NVIDIA Tesla K40c vs NVIDIA GeForce RTX 4090
| |
| Price | $7,699.00 $1,599.00 |
| Our Rating | |
| Brand | NVIDIA NVIDIA |
| Category | GPU Benchmarks GPU Benchmarks |
BASIC GPU INFO
| GPU name | GK180 AD102 |
| Manufacturer | TSMC NVIDIA |
| Released date | Oct 8th, 2013 Sep 20th, 2022 |
| Launch price | $7,699 $1,599 |
| Foundry | TSMC |
| Purpose | gaming |
| GPU codename | AD102-300-A1 |
| Architecture | Kepler Ada Lovelace |
| Generation | Tesla Kepler (Kxx) GeForce 40 |
| Production | End-of-life Available |
| Successor | Tesla Maxwell GeForce 50 |
| Predecessor | GeForce 30 |
BOARD DESIGN
| TDP | 245 W 450 W |
| Slot width | Dual-slot Triple-slot |
| Power connectors | 1x 6-pin + 1x 8-pin 1x 16-pin |
| Length | N/A 304 mm 12 inches |
| Height | N/A 61 mm 2.4 inches |
| Width | N/A 137 mm 5.4 inches |
| Outputs | No outputs available on this GPU 1x HDMI 2.1 and 3x DisplayPort 1.4a |
| Board number | P2081 SKU 206 PG139 SKU 330 |
| Weight | N/A |
| PSU | 850 W |
| Bus interface | PCIe 4.0 x16 |
GRAPHICS PROCESSING UNIT
| Base clock | 745 MHz 2235 MHz |
| Boost clock | 876 MHz 2520 MHz |
| Transistors | 7,080 million 76,300 million |
| Process size | 28 nm 5 nm |
| Process type | N/A |
| Die size | 561 mm² 609 mm² |
| MCD Die density | N/A |
| Chip package | BGA-2152 |
| Density | 12.6M / mm² 125.3M / mm² |
GPU MEMORY
| Memory type | GDDR5 GDDR6X |
| Memory size | 12 GB 24 GB |
| Memory bus | 384 bit 384 bit |
| Bandwidth | 288.4 GB/s 1.01 TB/s |
| Memory clock | 1502 MHz 6 Gbps more effective 1313 MHz 21 Gbps more effective |
GRAPHICS FEATURES (API)
| Vulkan | 1.2.175 1.3 |
| DirectX | 12 (11_0) 12 Ultimate (12_2) |
| OpenGL | 4.6 4.6 |
| OpenCL | 3.0 3.0 |
| Display port | N/A N/A |
| Shader model | 5.1 6.8 |
| Ray tracing | N/A N/A |
| CUDA | 8.9 |
CONFIGURATION
| ROPs | 48 176 |
| Shading units | 2880 16384 |
| TMUs | 240 512 |
| Compute units | N/A |
| L1 cache | 16 KB (per SMX) 128 KB (per SM) |
| L2 cache | 1536 KB 72 MB |
GPU PERFORMANCE
| Pixel rate | 52.56 GPixel/s 443.5 GPixel/s |
| Texture rate | 210.2 GTexel/s 1,290 GTexel/s |
| FP16 (half) | N/A 82.58 TFLOPS (1:1) |
| FP32 (float) | 5.046 TFLOPS 82.58 TFLOPS |
| FP64 (double) | 1.682 TFLOPS (1:3) 1,290 GFLOPS (1:64) |
|
