AMD Radeon Instinct MI8 vs NVIDIA GeForce GTX 480
Graphics Processor
| GPU model | Fiji | GF100 |
|---|---|---|
| GPU variant | Fiji XT | GF100-375-A3 |
| Architecture | GCN 3.0 | Fermi |
| Foundry | TSMC | TSMC |
| Manufacturing process | 28 nm | 40 nm |
| Number of transistors | 8,900 million | 3,100 million |
| Die size | 596 mm² | 529 mm² |
Graphics Card
| Release date | Dec 12th, 2016 | Mar 26th, 2010 |
|---|---|---|
| Generation | Radeon Instinct | GeForce 400 |
| Production | End-of-life | End-of-life |
| Interface | PCIe 3.0 x16 | PCIe 2.0 x16 |
| Launch price | — | 499 USD |
| Reviews | — | 84 in our database |
| Predecessor | — | GeForce 200 |
| Successor | — | GeForce 500 |
Clocks
| GPU clock | 1000 MHz | 701 MHz |
|---|---|---|
| Memory clock | 500 MHz 1000 Mbps effective | 924 MHz 3.7 Gbps effective |
| Shader clock | — | 1401 MHz |
Memory Configuration
| Memory size | 4 GB | 1536 MB |
|---|---|---|
| Memory type | HBM | GDDR5 |
| Memory bus width | 4096 bit | 384 bit |
| Bandwidth | 512.0 GB/s | 177.4 GB/s |
Render Configuration
| Shading units | 4096 | 480 |
|---|---|---|
| TMUs | 256 | 60 |
| ROPs | 64 | 48 |
| Compute units | 64 | — |
| Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
| Cache L2 | 2 MB | 768 KB |
| SM count | — | 15 |
Performance
| Pixel rate | 64.00 GPixel/s | 21.03 GPixel/s |
|---|---|---|
| Texture rate | 256.0 GTexel/s | 42.06 GTexel/s |
| FP16 (half) performance | 8.192 TFLOPS (1:1) | — |
| FP32 (float) performance | 8.192 TFLOPS | 1,345 GFLOPS |
| FP64 (double) performance | 512.0 GFLOPS (1:16) | 168.1 GFLOPS (1:8) |
Dimensions & Outputs
| Slot width | Dual-slot | Dual-slot |
|---|---|---|
| Length | 152 mm 6 inches | 267 mm 10.5 inches |
| Width | 111 mm 4.4 inches | — |
| TDP | 175 W | 250 W |
| Suggested PSU | 450 W | 600 W |
| Outputs | No outputs | 2x DVI1x mini-HDMI |
| Power connectors | 1x 8-pin | 1x 6-pin + 1x 8-pin |
| Board number | — | P1022 |
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 | — | 2.0 |
