Skip to content

Commit a515b29

Browse files
mattmcinnesmattmcinnes
committed
Adding last of the HPC files
1 parent ea4f8eb commit a515b29

16 files changed

+339
-1
lines changed

‎articles/virtual-machines/sizes/fpga-accelerated/includes/np-series-specs.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -16,4 +16,4 @@ ms.custom: include file
1616
| Memory | 168 - 672<sup>GiB | |
1717
| Data Disks | 8 - 32<sup>Disks | |
1818
| Network | 1 - 4<sup>NICs | 7500 - 30000<sup>Mbps |
19-
| Accelerators | 1 - 4 [Xilinx U250](https://www.xilinx.com/products/boards-and-kits/alveo/u250.html) | 64<sup>GiB </sup>/ FPGA |
19+
| Accelerators | 1 - 4<sup>FPGAs</sup> | [Xilinx U250](https://www.xilinx.com/products/boards-and-kits/alveo/u250.html) 64<sup>GiB </sup> <br> 64 - 256<sup>GiB</sup> per VM |

‎articles/virtual-machines/sizes/high-performance-compute/hb-family.md

Lines changed: 66 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,66 @@
1+
---
2+
title: HB sub-family VM size series
3+
description: Overview of the 'HB' sub-family of virtual machine sizes
4+
author: mattmcinnes
5+
ms.service: virtual-machines
6+
ms.subservice: sizes
7+
ms.topic: conceptual
8+
ms.date: 04/19/2024
9+
ms.author: mattmcinnes
10+
---
11+
12+
# 'HB' sub-family storage optimized VM size series
13+
14+
**Applies to:** :heavy_check_mark: Linux VMs :heavy_check_mark: Windows VMs :heavy_check_mark: Flexible scale sets :heavy_check_mark: Uniform scale sets
15+
16+
The 'HB' sub-family of VM size series are one of Azure's high-performance computing (HPC) optimized H-family VM instances. They're designed for compute-intensive workloads, such as computational fluid dynamics, finite element analysis, and large-scale scientific simulations. Equipped with high-performance AMD EPYC processors and fast memory, HB-series VMs offer exceptional CPU and memory bandwidth, making them ideal for applications that require extensive computational resources to perform large-scale calculations and data processing. This makes them particularly well-suited for industries like engineering, scientific research, and data analysis where processing speed and accuracy are critical for productivity and innovation.
17+
18+
## Workloads and use cases
19+
20+
**Computational Fluid Dynamics (CFD):** HB-family VMs are ideal for simulations in fields like aerospace, automotive design, and manufacturing, where fluid dynamics calculations are intensive.
21+
22+
**Finite Element Analysis (FEA):** HB-family VMs are suitable for engineering analyses that simulate physical phenomena, requiring intensive computational power to model complex systems and materials.
23+
24+
**Weather Forecasting:** HB-family VMs can handle the massive datasets and complex simulations required for high-resolution weather modeling and forecasting.
25+
26+
**Seismic Processing:** Used in the oil and gas industry, HB-family VMs can process seismic data to help map and understand subsurface structures.
27+
28+
**Scientific Research:** HB-family VMs support a wide range of scientific research that requires large-scale mathematical modeling, including physics and computational chemistry simulations.
29+
30+
**Genomics and Bioinformatics:** HB-family VMs are also used in life sciences for genomic analysis, where large amounts of data need to be processed quickly to decode genetic information.
31+
32+
## Series in family
33+
34+
### HB-series V1
35+
[!INCLUDE [hb-series-summary](./includes/hb-series-summary.md)]
36+
37+
[View the full hb-series page](../../hb-series.md).
38+
39+
[!INCLUDE [hb-series-specs](./includes/hb-series-specs.md)]
40+
41+
42+
### HBv2-series
43+
[!INCLUDE [hbv2-series-summary](./includes/hbv2-series-summary.md)]
44+
45+
[View the full hbv2-series page](../../hbv2-series.md).
46+
47+
[!INCLUDE [hbv2-series-specs](./includes/hbv2-series-specs.md)]
48+
49+
50+
### HBv3-series
51+
[!INCLUDE [hbv3-series-summary](./includes/hbv3-series-summary.md)]
52+
53+
[View the full hbv3-series page](../../hbv3-series.md).
54+
55+
[!INCLUDE [hbv3-series-specs](./includes/hbv3-series-specs.md)]
56+
57+
58+
### HBv4-series
59+
[!INCLUDE [hbv4-series-summary](./includes/hbv4-series-summary.md)]
60+
61+
[View the full hbv4-series page](../../hbv4-series.md).
62+
63+
[!INCLUDE [hbv4-series-specs](./includes/hbv4-series-specs.md)]
64+
65+
66+
[!INCLUDE [sizes-footer](../includes/sizes-footer.md)]

‎articles/virtual-machines/sizes/high-performance-compute/hc-family.md

Lines changed: 40 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,40 @@
1+
---
2+
title: HC sub-family VM size series
3+
description: Overview of the 'HC' sub-family of virtual machine sizes
4+
author: mattmcinnes
5+
ms.service: virtual-machines
6+
ms.subservice: sizes
7+
ms.topic: conceptual
8+
ms.date: 04/19/2024
9+
ms.author: mattmcinnes
10+
---
11+
12+
# 'HC' sub-family storage optimized VM size series
13+
14+
**Applies to:** :heavy_check_mark: Linux VMs :heavy_check_mark: Windows VMs :heavy_check_mark: Flexible scale sets :heavy_check_mark: Uniform scale sets
15+
16+
The 'HC' family of VM size series are one of Azure's high-performance computing (HPC) optimized VM instances. They're designed for compute-intensive workloads that require substantial CPU power, such as genomic sequencing, engineering simulations, and financial modeling. Equipped with high-performance Intel Xeon Scalable processors and fast memory, HC-series VMs offer exceptional computational capabilities and memory bandwidth, making them ideal for applications that demand intense processing power to handle complex calculations and massive data sets efficiently. This makes them particularly well-suited for sectors like healthcare, finance, and engineering, where rapid data processing and simulation accuracy are critical for advanced research and development.
17+
18+
## Workloads and use cases
19+
20+
**Genomic Sequencing:** HC-series VMs provide the computational power needed for genomic sequencing, enabling researchers to process and analyze large genetic datasets quickly.
21+
22+
**Engineering Simulations:** Ideal for running complex simulations in fields such as automotive, aerospace, and mechanical engineering. These simulations often include finite element analysis (FEA) and computational fluid dynamics (CFD).
23+
24+
**Financial Modeling:** These VMs can handle the high demands of financial applications, including risk analysis and quantitative simulations, which require massive computational resources to execute many calculations quickly.
25+
26+
**Scientific Research:** HC-series VMs support a wide range of scientific computing needs, particularly in physics and chemistry, where large-scale computations and data analysis are crucial.
27+
28+
**Weather Forecasting and Climate Simulation:** They are used in meteorology for high-resolution weather modeling and climate simulations, which require processing large datasets and performing complex simulations.
29+
30+
## Series in family
31+
32+
### HC-series
33+
[!INCLUDE [hc-series-summary](./includes/hc-series-summary.md)]
34+
35+
[View the full HC-series page](../../hc-series.md).
36+
37+
[!INCLUDE [hc-series-specs](./includes/hc-series-specs.md)]
38+
39+
40+
[!INCLUDE [sizes-footer](../includes/sizes-footer.md)]

‎articles/virtual-machines/sizes/high-performance-compute/hx-family.md

Lines changed: 40 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,40 @@
1+
---
2+
title: HX sub-family VM size series
3+
description: Overview of the 'HX' sub-family of virtual machine sizes
4+
author: mattmcinnes
5+
ms.service: virtual-machines
6+
ms.subservice: sizes
7+
ms.topic: conceptual
8+
ms.date: 04/19/2024
9+
ms.author: mattmcinnes
10+
---
11+
12+
# 'HX' sub-family storage optimized VM size series
13+
14+
**Applies to:** :heavy_check_mark: Linux VMs :heavy_check_mark: Windows VMs :heavy_check_mark: Flexible scale sets :heavy_check_mark: Uniform scale sets
15+
16+
The 'HX' family of VM size series are one of Azure's high-memory, high-performance computing (HPC) optimized VM instances. They're designed for memory-intensive workloads that require both large amounts of RAM and significant CPU performance, such as in-memory databases, big data analytics, and complex scientific simulations. Equipped with expansive memory and powerful CPUs, HX-series VMs provide the necessary resources to efficiently handle large datasets and perform rapid data processing. This makes them particularly well-suited for sectors like financial services, scientific research, and enterprise resource planning, where managing and analyzing large volumes of data in real-time is crucial for operational success and innovation.
17+
18+
## Workloads and use cases
19+
20+
**In-Memory Databases:** HX-series VMs are excellent for hosting in-memory databases like SAP HANA, which require extensive memory to maintain large datasets in RAM for ultra-fast processing and access.
21+
22+
**Big Data Analytics:** They can handle big data analytics applications that need to process vast amounts of data in memory to speed up analysis, which is critical for real-time decision-making.
23+
24+
**Genomic Research:** Genomics research often involves large-scale data analysis, where high memory capacity can significantly enhance performance by allowing more of the dataset to be held in memory, speeding up the analysis.
25+
26+
**Financial Simulations:** Financial institutions use HX-series VMs for high-frequency trading platforms and risk management simulations that require rapid processing of large data volumes to predict stock trends or calculate credit risks in real time.
27+
28+
**ERP Systems:** Large enterprise resource planning (ERP) systems benefit from the high memory and processing power of HX-series VMs to manage and process extensive enterprise data and support large numbers of concurrent users effectively.
29+
30+
## Series in family
31+
32+
### HB-series
33+
[!INCLUDE [hx-series-summary](./includes/hx-series-summary.md)]
34+
35+
[View the full HX-series page](../../hx-series.md).
36+
37+
[!INCLUDE [hx-series-specs](./includes/hx-series-specs.md)]
38+
39+
40+
[!INCLUDE [sizes-footer](../includes/sizes-footer.md)]

‎articles/virtual-machines/sizes/high-performance-compute/includes/hb-series-specs.md

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
---
2+
title: HB-series specs include
3+
description: Include file containing specifications of HB-series VM sizes.
4+
services: virtual-machines
5+
author: mattmcinnes
6+
ms.topic: include
7+
ms.service: virtual-machines
8+
ms.subservice: sizes
9+
ms.date: 04/19/2024
10+
ms.author: mattmcinnes
11+
ms.custom: include file
12+
---
13+
| Part | Quantity <br><sup>Count <sup>Units | Specs <br><sup>SKU ID, Performance <sup>Units</sup>, etc. |
14+
|---|---|---|
15+
| Processor | 15 - 60<sup>vCores | AMD EPYC™ 7551 (Naples) |
16+
| Memory | 228<sup>GiB | 263<sup>GBps</sup> |
17+
| Data Disks | 4<sup>Disks | |
18+
| Network | 8<sup>vNICs | Mellanox EDR Infiniband 100<sup>Gbps</sup> |
19+
| Accelerators | None | |

‎articles/virtual-machines/sizes/high-performance-compute/includes/hb-series-summary.md

Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,13 @@
1+
---
2+
title: HB-series V1 summary include
3+
description: Include file containing a summary of the HB-series V1 size family.
4+
services: virtual-machines
5+
author: mattmcinnes
6+
ms.topic: include
7+
ms.service: virtual-machines
8+
ms.subservice: sizes
9+
ms.date: 04/19/2024
10+
ms.author: mattmcinnes
11+
ms.custom: include file
12+
---
13+
HB-series VMs are optimized for applications that are driven by memory bandwidth, such as fluid dynamics, explicit finite element analysis, and weather modeling. HB VMs feature 60 AMD EPYC 7551 processor cores, 4 GB of RAM per CPU core, and no simultaneous multithreading. An HB VM provides up to 260 GB/sec of memory bandwidth. HB-series VMs feature 100 Gb/sec Mellanox EDR InfiniBand. These VMs are connected in a non-blocking fat tree for optimized and consistent RDMA performance. These VMs support Adaptive Routing and the Dynamic Connected Transport (DCT, in addition to standard RC and UD transports). These features enhance application performance, scalability, and consistency, and their usage is recommended.

‎articles/virtual-machines/sizes/high-performance-compute/includes/hbv2-series-specs.md

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
---
2+
title: HBv2-series specs include
3+
description: Include file containing specifications of HBv2-series VM sizes.
4+
services: virtual-machines
5+
author: mattmcinnes
6+
ms.topic: include
7+
ms.service: virtual-machines
8+
ms.subservice: sizes
9+
ms.date: 04/19/2024
10+
ms.author: mattmcinnes
11+
ms.custom: include file
12+
---
13+
| Part | Quantity <br><sup>Count <sup>Units | Specs <br><sup>SKU ID, Performance <sup>Units</sup>, etc. |
14+
|---|---|---|
15+
| Processor | 16 - 120<sup>vCores | AMD EPYC™ 7V12 (Rome) |
16+
| Memory | 456<sup>GiB | 350<sup>GBps</sup> |
17+
| Data Disks | 8<sup>Disks | |
18+
| Network | 8<sup>vNICs | Mellanox HDR Infiniband 200<sup>Gbps</sup> |
19+
| Accelerators | None | |

‎articles/virtual-machines/sizes/high-performance-compute/includes/hbv2-series-summary.md

Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,13 @@
1+
---
2+
title: HBv2-series summary include
3+
description: Include file containing a summary of the HBv2-series size family.
4+
services: virtual-machines
5+
author: mattmcinnes
6+
ms.topic: include
7+
ms.service: virtual-machines
8+
ms.subservice: sizes
9+
ms.date: 04/19/2024
10+
ms.author: mattmcinnes
11+
ms.custom: include file
12+
---
13+
HBv2-series VMs are optimized for applications that are driven by memory bandwidth, such as fluid dynamics, finite element analysis, and reservoir simulation. HBv2 VMs feature 120 AMD EPYC 7V12 processor cores, 4 GB of RAM per CPU core, and no simultaneous multithreading. Each HBv2 VM provides up to 350 GB/s of memory bandwidth, and up to 4 teraFLOPS of FP64 compute. HBv2-series VMs feature 200 Gb/sec Mellanox HDR InfiniBand. These VMs are connected in a non-blocking fat tree for optimized and consistent RDMA performance. These VMs support Adaptive Routing and the Dynamic Connected Transport (DCT, in addition to standard RC and UD transports). These features enhance application performance, scalability, and consistency, and their usage is recommended.

‎articles/virtual-machines/sizes/high-performance-compute/includes/hbv3-series-specs.md

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
---
2+
title: HBv3-series specs include
3+
description: Include file containing specifications of HBv3-series VM sizes.
4+
services: virtual-machines
5+
author: mattmcinnes
6+
ms.topic: include
7+
ms.service: virtual-machines
8+
ms.subservice: sizes
9+
ms.date: 04/19/2024
10+
ms.author: mattmcinnes
11+
ms.custom: include file
12+
---
13+
| Part | Quantity <br><sup>Count <sup>Units | Specs <br><sup>SKU ID, Performance <sup>Units</sup>, etc. |
14+
|---|---|---|
15+
| Processor | 16 - 120<sup>vCores | AMD EPYC™ 7V73X (Milan-X) |
16+
| Memory | 448<sup>GiB | 350<sup>GBps</sup> |
17+
| Data Disks | 32<sup>Disks | |
18+
| Network | 8<sup>vNICs | Mellanox HDR Infiniband 200<sup>Gbps</sup> |
19+
| Accelerators | None | |

‎articles/virtual-machines/sizes/high-performance-compute/includes/hbv3-series-summary.md

Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,13 @@
1+
---
2+
title: HBv3-series summary include
3+
description: Include file containing a summary of the HBv3-series size family.
4+
services: virtual-machines
5+
author: mattmcinnes
6+
ms.topic: include
7+
ms.service: virtual-machines
8+
ms.subservice: sizes
9+
ms.date: 04/19/2024
10+
ms.author: mattmcinnes
11+
ms.custom: include file
12+
---
13+
HBv3-series VMs are optimized for HPC applications such as fluid dynamics, explicit and implicit finite element analysis, weather modeling, seismic processing, reservoir simulation, and RTL simulation. HBv3 VMs feature up to 120 AMD EPYC™ 7V73X (Milan-X) CPU cores, 448 GB of RAM, and no simultaneous multithreading. HBv3-series VMs also provide 350 GB/sec of memory bandwidth (amplified up to 630 GB/s), up to 96 MB of L3 cache per core (1.536 GB total per VM), up to 7 GB/s of block device SSD performance, and clock frequencies up to 3.5 GHz. All HBv3-series VMs feature 200 Gb/sec HDR InfiniBand from NVIDIA Networking to enable supercomputer-scale MPI workloads. These VMs are connected in a non-blocking fat tree for optimized and consistent RDMA performance. The HDR InfiniBand fabric also supports Adaptive Routing and the Dynamic Connected Transport (DCT, in additional to standard RC and UD transports). These features enhance application performance, scalability, and consistency, and their usage is strongly recommended.

0 commit comments

Comments
 (0)