Though Intel doesn’t have as tight a grip on the processor market as it once did, the company is still the main player. In order not to cede any further territory to the competitors – above all AMD – Intel relies fully on power. With its latest CPU and GPU offerings, the Company relies on high-performance processing Fend off competitors with the new Intel Xeon Max series.
Xeon Mac CPU
Starting with the CPU, Xeon Max DDR5 memory supports PCIe 5.0 and Compute Express Link (CXL) 1.1. There are 56 performance cores from the Golden Cove architecture, which Intel is already using in its 12th-Gen Core processors.
In addition, the Xeon Max has 20 accelerators to support high-performance computing (HPC) workloads and also AI/machine learning:
- Intel Deep Learning Boost (DL Boost)
- Intel Advanced Vector Extensions 512 (AVX-512)
- Intel Data Streaming Accelerator (DSA)
- Intel Advanced Matrix Extensions (AMX)
Intel points out the following advantages of the Xeon Max CPU:
- “68% less power consumption than an AMD Milan-X cluster with the same HPCG performance.
- AMX extensions boost AI performance and deliver 8X peak throughput over AVX-512 for INT8 with INT32 accumulation operations.2
- Provides flexibility to operate in various HBM and DDR memory configurations.
- Workload Benchmarks:
- Climate modeling: 2.4x faster than AMD Milan-X on MPAS-A with HBM only.
- Molecular Dynamics: On DeePMD, 2.8x performance improvement over competing products with DDR memory.”
Xeon Max GPU
Next up is the Xeon Max GPU, which Nvidia is targeting as the leading name in data center GPUs. Intel describes the package as the “highest density processor” with over 100 billion transistors on a system of 47 chiplets.
It has 128 cores based on Intel’s Xe HPC microarchitecture. There are also 128 ray tracing units specifically designed for simulation software and for generating digital content. Below are the benefits that Intel says the Xeon Max GPU will bring:
- “408MB L2 cache – the highest in the industry – and 64MB L1 cache to increase throughput and performance.
- The only HPC/AI GPU with native ray tracing acceleration designed to accelerate scientific visualization and animation.
- Workload Benchmarks:
- Finance: 2.4x performance improvement over NVIDIA’s A100 on Riskfuel credit option pricing.
- Physics: 1.5x improvement over A100 for NekRS virtual reactor simulations.”
Advice of the day: Did you know you can Do you also use the Microsoft Defender antivirus built into Windows with scheduled scans? In our tutorial, we give you a step-by-step guide on how to program your personal scan schedule to stay malware-free.