NVIDIA CMP 170HX vs NVIDIA GeForce RTX 3060 Ti
Graphics Processor
| GPU model | GA100 | GA104 |
|---|---|---|
| GPU variant | GA100-105F-A1 | GA104-200-A1 |
| Architecture | Ampere | Ampere |
| Foundry | TSMC | Samsung |
| Manufacturing process | 7 nm | 8 nm |
| Number of transistors | 54,200 million | 17,400 million |
| Die size | 826 mm² | 392 mm² |
Graphics Card
| Release date | Sep 1st, 2021 | Dec 1st, 2020 |
|---|---|---|
| Generation | Mining GPUs | GeForce 30 |
| Production | Active | Active |
| Interface | PCIe 4.0 x4 | PCIe 4.0 x16 |
| Launch price | 4,299 USD | 399 USD |
| gpu.details.availability | — | Dec 2nd, 2020 |
| Predecessor | — | GeForce 20 |
| Reviews | — | 64 in our database |
Clocks
| Base clock | 1140 MHz | 1410 MHz |
|---|---|---|
| Boost clock | 1410 MHz | 1665 MHz |
| Memory clock | 1458 MHz 2.9 Gbps effective | 1750 MHz 14 Gbps effective |
Memory Configuration
| Memory size | 16 GB | 8 GB |
|---|---|---|
| Memory type | HBM2e | GDDR6 |
| Memory bus width | 4096 bit | 256 bit |
| Bandwidth | 1,493 GB/s | 448.0 GB/s |
Render Configuration
| Shading units | 4480 | 4864 |
|---|---|---|
| TMUs | 280 | 152 |
| ROPs | 128 | 80 |
| SM count | 70 | 38 |
| Tensor cores | 280 | 152 |
| Cache L1 | 192 KB (per SM) | 128 KB (per SM) |
| Cache L2 | 8 MB | 4 MB |
| RT cores | — | 38 |
Performance
| Pixel rate | 180.5 GPixel/s | 133.2 GPixel/s |
|---|---|---|
| Texture rate | 394.8 GTexel/s | 253.1 GTexel/s |
| FP16 (half) performance | 50.53 TFLOPS (4:1) | 16.20 TFLOPS (1:1) |
| FP32 (float) performance | 12.63 TFLOPS | 16.20 TFLOPS |
| FP64 (double) performance | 6.317 TFLOPS (1:2) | 253.1 GFLOPS (1:64) |
Dimensions & Outputs
| Slot width | IGP | Dual-slot |
|---|---|---|
| TDP | 250 W | 200 W |
| Suggested PSU | 600 W | 550 W |
| Outputs | No outputs | 1x HDMI3x DisplayPort |
| Power connectors | 2x 8-pin | 1x 12-pin |
| Length | — | 242 mm 9.5 inches |
| Width | — | 112 mm 4.4 inches |
| Board number | — | PG142 SKU 20 |
API Support & Features
| DirectX | — | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | — | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | — | 1.2 |
| CUDA | 8.0 | 8.6 |
| Shader model | — | 6.6 |
