AMD Radeon HD 8950 OEM vs NVIDIA Quadro K620
Graphics Processor
| GPU model | Tahiti | GM107 |
|---|---|---|
| GPU variant | Tahiti PRO (215-0821056) | GM107-850-A2 |
| Architecture | GCN 1.0 | Maxwell |
| Foundry | TSMC | TSMC |
| Manufacturing process | 28 nm | 28 nm |
| Number of transistors | 4,313 million | 1,870 million |
| Die size | 352 mm² | 148 mm² |
Graphics Card
| Release date | Jan 8th, 2013 | Jul 22nd, 2014 |
|---|---|---|
| Generation | Sea Islands | Quadro |
| Production | End-of-life | End-of-life |
| Interface | PCIe 3.0 x16 | PCIe 2.0 x16 |
| Predecessor | Southern Islands | — |
| Successor | Volcanic Islands | — |
| Reviews | — | 26 in our database |
Clocks
| Base clock | 850 MHz | 1058 MHz |
|---|---|---|
| Boost clock | 925 MHz | 1124 MHz |
| Memory clock | 1250 MHz 5 Gbps effective | 900 MHz 1800 Mbps effective |
Memory Configuration
| Memory size | 3 GB | 2 GB |
|---|---|---|
| Memory type | GDDR5 | DDR3 |
| Memory bus width | 384 bit | 128 bit |
| Bandwidth | 240.0 GB/s | 28.80 GB/s |
Render Configuration
| Shading units | 1792 | 384 |
|---|---|---|
| TMUs | 112 | 24 |
| ROPs | 32 | 16 |
| Compute units | 28 | — |
| Cache L1 | 16 KB (per CU) | 64 KB (per SMM) |
| Cache L2 | 768 KB | 2 MB |
| SMM count | — | 3 |
Performance
| Pixel rate | 29.60 GPixel/s | 17.98 GPixel/s |
|---|---|---|
| Texture rate | 103.6 GTexel/s | 26.98 GTexel/s |
| FP32 (float) performance | 3.315 TFLOPS | 863.2 GFLOPS |
| FP64 (double) performance | 828.8 GFLOPS (1:4) | 26.98 GFLOPS (1:32) |
Dimensions & Outputs
| Slot width | Dual-slot | Single-slot |
|---|---|---|
| Length | 267 mm 10.5 inches | 160 mm 6.3 inches |
| TDP | 200 W | 45 W |
| Suggested PSU | 550 W | 200 W |
| Outputs | 1x DVI1x HDMI2x mini-DisplayPort | 1x DVI1x DisplayPort |
| Power connectors | 2x 6-pin | None |
| Board number | C386-42 | P2012 |
| Width | — | 69 mm 2.7 inches |
API Support & Features
| DirectX | 12 (11_1) | 12 (11_0) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 1.2 | 3.0 |
| Vulkan | 1.2 | 1.1 |
| Shader model | 5.1 | 5.1 |
| CUDA | — | 5.0 |
