AMD Radeon R9 M470X vs NVIDIA Tesla K40m
Graphics Processor
| GPU model | Emerald | GK110B |
|---|---|---|
| GPU variant | Emerald XT | — |
| Architecture | GCN 2.0 | Kepler |
| Foundry | TSMC | TSMC |
| Manufacturing process | 28 nm | 28 nm |
| Number of transistors | 2,080 million | 7,080 million |
| Die size | 160 mm² | 561 mm² |
Mobile graphics
| Release date | May 15th, 2016 | — |
|---|---|---|
| Generation | Crystal System (R9 M400) | — |
| Production | End-of-life | — |
| Interface | PCIe 3.0 x16 | — |
| Predecessor | Solar System | — |
| Successor | Mobility Radeon | — |
Clocks
| Base clock | 1000 MHz | 745 MHz |
|---|---|---|
| Boost clock | 1100 MHz | 876 MHz |
| Memory clock | 1500 MHz 6 Gbps effective | 1502 MHz 6 Gbps effective |
Memory Configuration
| Memory size | 4 GB | 12 GB |
|---|---|---|
| Memory type | GDDR5 | GDDR5 |
| Memory bus width | 128 bit | 384 bit |
| Bandwidth | 96.00 GB/s | 288.4 GB/s |
Render Configuration
| Shading units | 896 | 2880 |
|---|---|---|
| TMUs | 56 | 240 |
| ROPs | 16 | 48 |
| Compute units | 14 | — |
| Cache L1 | 16 KB (per CU) | 16 KB (per SMX) |
| Cache L2 | 256 KB | 1536 KB |
| SMX count | — | 15 |
Performance
| Pixel rate | 17.60 GPixel/s | 52.56 GPixel/s |
|---|---|---|
| Texture rate | 61.60 GTexel/s | 210.2 GTexel/s |
| FP32 (float) performance | 1.971 TFLOPS | 5.046 TFLOPS |
| FP64 (double) performance | 123.2 GFLOPS (1:16) | 1.682 TFLOPS (1:3) |
Dimensions & Outputs
| TDP | unknown | 245 W |
|---|---|---|
| Outputs | No outputs | No outputs |
| Slot width | — | Dual-slot |
| Length | — | 267 mm 10.5 inches |
| Suggested PSU | — | 550 W |
API Support & Features
| DirectX | 12 (12_0) | 12 (11_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 3.0 |
| Vulkan | 1.2 | 1.1 |
| Shader model | 6.3 | 5.1 |
| CUDA | — | 3.5 |
Other Features
Graphics Card
| Release date | — | Nov 22nd, 2013 |
|---|---|---|
| Generation | — | Tesla |
| Production | — | End-of-life |
| Launch price | — | 7,699 USD |
| Interface | — | PCIe 3.0 x16 |
