NVIDIA has also brought its massive army of workstation-ready RTX graphics cards which include the RTX A6000, A5000, A4000, A3000 & A2000 to the desktop and laptop segment. Designed for professionals and content creators, the new GPUs pack a whole lot of punch for users of each category, whether they want high-performance on their desks or on the go.
NVIDIA RTX A5000, A4000, A3000, A2000 Workstation Ampere Graphics Cards Power Pro Workloads On Desktops & Laptops
The NVIDIA RTX A5000 and RTX A4000 graphics cards are based on the Ampere GPU architecture and are siblings to the flagship RTX A6000. Currently, the NVIDIA RTX A6000 uses the full GA102 GPU and while the RTX A4000 does feature the full GA106 GPU core, the RTX A5000 relies on a cut-down GA102 GPU.
NVIDIA RTX A5000 Desktop Specifications
The NVIDIA RTX A5000 features a cut-down GA102 GPU with 8192 CUDA cores, 64 Tensor Cores. It comes with 24 GB of GDDR6 memory which operates across a 384-bit bus interface and has power delivered through an 8+6 pin connector configuration. The card makes use of an active-fan cooling solution to dissipate its 230W TDP. The card offers 27.8 TFLOPs of FP32, 54.2 TFLOPs of RT & 222.2 TFLOPs of tensor core performance.
NVIDIA RTX A4000 Desktop Specifications
The NVIDIA RTX A4000 features the full GA106 GPU with 6144 CUDA cores, 48 Tensor Cores. It comes with 16 GB of GDDR6 memory which operates across a 256-bit bus interface and has power delivered through a single 8-pin connector configuration. The card makes use of an active-fan cooling solution to dissipate its 140W TDP. The card offers 19.2 TFLOPs of FP32, 37.4 TFLOPs of RT & 153.4 TFLOPs of tensor core performance. The RTX A4000 also makes use of a single-slot design while the RTX A5000 relies on a dual-slot solution.
Both cards feature four DP1.4 display outputs, Quadro Sync technology. The RTX A5000 also packs vGPU support and can be plugged in 2-Way NVLINK.
NVIDIA Ampere Workstation Graphics Cards:
| Graphics Card | NVIDIA RTX A4000 | NVIDIA RTX A5000 | NVIDIA RTX A6000 |
|---|---|---|---|
| GPU | Ampere GA106 GPU | Ampere GA102 GPU | Ampere GA102 GPU |
| GPU Process | Samsung 8nm | Samsung 8nm | Samsung 8nm |
| Die Size | 276 mm² | 628mm² | 628mm² |
| GPU Cores | 6,144 | 8,192 | 10752 |
| Tensor Cores | 192 | 256 | 336 |
| Boost Clock | TBC | TBC | 1860 MHz |
| Single Precision | TBC | TBC | 40 TFLOPs |
| VRAM | 16 GB GDDR6 | 24 GB GDDR6 | 48 GB GDDR6 |
| NVLINK VRAM | TBC | TBC | 96 GB GDDR6 |
| Memory Bus | 256-bit | 384-bit | 284-bit |
| Memory Bandwidth | 448 GB/s | 768 GB/s | 768 GB/s |
| TDP | 140W | 230W | 300W |
| Launch Price | TBC | TBC | $4650 US |
| Launch Date | TBC | TBC | December, 2020 |
All the NVIDIA RTX GPUs feature the latest technologies in the NVIDIA Ampere architecture:
- Second-Generation RT Cores: Up to 2x the throughput of the previous generation, with the ability to run concurrent ray tracing, shading, and denoising tasks.
- Third-generation Tensor Cores: Up to 2x the throughput of the previous generation, up to 10x with sparsity, with support for new TF32 and BFloat16 data formats.
- CUDA Cores: Up to 2.5x the FP32 throughput of the previous generation for significant increases in graphics and compute workloads.
Desktop GPU features and technology include:
- Up to 24GB of GPU memory: Double the memory of the previous generation, the RTX A4000 with 16GB GDDR6 memory and the RTX A5000 with 24GB of GDDR6 memory both support ECC memory for error-free computing. The RTX A5000 is expandable up to 48GB of memory using NVIDIA NVLink® to connect two GPUs.
- Virtualization: The RTX A5000 supports NVIDIA RTX vWS software for multiple high-performance virtual workstation instances that enable remote users to share resources to drive high-end design, AI, and compute workloads.
- PCIe Gen 4: Doubles the bandwidth of the previous generation and speeds up data transfers for data-intensive tasks such as AI, data science, and creating 3D models.
Laptop GPU features and technology include:
- Third-Gen Max-Q technology: For thin and light laptops that perform quieter and more efficiently with Dynamic Boost 2.0, WhisperMode 2.0, Resizable BAR, and NVIDIA DLSS technology.
- Up to 16GB of GPU memory: For the largest models, scenes, assemblies, and advanced multi-application workflows.
| NVIDIA RTX Ampere Workstation Mobile GPUs | ||||
|---|---|---|---|---|
| RTX A2000 | RTX A3000 | RTX A4000 | RTX A5000 | |
| GPU | GA106 | GA104 | GA104 | GA102 |
| Transistors | 12 billion | 17.4 billion | 17.4 billion | 28 billion |
| Fabrication Node | 8 nm | 8 nm | 8 nm | 8 nm |
| Chip size | 276 mm² | 392.5 mm² | 392.5 mm² | 628.4 mm² |
| FP32 ALUs | 2,560 | 4,096 | 5,120 | 6,144 |
| INT32 ALUs | 1,280 | 2,048 | 2,560 | 3,072 |
| SMs | 20th | 32 | 40 | 48 |
| Tensor cores | 80 | 128 | 160 | 192 |
| RT Cores | 20th | 32 | 40 | 48 |
| FP32 performance | 9.3 TFLOPS | 12.8 TFLOPS | 17.8 TFLOPS | 21.7 TFLOPS |
| RT performance | 18.2 TFLOPS | 25.0 TFLOPS | 34.8 TFLOPS | 75.6 TFLOPS |
| Tensor performance | 74.7 TFLOPS | 102.2 TFLOPS | 142.5 TFLOPS | 174.0 TFLOPS |
| Storage capacity | 4 GB | 6 GB | 8 GB | 16 GB |
| Storage type | GDDR6 | GDDR6 | GDDR6 | GDDR6 |
| Memory interface | 128 bit | 192 bits | 256 bit | 256 bit |
| Memory bandwidth | 192 GB / s | 264 GB / s | 384 GB / s | 448 GB / s |
| TDP | 35 – 95 W. | 60 – 130 W. | 80 – 140 W. | 80 – 165 W. |
Availability
The new NVIDIA RTX laptop GPUs will be available in mobile workstations anticipated in Q2 this year from global OEMs.
The new NVIDIA RTX desktop GPUs and NVIDIA data center GPUs will be available from global distribution partners and OEMs starting later this month.
[ad_2]