NVIDIA GRID K1 vs NVIDIA Tesla K40m
Graphics Processor
| GPU model | GK107 | GK110B |
|---|---|---|
| GPU variant | GK107-450-A2 | — |
| Architecture | Kepler | Kepler |
| Foundry | TSMC | TSMC |
| Manufacturing process | 28 nm | 28 nm |
| Number of transistors | 1,270 million | 7,080 million |
| Die size | 118 mm² | 561 mm² |
Graphics Card
| Release date | Mar 18th, 2013 | Nov 22nd, 2013 |
|---|---|---|
| Generation | GRID | Tesla |
| Production | End-of-life | End-of-life |
| Launch price | 4,140 USD | 7,699 USD |
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Clocks
| GPU clock | 850 MHz | — |
|---|---|---|
| Memory clock | 891 MHz 1782 Mbps effective | 1502 MHz 6 Gbps effective |
| Base clock | — | 745 MHz |
| Boost clock | — | 876 MHz |
Memory Configuration
| Memory size | 4 GB | 12 GB |
|---|---|---|
| Memory type | DDR3 | GDDR5 |
| Memory bus width | 128 bit | 384 bit |
| Bandwidth | 28.51 GB/s | 288.4 GB/s |
Render Configuration
| Shading units | 192 | 2880 |
|---|---|---|
| TMUs | 16 | 240 |
| ROPs | 16 | 48 |
| SMX count | 1 | 15 |
| Cache L1 | 16 KB (per SMX) | 16 KB (per SMX) |
| Cache L2 | 256 KB | 1536 KB |
Performance
| Pixel rate | 3.400 GPixel/s | 52.56 GPixel/s |
|---|---|---|
| Texture rate | 13.60 GTexel/s | 210.2 GTexel/s |
| FP32 (float) performance | 326.4 GFLOPS | 5.046 TFLOPS |
| FP64 (double) performance | 13.60 GFLOPS (1:24) | 1.682 TFLOPS (1:3) |
Dimensions & Outputs
| Slot width | Dual-slot | Dual-slot |
|---|---|---|
| Length | 267 mm 10.5 inches | 267 mm 10.5 inches |
| TDP | 130 W | 245 W |
| Suggested PSU | 300 W | 550 W |
| Outputs | No outputs | No outputs |
| Power connectors | 1x 6-pin | — |
| Board number | P2401 SKU 502 | — |
API Support & Features
| DirectX | 12 (11_0) | 12 (11_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.1 | 1.1 |
| CUDA | 3.0 | 3.5 |
| Shader model | 5.1 | 5.1 |
