ATI Radeon HD 4870 vs NVIDIA GeForce GTS 150 OEM
Graphics Processor
| GPU model | RV770 | G92 |
|---|---|---|
| GPU variant | RV770 XT (215-0669049) | — |
| Architecture | TeraScale | Tesla |
| Foundry | TSMC | TSMC |
| Manufacturing process | 55 nm | 65 nm |
| Number of transistors | 956 million | 754 million |
| Die size | 256 mm² | 324 mm² |
Graphics Card
| Release date | Jun 25th, 2008 | Mar 10th, 2009 |
|---|---|---|
| Generation | Radeon R700 | GeForce 100 |
| Production | End-of-life | End-of-life |
| Launch price | 299 USD | — |
| Interface | PCIe 2.0 x16 | PCIe 2.0 x16 |
| Reviews | 135 in our database | — |
| Predecessor | Radeon R600 | GeForce 9 |
| Successor | Evergreen | GeForce 200 |
Clocks
| GPU clock | 750 MHz | 738 MHz |
|---|---|---|
| Memory clock | 900 MHz 3.6 Gbps effective | 1000 MHz 2 Gbps effective |
| Shader clock | — | 1836 MHz |
Memory Configuration
| Memory size | 512 MB | 1024 MB |
|---|---|---|
| Memory type | GDDR5 | GDDR3 |
| Memory bus width | 256 bit | 256 bit |
| Bandwidth | 115.2 GB/s | 64.00 GB/s |
Render Configuration
| Shading units | 800 | 128 |
|---|---|---|
| TMUs | 40 | 64 |
| ROPs | 16 | 16 |
| Compute units | 10 | — |
| Cache L1 | 16 KB (per CU) | — |
| Cache L2 | 256 KB | 64 KB |
| SM count | — | 16 |
Performance
| Pixel rate | 12.00 GPixel/s | 11.81 GPixel/s |
|---|---|---|
| Texture rate | 30.00 GTexel/s | 47.23 GTexel/s |
| FP32 (float) performance | 1,200 GFLOPS | 470.0 GFLOPS |
| FP64 (double) performance | 240.0 GFLOPS (1:5) | — |
Dimensions & Outputs
| Slot width | Dual-slot | Dual-slot |
|---|---|---|
| Length | 241 mm 9.5 inches | 267 mm 10.5 inches |
| Width | 111 mm 4.4 inches | — |
| Height | 40 mm 1.6 inches | — |
| TDP | 150 W | 141 W |
| Suggested PSU | 450 W | 300 W |
| Outputs | 2x DVI1x S-Video | 2x DVI1x S-Video |
| Power connectors | 2x 6-pin | 2x 6-pin |
| Board number | B507-31 | — |
API Support & Features
| DirectX | 10.1 (10_1) | 11.1 (10_0) |
|---|---|---|
| OpenGL | 3.3 | 3.3 |
| OpenCL | 1.1 | 1.1 |
| Vulkan | — | — |
| Shader model | 4.1 | 4.0 |
| CUDA | — | 1.1 |
