NVIDIA Grace Hopper Superchip CG1 model 54V - 900-2G530-0020-000
Liczba rdzeni: 72 Liczba wątków: 72 Pamięć cache L3: 117 MB TDP: 450W-1000W
Jesteś zainteresowany zakupem większej ilości sztuk? Poproś o indywidualną ofertę B2B na ten produkt.
| Kod towaru | 204.170375 |
|---|---|
| Part number | 900-2G530-0020-000 |
| Supermicro Part No. | GPU-NVGH480-54V |
| Producent | NVIDIA |
| Dostępność | Na zamówienie |
| Gwarancja | 24 miesięcy |
| Waga | 0.2 kg |
| Cena zawiera wszystkie obowiązujące opłaty | |
Szczegółowe informacje
NVIDIA GH200 Grace Hopper Superchip
The breakthrough accelerated CPU for large-scale AI and high-performance computing (HPC) applications.
- 72-core NVIDIA Grace CPU
- NVIDIA H100 Tensor Core GPU
- Up to 480GB of LPDDR5X memory with error-correction code (ECC)
- Supports 96GB of HBM3 or 144GB of HBM3e
- Up to 624GB of fast-access memory
- NVLink-C2C: 900GB/s of coherent memory
Power and Efficiency With the Grace CPU
The NVIDIA Grace CPU delivers 2X the performance per watt of conventional x86-64 platforms and is the world’s fastest Arm® data center CPU. The Grace CPU was designed for high single-threaded performance, high-memory bandwidth, and outstanding data-movement capabilities. The NVIDIA Grace CPU combines 72 Neoverse V2 Armv9 cores with up to 480GB of server-class LPDDR5X memory with ECC. This design strikes the optimal balance of bandwidth, energy efficiency, capacity, and cost. Compared to an eight-channel DDR5 design, the Grace CPU LPDDR5X memory subsystem provides up to 53 percent more bandwidth at one- eighth the power per gigabyte per second.
The Power of Coherent Memory
NVLink-C2C memory coherency increases developer productivity, performance, and the amount of GPU-accessible memory. CPU and GPU threads can concurrently and transparently access both CPU and GPU resident memory, allowing developers to focus on algorithms instead of explicit memory management. Memory coherency lets developers only transfer the data they need and not migrate entire pages to and from the GPU. It also provides lightweight synchronization primitives across GPU and CPU threads by enabling native atomics from both the CPU and GPU. Fourth-generation NVLink allows accessing peer memory with direct loads, stores, and atomic operations, so accelerated applications can solve larger problems more easily than ever.
Class-Leading Performance for HPC and AI Workloads
The GH200 Grace Hopper Superchip is the first true heterogeneous accelerated platform for HPC workloads. It accelerates any application with the strengths of both GPUs and CPUs while providing the simplest and most productive heterogeneous programming model to date, enabling scientists and engineers to focus on solving the world’s most important problems. For AI inference workloads, GH200 Grace Hopper Superchips combine with NVIDIA networking technologies to provide the best TCO for scale-out solutions, letting customers take on larger datasets, more complex models, and new workloads using up to 624GB of fast-access memory. For AI training, up to 256 NVLink-connected GPUs can access up to 144TB of memory at high bandwidth for large language model (LLM) or recommender system training.
Grace Hopper HPC Performance
-
- Grace CPU
CPU core count 72 Arm Neoverse V2 cores L1 cache 64KB i-cache + 64KB d-cache L2 cache 1MB per core L3 cache 117MB LPDDR5X size Up to 480GB Memory bandwidth Up to 512GB/s PCIe links Up to 4x PCIe x16 (Gen5)
-
- Hopper H100 GPU
FP64 34 teraFLOPS FP32 67 teraFLOPS FP64 Tensor Core 67 teraFLOPS TF32 Tensor Core 989 teraFLOPS | 494 teraFLOPS High-bandwidth memory (HBM) size Up to 96GB | 144GB HBM3e Memory bandwidth Up to 4TB/s | Up to 4.9TB/s HBM3e Module thermal design power (TDP) Programmable from 450W to 1000W
(CPU + GPU + memory)
Parametry
| Wielkość HBM | 0 |
|---|---|
| Socket | SoC Nvidia |
| Oznaczenie modelu | Grace |
| Generacja | Hopper |
| Liczba rdzeni | 72 |
| Frekvence CPU (GHz) | 3.10 |
| Turbo frekwencja | 3.10 |
| Cache | 117 |
| TDP (W) | 450-1000 |
| Seria procesorów | TypProc Hopper |
