AMD Radeon HD 7950 vs NVIDIA GeForce GTX 1050 Ti
Graphics Processor
| GPU model | Tahiti | GP107 |
|---|---|---|
| GPU variant | Tahiti PRO (215-0821056) | GP107-400-A1 |
| Architecture | GCN 1.0 | Pascal |
| Foundry | TSMC | Samsung |
| Manufacturing process | 28 nm | 14 nm |
| Number of transistors | 4,313 million | 3,300 million |
| Die size | 352 mm² | 132 mm² |
Graphics Card
| Release date | Jan 31st, 2012 | Oct 25th, 2016 |
|---|---|---|
| Generation | Southern Islands | GeForce 10 |
| Production | End-of-life | End-of-life |
| Launch price | 449 USD | 139 USD |
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Reviews | 118 in our database | 58 in our database |
| Predecessor | Northern Islands | GeForce 900 |
| Successor | Sea Islands | GeForce 20 |
Clocks
| GPU clock | 800 MHz | — |
|---|---|---|
| Memory clock | 1250 MHz 5 Gbps effective | 1752 MHz 7 Gbps effective |
| Base clock | — | 1291 MHz |
| Boost clock | — | 1392 MHz |
Memory Configuration
| Memory size | 3 GB | 4 GB |
|---|---|---|
| Memory type | GDDR5 | GDDR5 |
| Memory bus width | 384 bit | 128 bit |
| Bandwidth | 240.0 GB/s | 112.1 GB/s |
Render Configuration
| Shading units | 1792 | 768 |
|---|---|---|
| TMUs | 112 | 48 |
| ROPs | 32 | 32 |
| Compute units | 28 | — |
| Cache L1 | 16 KB (per CU) | 48 KB (per SM) |
| Cache L2 | 768 KB | 1024 KB |
| SM count | — | 6 |
Performance
| Pixel rate | 25.60 GPixel/s | 44.54 GPixel/s |
|---|---|---|
| Texture rate | 89.60 GTexel/s | 66.82 GTexel/s |
| FP32 (float) performance | 2.867 TFLOPS | 2.138 TFLOPS |
| FP64 (double) performance | 716.8 GFLOPS (1:4) | 66.82 GFLOPS (1:32) |
| FP16 (half) performance | — | 33.41 GFLOPS (1:64) |
Dimensions & Outputs
| Slot width | Dual-slot | Dual-slot |
|---|---|---|
| Length | 278 mm 10.9 inches | 145 mm 5.7 inches |
| Width | 111 mm 4.4 inches | 111 mm 4.4 inches |
| Height | 38 mm 1.5 inches | — |
| TDP | 200 W | 75 W |
| Suggested PSU | 550 W | 250 W |
| Outputs | 1x DVI1x HDMI2x mini-DisplayPort | 1x DVI1x HDMI1x DisplayPort |
| Power connectors | 2x 6-pin | None |
| Board number | C386-37 | PG210 |
API Support & Features
| DirectX | 12 (11_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 1.2 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader model | 5.1 | 6.4 |
| CUDA | — | 6.1 |
