Intel’s Powerful Next Generation Gaudi 2 HL 2080 AI Processor Leaked

We recently got our hands on some internal documents that confirm Intel is preparing to launch

[{"selector":"#anim-0156ab82-e214-47c9-855c-af1d832f359c [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-645aeebc-bba4-43d1-80df-88235118c19e","keyframes":{"transform":["translate3d(-115.33547%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-2067b85a-8862-425f-8243-3e1054588568","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-91a13364-3d66-4805-9617-2569e859aa30","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}]

a next-generation AI training accelerator with monstrous capabilities later this year.

[{"selector":"#anim-f3a3f328-e387-41f3-96e7-ff3ab5e61068 [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-d71ef965-f16e-4eec-be9a-623ab3927c4e","keyframes":{"transform":["translate3d(116.29393%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-68e7e37c-6811-4681-9cf4-3b5058473e3c","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-774b53a0-cbeb-46ab-89e2-d8954922115f","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}]

Dubbed the Habana Gaudi 2 platform, it will take aim at NVIDIA's new datacenter products

[{"selector":"#anim-9229c4a5-6882-43eb-9c94-219eaffddd33 [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-aad4398a-71c0-4d62-8bf4-b916c4a05b54","keyframes":{"transform":["translate3d(-115.33547%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-5fd81694-165c-4c09-8ce7-2487f977b403","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-f2a5b4f9-1322-41e1-a686-bf73153dd399","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}]

for deep learning and aims to provide a higher value (from a TCO perspective) alternative.

[{"selector":"#anim-4a096a7f-aa12-44f8-8cc1-29a9628e4f5b [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-111cd8d6-f8c6-46d6-938f-151621bf62e0","keyframes":{"transform":["translate3d(116.29393%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-46ea37d9-5773-47b0-b991-70bd7b22caee","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-803b77a8-3b55-4685-85ab-4024db0372ca","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}]

Intel's Habana offerings are split into two categories: AI training and AI inference.

[{"selector":"#anim-9750cf5c-9e5b-4594-81ea-17ea150b6847 [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-e762f59a-8a79-4a24-9a30-542cb835a4ef","keyframes":{"transform":["translate3d(-115.33547%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-78f9a199-96cb-4ab0-a71b-60a2fe61e2f0","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-2248a65c-14f0-4a44-b243-0e38ab4a0294","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}]

The Gaudi platform is the AI training platform and Goya is the AI inference platform.

[{"selector":"#anim-dcaf0c7b-7398-4851-ad49-b071629087ae [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-a31bcab5-793f-4f12-85c8-bc226113e87e","keyframes":{"transform":["translate3d(116.29393%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-5b77d65c-22d6-4ecf-9f92-1e97baa08b81","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-f4be8e81-23ff-4903-bff2-478043a018e7","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}]

The Gaudi 2 chip will succeed the older Gaudi chips offered by Intel.

[{"selector":"#anim-84059122-daf9-4ce8-814e-b57763249f81 [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-1b8bf369-7bbe-4fc4-90e8-ac6717e6c1ec","keyframes":{"transform":["translate3d(-115.33547%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-6965e559-980f-4327-a582-fef4e9c8c2f0","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-9115aad6-6f45-463a-b520-96c5f5daf3f0","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}]