Discover Amazon EC2 G6 Instances' Deep Learning Power

The NVIDIA L4 Tensor Core GPU-powered Amazon EC2 G6 instances are now generally available

[{"selector":"#anim-52518bc9-c136-4901-a962-81afa798c346","keyframes":{"opacity":[0,1]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-397f7030-6b82-49bf-ad54-c2748bc76836","keyframes":{"transform":["scale(0.3333333333333333)","scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}] [{"selector":"#anim-d2ae6f57-f7ac-4b5d-a59b-19b8197695e9 [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(-36.069749131772724%, 0, 0) translate(-25%, 0%) scale(1.5)","translate3d(0%, 0, 0) translate(0%, 0%) scale(1)"]},"delay":0,"duration":2000,"fill":"forwards"}]

Numerous machine learning and graphics-intensive use cases are compatible with G6 instances

[{"selector":"#anim-f9e455c4-b883-4eaa-995c-4d168b55bb19","keyframes":{"transform":["translate3d(132.14285%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-a17f0314-414b-4ad0-8ecc-dfc617adb3db","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-ee1ea18f-76fc-45d9-ae50-a92d10629d60","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}] [{"selector":"#anim-ac18451c-dc5a-4ffc-92d2-673ff20609c2 [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"}]

Many graphics-intensive and machine learning use cases may be fulfilled by NVIDIA L4 Tensor Core GPU-powered Amazon EC2 G6 instances

[{"selector":"#anim-49ea1820-24d0-4b8a-9add-4231c0e8d363","keyframes":{"transform":["translate3d(124.82014%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-38e0d69a-7c6f-47d2-99ee-04ea0507427c","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-6542f417-150e-49ba-ae1c-a927d7f6d288","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}] [{"selector":"#anim-17ebd775-c406-4af0-bdf2-bb461e464c44 [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"}]

Amazon EC2 G6 instances use third-generation AMD EPYC CPUs and up to eight 24-GB RAM NVIDIA L4 Tensor Core GPUs

[{"selector":"#anim-b68f04f4-a74c-4253-a538-7bc7216d8a62","keyframes":{"transform":["translate3d(-128.13689%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .8, 1)","fill":"both"}] [{"selector":"#anim-f6554bb2-6a48-4dd0-8ca0-d87cd890999f","keyframes":{"transform":["rotateZ(-180deg)","rotateZ(0deg)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .5, 1)","fill":"forwards"}] [{"selector":"#anim-4528cc99-0d63-4a80-9cfb-1037373ba297 [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(-35.21169345865223%, 0, 0) translate(-25%, 0%) scale(1.5)","translate3d(0%, 0, 0) translate(0%, 0%) scale(1)"]},"delay":0,"duration":2000,"fill":"forwards"}]

There is a very effective and affordable option for clients that want to execute their machine learning applications using NVIDIA libraries like TensorRT, CUDA, and cuDNN

[{"selector":"#anim-069e9018-6b3f-4ae3-a2dc-9e0016283982","keyframes":{"transform":["translate3d(133.82352%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .8, 1)","fill":"both"}] [{"selector":"#anim-56e7e605-0fe9-4f60-9563-e5c83bb80d12","keyframes":{"transform":["rotateZ(180deg)","rotateZ(0deg)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .5, 1)","fill":"forwards"}] [{"selector":"#anim-fd2f8e24-8ec0-43eb-af8e-ed37d2ddb2d5 [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"}]

They are driven by L4 GPUs, which enable NVIDIA RTX technology and have third-generation RT cores

[{"selector":"#anim-ba180f60-82f3-4f0c-89aa-59361f52b651","keyframes":{"transform":["translate3d(153.49999%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .8, 1)","fill":"both"}] [{"selector":"#anim-a8e20e4a-927e-4685-ba87-2c707938cecc","keyframes":{"transform":["rotateZ(180deg)","rotateZ(0deg)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .5, 1)","fill":"forwards"}] [{"selector":"#anim-71b12944-1bef-42ac-9041-9c438737004e [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(-35.937499914669296%, 0, 0) translate(-25%, 0%) scale(1.5)","translate3d(0%, 0, 0) translate(0%, 0%) scale(1)"]},"delay":0,"duration":2000,"fill":"forwards"}]

Gr6 instances are ideal for graphics applications requiring more memory since they provide a 1:8 vCPU:RAM ratio

[{"selector":"#anim-0d455fe1-0343-4ee0-bb77-b5d12b874472","keyframes":{"transform":["translate3d(133.73983%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-a61d7d4a-8782-4a78-9283-1cddbbfe398a","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-8c953976-2e16-4049-a4d2-1e2ed1ae0e27","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}] [{"selector":"#anim-117d4df4-653a-4a93-946c-562dbb245563 [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(-34.249999904429615%, 0, 0) translate(-25%, 0%) scale(1.5)","translate3d(0%, 0, 0) translate(0%, 0%) scale(1)"]},"delay":0,"duration":2000,"fill":"forwards"}]

The Nitro system uses Amazon EC2 G6 instances to provide the GPUs in a pass-through mode, giving them performance that is similar to that of bare metal for more details govindhtech.com

[{"selector":"#anim-c740181b-b6b1-4409-8d90-9bd849c77c87","keyframes":{"transform":["translate3d(121.42856%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .8, 1)","fill":"both"}] [{"selector":"#anim-09e81aaf-e3c6-490a-b2bf-7ebba0655363","keyframes":{"transform":["rotateZ(180deg)","rotateZ(0deg)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .5, 1)","fill":"forwards"}] [{"selector":"#anim-86064ca8-787b-469b-8667-c3ab2b01c659 [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(-35.937499914669296%, 0, 0) translate(-25%, 0%) scale(1.5)","translate3d(0%, 0, 0) translate(0%, 0%) scale(1)"]},"delay":0,"duration":2000,"fill":"forwards"}]