | 1190 MHz | 886 MHz |
|---|---|---|
| Boost clock | 1329 MHz | 1114 MHz |
| Memory clock | 715 MHz 1430 Mbps effective | 1502 MHz 6 Gbps effective |
Memory Configuration
| Memory size | 16 GB | 8 GB |
|---|---|---|
| Memory type | HBM2 | GDDR5 |
| Memory bus width | 4096 bit | 256 bit |
| Bandwidth | 732.2 GB/s | 192.3 GB/s |
Render Configuration
| Shading units | 3584 | 2560 |
|---|---|---|
| TMUs | 224 | 160 |
| ROPs | 96 | 64 |
| SM count | 56 | 20 |
| Cache L1 | 24 KB (per SM) | 48 KB (per SM) |
| Cache L2 | 4 MB | 2 MB |
Performance
| Pixel rate | 127.6 GPixel/s | 71.30 GPixel/s |
|---|---|---|
| Texture rate | 297.7 GTexel/s | 178.2 GTexel/s |
| FP16 (half) performance | 19.05 TFLOPS (2:1) | 89.12 GFLOPS (1:64) |
| FP32 (float) performance | 9.526 TFLOPS | 5.704 TFLOPS |
| FP64 (double) performance | 4.763 TFLOPS (1:2) | 178.2 GFLOPS (1:32) |
Dimensions & Outputs
| Slot width | Dual-slot | Single-slot |
|---|---|---|
| Length | 267 mm 10.5 inches | 168 mm 6.6 inches |
| TDP | 250 W | 75 W |
| Suggested PSU | 600 W | 250 W |
| Outputs | No outputs | No outputs |
| Power connectors | 1x 8-pin | None |
API Support & Features
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| CUDA | 6.0 | 6.1 |
| Shader model | 6.4 | 6.4 |
