NVIDIA A100 PCIe vs NVIDIA GeForce PCX 4300
Graphics Processor
| GPU model | GA100 | NV19 |
|---|---|---|
| Architecture | Ampere | Celsius |
| Foundry | TSMC | TSMC |
| Manufacturing process | 7 nm | 150 nm |
| Number of transistors | 54,200 million | 29 million |
| Die size | 826 mm² | 65 mm² |
Graphics Card
| Release date | Jun 22nd, 2020 | Feb 19th, 2004 |
|---|---|---|
| Generation | Tesla | GeForce PCX |
| Production | Active | End-of-life |
| Interface | PCIe 4.0 x16 | PCIe 1.0 x16 |
| Predecessor | — | GeForce 4 Ti |
| Successor | — | GeForce 6 PCIe |
Clocks
| GPU clock | 1410 MHz | 250 MHz |
|---|---|---|
| Memory clock | 1215 MHz 2.4 Gbps effective | 166 MHz 332 Mbps effective |
| Base clock | 765 MHz | — |
| Boost clock | 1410 MHz | — |
Memory Configuration
| Memory size | 40 GB | 64 MB |
|---|---|---|
| Memory type | HBM2E | DDR |
| Memory bus width | 5120 bit | 64 bit |
| Bandwidth | 1,555 GB/s | 2.656 GB/s |
Render Configuration
| Shading units | 6912 | — |
|---|---|---|
| TMUs | 432 | 2 |
| ROPs | 160 | 2 |
| SM count | 108 | — |
| Tensor cores | 432 | — |
| Cache L1 | 192 KB (per SM) | — |
| Cache L2 | 40 MB | — |
| Pixel shaders | — | 2 |
| Vertex shaders | — | 0 |
Performance
| Pixel rate | 225.6 GPixel/s | 500.0 MPixel/s |
|---|---|---|
| Texture rate | 609.1 GTexel/s | 500.0 MTexel/s |
| FP16 (half) performance | 77.97 TFLOPS (4:1) | — |
| FP32 (float) performance | 19.49 TFLOPS | — |
| FP64 (double) performance | 9.746 TFLOPS (1:2) | — |
Dimensions & Outputs
| Slot width | Dual-slot | Single-slot |
|---|---|---|
| Length | 267 mm 10.5 inches | — |
| TDP | 250 W | unknown |
| Suggested PSU | 600 W | 200 W |
| Outputs | No outputs | 1x DVI1x VGA1x S-Video |
| Power connectors | 8-pin EPS | None |
| Board number | P1001 SKU 200 | — |
API Support & Features
| DirectX | — | 7.0 |
|---|---|---|
| OpenGL | — | 1.5 |
| OpenCL | 3.0 | — |
| Vulkan | — | — |
| CUDA | 8.0 | — |
| Shader model | — | — |
| Pixel shader | — | 1.1 |
| Vertex shader | — | 1.1 |
