AMD Radeon R7 240 OEM vs NVIDIA GeForce 8800 GTS 640
Graphics Processor
| GPU model | Oland | G80 |
|---|---|---|
| Architecture | GCN 1.0 | Tesla |
| Foundry | TSMC | TSMC |
| Manufacturing process | 28 nm | 90 nm |
| Number of transistors | 950 million | 681 million |
| Die size | 77 mm² | 484 mm² |
| GPU variant | — | G80-100-K0-A2 |
Graphics Card
| Release date | Nov 1st, 2013 | Nov 8th, 2006 |
|---|---|---|
| Generation | Volcanic Islands | GeForce 8 |
| Production | End-of-life | End-of-life |
| Interface | PCIe 3.0 x8 | PCIe 1.0 x16 |
| Predecessor | Sea Islands | GeForce 7 PCIe |
| Successor | Pirate Islands | GeForce 9 |
| Launch price | — | 449 USD |
| Reviews | — | 403 in our database |
Clocks
| Base clock | 730 MHz | — |
|---|---|---|
| Boost clock | 780 MHz | — |
| Memory clock | 900 MHz 1800 Mbps effective | 792 MHz 1584 Mbps effective |
| GPU clock | — | 513 MHz |
| Shader clock | — | 1188 MHz |
Memory Configuration
| Memory size | 2 GB | 640 MB |
|---|---|---|
| Memory type | DDR3 | GDDR3 |
| Memory bus width | 128 bit | 320 bit |
| Bandwidth | 28.80 GB/s | 63.36 GB/s |
Render Configuration
| Shading units | 320 | 96 |
|---|---|---|
| TMUs | 20 | 24 |
| ROPs | 8 | 20 |
| Compute units | 5 | — |
| Cache L1 | 16 KB (per CU) | — |
| Cache L2 | 256 KB | 80 KB |
| SM count | — | 12 |
Performance
| Pixel rate | 6.240 GPixel/s | 10.26 GPixel/s |
|---|---|---|
| Texture rate | 15.60 GTexel/s | 24.62 GTexel/s |
| FP32 (float) performance | 499.2 GFLOPS | 228.1 GFLOPS |
| FP64 (double) performance | 31.20 GFLOPS (1:16) | — |
Dimensions & Outputs
| Slot width | Single-slot | Dual-slot |
|---|---|---|
| TDP | 50 W | 143 W |
| Suggested PSU | 250 W | 300 W |
| Outputs | 1x DVI1x HDMI1x VGA | 2x DVI1x S-Video |
| Power connectors | None | 1x 6-pin |
| Board number | C552 | P356 |
| Length | — | 267 mm 10.5 inches |
API Support & Features
| DirectX | 12 (11_1) | 11.1 (10_0) |
|---|---|---|
| OpenGL | 4.6 | 3.3 |
| OpenCL | 1.2 | 1.1 (1.0) |
| Vulkan | 1.2 | — |
| Shader model | 5.1 | 4.0 |
| CUDA | — | 1.0 |
