Microsoft Azure ND H200 V5 VMs For AI HPC Performance

Microsoft Azure is deploying new cloud-based AI-supercomputing clusters built with Azure ND H200 v5 series VMs since its clients depend on Azure AI infrastructure to generate creative AI-driven solutions

[{"selector":"#anim-37eb34e7-ded9-4dff-a03b-ca44cc58adec [data-leaf-element=\"true\"]","keyframes":{"transform":["translate(0%, 0%) scale(1.5)","translate(0%, 0%) scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}] [{"selector":"#anim-5f95a6b8-9821-4f5c-8c70-2bd1a6cbfabe","keyframes":{"opacity":[0,1]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-6e5ccf9e-a871-49f0-b627-aa39073d756a","keyframes":{"transform":["scale(0.3333333333333333)","scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}]

Due to their size, effectiveness, and improved performance, customers and Microsoft AI services like Azure Machine Learning and Azure OpenAI Service are already adopting its ND H200 v5 VMs

[{"selector":"#anim-bd24d02b-4768-42de-96c2-5ce8f0b6311f [data-leaf-element=\"true\"]","keyframes":{"transform":["translate(0%, 0%) scale(1.5)","translate(0%, 0%) scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}] [{"selector":"#anim-65349f0c-f07c-4732-b9d0-f1f05f266332","keyframes":{"transform":["translate3d(-115.2381%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-ec976d47-f6b7-4b31-8f8e-081dbd1e1478","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-c5af3626-406e-43f8-9915-1ad44e78341f","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}]

The Azure ND H200 v5 series virtual machine is engineered to provide outstanding performance for tasks related to artificial intelligence (AI) and high-performance computing (HPC)

[{"selector":"#anim-96aeb082-e2fa-49fd-8ec1-1f5e4be8fc7c [data-leaf-element=\"true\"]","keyframes":{"transform":["translate(0%, 0%) scale(1.5)","translate(0%, 0%) scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}] [{"selector":"#anim-75ca1946-9d7f-4d13-b4d7-6d6fdeda84bb","keyframes":{"transform":["translate3d(-115.55555%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-084cff78-0bd7-4750-979c-886f56580967","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-e8e1e7a1-f5dd-459a-8660-bdfe959d9a6f","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}]

Eight NVIDIA H200 Tensor Core GPUs coupled by 900 GB/s NVLink are the foundation of the Azure ND H200 v5 series, along with a single virtual machine

[{"selector":"#anim-0ce9a898-033a-4f34-9c63-93f71cf7f444 [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(-12.514648210040342%, 0, 0)","translate3d(0%, 0, 0)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-87283f6e-0160-4835-b4b4-78c897ad9dd0","keyframes":{"opacity":[0,1]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-8fca7c0d-074b-4aea-ba54-ca4340b1f7ad","keyframes":{"transform":["scale(0.3333333333333333)","scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}]

Every GPU in the virtual machine has a dedicated 400 Gb/s NVIDIA Quantum-2 CX7 InfiniBand connection that is not affected by topology

[{"selector":"#anim-023602a2-089a-481d-8ba9-b79a7380365a [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(12.514648210040342%, 0, 0)","translate3d(0%, 0, 0)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-41c6bdd5-e729-483b-b44b-5b7bd7c11bf9","keyframes":{"transform":["rotate(-540deg) scale(0.1)","none"],"opacity":[0,1]},"delay":0,"duration":1000,"fill":"both","iterations":1}]

Every GPU in the virtual machine has a dedicated 400 Gb/s NVIDIA Quantum-2 CX7 InfiniBand connection that is not affected by topology

[{"selector":"#anim-9f05c4b7-8061-45c2-9e20-391417615b8c [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(12.514648210040342%, 0, 0)","translate3d(0%, 0, 0)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-ee52c8a6-0af6-4aa3-97dc-73ede0bbd33c","keyframes":{"transform":["translate3d(115.55555%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .8, 1)","fill":"both"}] [{"selector":"#anim-433ee60f-8304-465a-b6af-d06f386375f7","keyframes":{"transform":["rotateZ(180deg)","rotateZ(0deg)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .5, 1)","fill":"forwards"}]

ND H200 v5 VM can support bigger batch sizes because of its increased HBM capacity, which improves GPU efficiency

[{"selector":"#anim-cb231097-5c24-4ccb-b982-8d5ab51f90d9 [data-leaf-element=\"true\"]","keyframes":{"transform":["translate(0%, 0%) scale(1.5)","translate(0%, 0%) scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}] [{"selector":"#anim-4ec7535d-4826-4684-8983-66d6efdc6bb8","keyframes":{"transform":["translate3d(-115.55555%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .8, 1)","fill":"both"}] [{"selector":"#anim-ee0e6f53-64ff-4cfa-8bb3-a847aa03ae6b","keyframes":{"transform":["rotateZ(-180deg)","rotateZ(0deg)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .5, 1)","fill":"forwards"}]

For more details visit Govindhtech.com

[{"selector":"#anim-b9af6df5-5169-402c-b933-3b66a073ecaf [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(-12.514648210040342%, 0, 0) translate(-25%, 0%) scale(1.5)","translate3d(0%, 0, 0) translate(0%, 0%) scale(1)"]},"delay":0,"duration":2000,"fill":"forwards"}]