AMD Radeon R7 M260 vs NVIDIA GeForce 820M
Graphics Processor
| GPU model | Topaz | GF117 |
|---|---|---|
| GPU variant | Topaz XT (216-0864030) | N15V-GM-B-A2 |
| Architecture | GCN 3.0 | Fermi 2.0 |
| Foundry | TSMC | TSMC |
| Manufacturing process | 28 nm | 28 nm |
| Number of transistors | 1,550 million | 585 million |
| Die size | 125 mm² | 116 mm² |
Mobile graphics
| Release date | Jun 11th, 2014 | Nov 27th, 2013 |
|---|---|---|
| Generation | Crystal System (R7 M200) | GeForce 800M |
| Production | End-of-life | End-of-life |
| Interface | PCIe 3.0 x8 | PCIe 2.0 x16 |
| Predecessor | Solar System | GeForce 700M |
| Successor | Mobility Radeon | GeForce 900M |
Clocks
| Base clock | 940 MHz | — |
|---|---|---|
| Boost clock | 980 MHz | — |
| Memory clock | 900 MHz 1800 Mbps effective | 900 MHz 1800 Mbps effective |
| GPU clock | — | 625 MHz |
| Shader clock | — | 1250 MHz |
Memory Configuration
| Memory size | 2 GB | 1024 MB |
|---|---|---|
| Memory type | DDR3 | DDR3 |
| Memory bus width | 64 bit | 64 bit |
| Bandwidth | 14.40 GB/s | 14.40 GB/s |
Render Configuration
| Shading units | 384 | 96 |
|---|---|---|
| TMUs | 24 | 16 |
| ROPs | 8 | 8 |
| Compute units | 6 | — |
| Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
| Cache L2 | 128 KB | 128 KB |
| SM count | — | 2 |
Performance
| Pixel rate | 7.840 GPixel/s | 2.500 GPixel/s |
|---|---|---|
| Texture rate | 23.52 GTexel/s | 10.00 GTexel/s |
| FP16 (half) performance | 752.6 GFLOPS (1:1) | — |
| FP32 (float) performance | 752.6 GFLOPS | 240.0 GFLOPS |
| FP64 (double) performance | 47.04 GFLOPS (1:16) | 20.00 GFLOPS (1:12) |
Dimensions & Outputs
| TDP | unknown | 15 W |
|---|---|---|
| Outputs | No outputs | No outputs |
| Board number | C720 | — |
API Support & Features
| DirectX | 12 (12_0) | 12 (11_0) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 1.1 |
| Vulkan | 1.2 | — |
| Shader model | 6.3 | 5.1 |
| CUDA | — | 2.1 |
