Tech News Today – Latest Gadget & AI Updates

Home

Santa Clara, California

Every enterprise technology officer has felt the same bottleneck: a GPU cluster powerful enough to run large language models at scale, throttled not by compute but by the network traffic choking between servers. That friction is not a minor inconvenience. It is a billion-dollar drag on AI ambitions. AMD advancing AI infrastructure at its June 2025 summit in Santa Clara offered what looked, on paper, like a direct answer to that problem — and the scale of the bet AMD is placing makes the proposal worth taking seriously.

AMD Advancing AI: From Chips to Systems

At the Advancing AI 2025 event on June 12, AMD CEO Dr. Lisa Su introduced more than just a new processor. She announced a change in approach. Instead of focusing on having the best GPU, AMD now aims to have the best overall rack system.

This change is important. For years, discussions about AI infrastructure focused on individual accelerator benchmarks like FLOPS, memory bandwidth, and chip size. Now, AMD’s approach is different: it argues that a chip performance does not matter if the system around it cannot move data quickly enough.

At Advancing AI 2025, AMD showed a complete, open-standards rack-scale AI infrastructure. This system is already being used with AMD Instinct MI350 Series GPUs, 5th Gen AMD EPYC processors, and AMD Pensando Pollara NICs in extensive deployments like Oracle Cloud Infrastructure. These are not just future plans—these systems are already running.

The Instinct GPU Arrays Powering the Next Phase

The main hardware feature is the Instinct GPU clusters using the MI350 Series. The Instinct MI355X GPU, built on AMD’s CDNA 4 architecture, offers up to 20 PFLOPS of FP4 performance, 288GB of HBM3E memory, and 8 TB/s of bandwidth. These systems can scale to 128 GPUs per rack with liquid cooling, reaching 2.6 exaFLOPS of AI compute and supporting models with more than 500 billion parameters.

In practical terms, a single Helios rack with 128 MI355X GPUs can train a 500-billion-parameter model without sending data to another rack. For enterprise teams with strict compliance needs, such as financial institutions, healthcare providers, or defense contractors, keeping training within a single secure, isolated rack is not just helpful—it is required.

AMD’s Instinct GPU clusters also have a strong competitive angle. The Helios rack-scale solution will use 72 MI400 Series GPUs, next-generation EPYC Venice CPUs, and Pensando Vulcano network adapters. Compared to the prerelease specs of NVIDIA’s Vera Rubin NVL72, Helios is expected to offer the same scale-up bandwidth and similar FP4 and FP8 performance, but with 50% more HBM4 memory capacity, memory bandwidth, and scale-out bandwidth.

Having more memory in each rack changes how models are served. Operators do not have to split models across many nodes as much, which lowers the delays users notice during inference.

Rethinking the Data Center Ecosystem

The main challenge in the past was building faster GPUs. Now, the focus is on creating a well-integrated data center ecosystem around those GPUs. AMD is tackling this with a multi-layered, open-standards strategy that spans the rack, software, and networking layers.

AMD leads to open standards like the Open Compute Project (OCP), Ultra Accelerator Link (UALink), and Ultra Ethernet Consortium (UEC). This leadership helps the industry scale through collaboration, enabling the development of open, high-performance systems for both scale-up and scale-out AI clusters.

AMD’s data center ecosystem is built to avoid the vendor lock-in seen with NVIDIA’s GB200 NVL72 systems. While NVIDIA’s NVLink fabric keeps customers tied to one vendor, AMD’s approach lets operators choose networking, cooling, and power equipment from different suppliers. For large-scale operators spending billions, this pliability has real financial benefits.

The market has responded quickly. Oracle plans to launch a public AI supercluster with 50,000 Instinct MI450 Series GPUs in Q3 2026, using the Helios rack design, next-gen EPYC Venice CPUs, and Pensando Vulcano networking. Vultr is also building a 50 MW AI supercluster in Ohio with 24,000 Instinct MI355X GPUs. These are full-scale projects, not just tests.

Solving Network Transport: The Hidden Bottleneck

The most important technical announcement from the June summit received little attention in mainstream coverage. Network transport, or how data moves between accelerators during distributed training, is now the main limit on cluster efficiency. AMD is addressing this issue directly.

AMD helped start the UALink Consortium, which is creating an open standard for GPU-to-GPU communication across servers and racks. UALink provides 260 TB/s of bandwidth within a rack, offering greater scalability and openness than proprietary options like NVLink. AMD also plans to support UALink over Ultra Ethernet, combining high performance with Ethernet’s flexibility.

The network transport issue is very real. When training large models on hundreds of GPUs, the interconnections among GPUs affect how much time is spent waiting for data updates rather than computing. Cutting interconnect latency by 10% can reduce training time by the same amount, yielding considerable cost savings for long training runs.

With the Helios reference design, performance scales smoothly across 72 GPUs using UALink. UALink connects the GPUs and scale-out NICs, and when used over Ethernet, links all the GPUs in the rack, so they work together as a single system.

AMD Accelerates Rack Scale Infrastructure for Enterprise AI Training

The most consequential implication of all this activity is the enterprise angle. AMD accelerates rack-scale infrastructure for enterprise AI training, making it available not only to hyperscalers but also to thousands of mid-sized organizations, such as regional banks, pharmaceutical companies, and national labs. These groups cannot build massive data centers but still need to handle demanding training jobs.

AMD is well-positioned to support every part of the AI stack, from Instinct GPUs and EPYC CPUs to Pensando DPUs and scale-out networking. All of this is built on open, flexible, and programmable infrastructure made for today’s AI needs.

AMD’s open-ecosystem approach is especially valuable in the enterprise market. For example, a hospital using AI for medical imaging cannot spend months integrating a proprietary system. A financial institution training credit-risk models on sensitive data needs full control over its deployment. AMD’s open-standard solutions, like OCP-compliant racks, UEC-compliant NICs, and ROCm open-source software, help remove the barriers that have kept enterprise AI from moving beyond the testing phase.

The $10 Billion Question

In the first quarter of 2026, AMD reported strong results. Demand for AI infrastructure drove data center revenue up 57% from the previous year. Total revenue hit $10.3 billion, thanks to hyperscalers and enterprise customers expanding their AI capacity. Wall Street analysts expect AMD’s AI GPU revenue for the year to be between $10 billion and $12 billion.

AMD and Meta have signed a multi-year deal to power Meta’s AI infrastructure with up to 6GW of AMD Instinct GPUs. Shipments will start in the second half of 2026, using the Helios rack-scale architecture.

These developments do not guarantee that AMD will catch up to NVIDIA. NVIDIA’s software ecosystem, including CUDA’s long lead time, developer tools, and optimization libraries, remains a major advantage. However, AMD is now competing on more than just chip performance. The company argues that the future of AI infrastructure lies in open systems and that enterprises seeking flexibility should have a supply chain that supports it.

The real test will come when Helios systems are shipped in large numbers in late 2026. AMD’s ability to deliver the combined quality and software reliability that enterprise customers expect will decide if this strategy leads to lasting market share or just a memorable keynote.

Source: AMD Newsroom
About US

Santa Clara, California

Every enterprise technology officer has felt the same bottleneck: a GPU cluster powerful enough to run large language models at scale, throttled not by compute but by the network traffic choking between servers. That friction is not a minor inconvenience. It is a billion-dollar drag on AI ambitions. AMD advancing AI infrastructure at its June 2025 summit in Santa Clara offered what looked, on paper, like a direct answer to that problem — and the scale of the bet AMD is placing makes the proposal worth taking seriously.

AMD Advancing AI: From Chips to Systems

At the Advancing AI 2025 event on June 12, AMD CEO Dr. Lisa Su introduced more than just a new processor. She announced a change in approach. Instead of focusing on having the best GPU, AMD now aims to have the best overall rack system.

This change is important. For years, discussions about AI infrastructure focused on individual accelerator benchmarks like FLOPS, memory bandwidth, and chip size. Now, AMD’s approach is different: it argues that a chip performance does not matter if the system around it cannot move data quickly enough.

At Advancing AI 2025, AMD showed a complete, open-standards rack-scale AI infrastructure. This system is already being used with AMD Instinct MI350 Series GPUs, 5th Gen AMD EPYC processors, and AMD Pensando Pollara NICs in extensive deployments like Oracle Cloud Infrastructure. These are not just future plans—these systems are already running.

The Instinct GPU Arrays Powering the Next Phase

The main hardware feature is the Instinct GPU clusters using the MI350 Series. The Instinct MI355X GPU, built on AMD’s CDNA 4 architecture, offers up to 20 PFLOPS of FP4 performance, 288GB of HBM3E memory, and 8 TB/s of bandwidth. These systems can scale to 128 GPUs per rack with liquid cooling, reaching 2.6 exaFLOPS of AI compute and supporting models with more than 500 billion parameters.

In practical terms, a single Helios rack with 128 MI355X GPUs can train a 500-billion-parameter model without sending data to another rack. For enterprise teams with strict compliance needs, such as financial institutions, healthcare providers, or defense contractors, keeping training within a single secure, isolated rack is not just helpful—it is required.

AMD’s Instinct GPU clusters also have a strong competitive angle. The Helios rack-scale solution will use 72 MI400 Series GPUs, next-generation EPYC Venice CPUs, and Pensando Vulcano network adapters. Compared to the prerelease specs of NVIDIA’s Vera Rubin NVL72, Helios is expected to offer the same scale-up bandwidth and similar FP4 and FP8 performance, but with 50% more HBM4 memory capacity, memory bandwidth, and scale-out bandwidth.

Having more memory in each rack changes how models are served. Operators do not have to split models across many nodes as much, which lowers the delays users notice during inference.

Rethinking the Data Center Ecosystem

The main challenge in the past was building faster GPUs. Now, the focus is on creating a well-integrated data center ecosystem around those GPUs. AMD is tackling this with a multi-layered, open-standards strategy that spans the rack, software, and networking layers.

AMD leads to open standards like the Open Compute Project (OCP), Ultra Accelerator Link (UALink), and Ultra Ethernet Consortium (UEC). This leadership helps the industry scale through collaboration, enabling the development of open, high-performance systems for both scale-up and scale-out AI clusters.

AMD’s data center ecosystem is built to avoid the vendor lock-in seen with NVIDIA’s GB200 NVL72 systems. While NVIDIA’s NVLink fabric keeps customers tied to one vendor, AMD’s approach lets operators choose networking, cooling, and power equipment from different suppliers. For large-scale operators spending billions, this pliability has real financial benefits.

The market has responded quickly. Oracle plans to launch a public AI supercluster with 50,000 Instinct MI450 Series GPUs in Q3 2026, using the Helios rack design, next-gen EPYC Venice CPUs, and Pensando Vulcano networking. Vultr is also building a 50 MW AI supercluster in Ohio with 24,000 Instinct MI355X GPUs. These are full-scale projects, not just tests.

Solving Network Transport: The Hidden Bottleneck

The most important technical announcement from the June summit received little attention in mainstream coverage. Network transport, or how data moves between accelerators during distributed training, is now the main limit on cluster efficiency. AMD is addressing this issue directly.

AMD helped start the UALink Consortium, which is creating an open standard for GPU-to-GPU communication across servers and racks. UALink provides 260 TB/s of bandwidth within a rack, offering greater scalability and openness than proprietary options like NVLink. AMD also plans to support UALink over Ultra Ethernet, combining high performance with Ethernet’s flexibility.

The network transport issue is very real. When training large models on hundreds of GPUs, the interconnections among GPUs affect how much time is spent waiting for data updates rather than computing. Cutting interconnect latency by 10% can reduce training time by the same amount, yielding considerable cost savings for long training runs.

With the Helios reference design, performance scales smoothly across 72 GPUs using UALink. UALink connects the GPUs and scale-out NICs, and when used over Ethernet, links all the GPUs in the rack, so they work together as a single system.

AMD Accelerates Rack Scale Infrastructure for Enterprise AI Training

The most consequential implication of all this activity is the enterprise angle. AMD accelerates rack-scale infrastructure for enterprise AI training, making it available not only to hyperscalers but also to thousands of mid-sized organizations, such as regional banks, pharmaceutical companies, and national labs. These groups cannot build massive data centers but still need to handle demanding training jobs.

AMD is well-positioned to support every part of the AI stack, from Instinct GPUs and EPYC CPUs to Pensando DPUs and scale-out networking. All of this is built on open, flexible, and programmable infrastructure made for today’s AI needs.

AMD’s open-ecosystem approach is especially valuable in the enterprise market. For example, a hospital using AI for medical imaging cannot spend months integrating a proprietary system. A financial institution training credit-risk models on sensitive data needs full control over its deployment. AMD’s open-standard solutions, like OCP-compliant racks, UEC-compliant NICs, and ROCm open-source software, help remove the barriers that have kept enterprise AI from moving beyond the testing phase.

The $10 Billion Question

In the first quarter of 2026, AMD reported strong results. Demand for AI infrastructure drove data center revenue up 57% from the previous year. Total revenue hit $10.3 billion, thanks to hyperscalers and enterprise customers expanding their AI capacity. Wall Street analysts expect AMD’s AI GPU revenue for the year to be between $10 billion and $12 billion.

AMD and Meta have signed a multi-year deal to power Meta’s AI infrastructure with up to 6GW of AMD Instinct GPUs. Shipments will start in the second half of 2026, using the Helios rack-scale architecture.

These developments do not guarantee that AMD will catch up to NVIDIA. NVIDIA’s software ecosystem, including CUDA’s long lead time, developer tools, and optimization libraries, remains a major advantage. However, AMD is now competing on more than just chip performance. The company argues that the future of AI infrastructure lies in open systems and that enterprises seeking flexibility should have a supply chain that supports it.

The real test will come when Helios systems are shipped in large numbers in late 2026. AMD’s ability to deliver the combined quality and software reliability that enterprise customers expect will decide if this strategy leads to lasting market share or just a memorable keynote.

Source: AMD Newsroom
Tech Reviews

Santa Clara, California

Every enterprise technology officer has felt the same bottleneck: a GPU cluster powerful enough to run large language models at scale, throttled not by compute but by the network traffic choking between servers. That friction is not a minor inconvenience. It is a billion-dollar drag on AI ambitions. AMD advancing AI infrastructure at its June 2025 summit in Santa Clara offered what looked, on paper, like a direct answer to that problem — and the scale of the bet AMD is placing makes the proposal worth taking seriously.

AMD Advancing AI: From Chips to Systems

At the Advancing AI 2025 event on June 12, AMD CEO Dr. Lisa Su introduced more than just a new processor. She announced a change in approach. Instead of focusing on having the best GPU, AMD now aims to have the best overall rack system.

This change is important. For years, discussions about AI infrastructure focused on individual accelerator benchmarks like FLOPS, memory bandwidth, and chip size. Now, AMD’s approach is different: it argues that a chip performance does not matter if the system around it cannot move data quickly enough.

At Advancing AI 2025, AMD showed a complete, open-standards rack-scale AI infrastructure. This system is already being used with AMD Instinct MI350 Series GPUs, 5th Gen AMD EPYC processors, and AMD Pensando Pollara NICs in extensive deployments like Oracle Cloud Infrastructure. These are not just future plans—these systems are already running.

The Instinct GPU Arrays Powering the Next Phase

The main hardware feature is the Instinct GPU clusters using the MI350 Series. The Instinct MI355X GPU, built on AMD’s CDNA 4 architecture, offers up to 20 PFLOPS of FP4 performance, 288GB of HBM3E memory, and 8 TB/s of bandwidth. These systems can scale to 128 GPUs per rack with liquid cooling, reaching 2.6 exaFLOPS of AI compute and supporting models with more than 500 billion parameters.

In practical terms, a single Helios rack with 128 MI355X GPUs can train a 500-billion-parameter model without sending data to another rack. For enterprise teams with strict compliance needs, such as financial institutions, healthcare providers, or defense contractors, keeping training within a single secure, isolated rack is not just helpful—it is required.

AMD’s Instinct GPU clusters also have a strong competitive angle. The Helios rack-scale solution will use 72 MI400 Series GPUs, next-generation EPYC Venice CPUs, and Pensando Vulcano network adapters. Compared to the prerelease specs of NVIDIA’s Vera Rubin NVL72, Helios is expected to offer the same scale-up bandwidth and similar FP4 and FP8 performance, but with 50% more HBM4 memory capacity, memory bandwidth, and scale-out bandwidth.

Having more memory in each rack changes how models are served. Operators do not have to split models across many nodes as much, which lowers the delays users notice during inference.

Rethinking the Data Center Ecosystem

The main challenge in the past was building faster GPUs. Now, the focus is on creating a well-integrated data center ecosystem around those GPUs. AMD is tackling this with a multi-layered, open-standards strategy that spans the rack, software, and networking layers.

AMD leads to open standards like the Open Compute Project (OCP), Ultra Accelerator Link (UALink), and Ultra Ethernet Consortium (UEC). This leadership helps the industry scale through collaboration, enabling the development of open, high-performance systems for both scale-up and scale-out AI clusters.

AMD’s data center ecosystem is built to avoid the vendor lock-in seen with NVIDIA’s GB200 NVL72 systems. While NVIDIA’s NVLink fabric keeps customers tied to one vendor, AMD’s approach lets operators choose networking, cooling, and power equipment from different suppliers. For large-scale operators spending billions, this pliability has real financial benefits.

The market has responded quickly. Oracle plans to launch a public AI supercluster with 50,000 Instinct MI450 Series GPUs in Q3 2026, using the Helios rack design, next-gen EPYC Venice CPUs, and Pensando Vulcano networking. Vultr is also building a 50 MW AI supercluster in Ohio with 24,000 Instinct MI355X GPUs. These are full-scale projects, not just tests.

Solving Network Transport: The Hidden Bottleneck

The most important technical announcement from the June summit received little attention in mainstream coverage. Network transport, or how data moves between accelerators during distributed training, is now the main limit on cluster efficiency. AMD is addressing this issue directly.

AMD helped start the UALink Consortium, which is creating an open standard for GPU-to-GPU communication across servers and racks. UALink provides 260 TB/s of bandwidth within a rack, offering greater scalability and openness than proprietary options like NVLink. AMD also plans to support UALink over Ultra Ethernet, combining high performance with Ethernet’s flexibility.

The network transport issue is very real. When training large models on hundreds of GPUs, the interconnections among GPUs affect how much time is spent waiting for data updates rather than computing. Cutting interconnect latency by 10% can reduce training time by the same amount, yielding considerable cost savings for long training runs.

With the Helios reference design, performance scales smoothly across 72 GPUs using UALink. UALink connects the GPUs and scale-out NICs, and when used over Ethernet, links all the GPUs in the rack, so they work together as a single system.

AMD Accelerates Rack Scale Infrastructure for Enterprise AI Training

The most consequential implication of all this activity is the enterprise angle. AMD accelerates rack-scale infrastructure for enterprise AI training, making it available not only to hyperscalers but also to thousands of mid-sized organizations, such as regional banks, pharmaceutical companies, and national labs. These groups cannot build massive data centers but still need to handle demanding training jobs.

AMD is well-positioned to support every part of the AI stack, from Instinct GPUs and EPYC CPUs to Pensando DPUs and scale-out networking. All of this is built on open, flexible, and programmable infrastructure made for today’s AI needs.

AMD’s open-ecosystem approach is especially valuable in the enterprise market. For example, a hospital using AI for medical imaging cannot spend months integrating a proprietary system. A financial institution training credit-risk models on sensitive data needs full control over its deployment. AMD’s open-standard solutions, like OCP-compliant racks, UEC-compliant NICs, and ROCm open-source software, help remove the barriers that have kept enterprise AI from moving beyond the testing phase.

The $10 Billion Question

In the first quarter of 2026, AMD reported strong results. Demand for AI infrastructure drove data center revenue up 57% from the previous year. Total revenue hit $10.3 billion, thanks to hyperscalers and enterprise customers expanding their AI capacity. Wall Street analysts expect AMD’s AI GPU revenue for the year to be between $10 billion and $12 billion.

AMD and Meta have signed a multi-year deal to power Meta’s AI infrastructure with up to 6GW of AMD Instinct GPUs. Shipments will start in the second half of 2026, using the Helios rack-scale architecture.

These developments do not guarantee that AMD will catch up to NVIDIA. NVIDIA’s software ecosystem, including CUDA’s long lead time, developer tools, and optimization libraries, remains a major advantage. However, AMD is now competing on more than just chip performance. The company argues that the future of AI infrastructure lies in open systems and that enterprises seeking flexibility should have a supply chain that supports it.

The real test will come when Helios systems are shipped in large numbers in late 2026. AMD’s ability to deliver the combined quality and software reliability that enterprise customers expect will decide if this strategy leads to lasting market share or just a memorable keynote.

Source: AMD Newsroom
- AI
- Troubleshooting
- Smartwatches
- Smartphones
- Camera
- Gadgets
- Games
- Laptops
- Seasonal Sales
Phone Features

Santa Clara, California

Every enterprise technology officer has felt the same bottleneck: a GPU cluster powerful enough to run large language models at scale, throttled not by compute but by the network traffic choking between servers. That friction is not a minor inconvenience. It is a billion-dollar drag on AI ambitions. AMD advancing AI infrastructure at its June 2025 summit in Santa Clara offered what looked, on paper, like a direct answer to that problem — and the scale of the bet AMD is placing makes the proposal worth taking seriously.

AMD Advancing AI: From Chips to Systems

At the Advancing AI 2025 event on June 12, AMD CEO Dr. Lisa Su introduced more than just a new processor. She announced a change in approach. Instead of focusing on having the best GPU, AMD now aims to have the best overall rack system.

This change is important. For years, discussions about AI infrastructure focused on individual accelerator benchmarks like FLOPS, memory bandwidth, and chip size. Now, AMD’s approach is different: it argues that a chip performance does not matter if the system around it cannot move data quickly enough.

At Advancing AI 2025, AMD showed a complete, open-standards rack-scale AI infrastructure. This system is already being used with AMD Instinct MI350 Series GPUs, 5th Gen AMD EPYC processors, and AMD Pensando Pollara NICs in extensive deployments like Oracle Cloud Infrastructure. These are not just future plans—these systems are already running.

The Instinct GPU Arrays Powering the Next Phase

The main hardware feature is the Instinct GPU clusters using the MI350 Series. The Instinct MI355X GPU, built on AMD’s CDNA 4 architecture, offers up to 20 PFLOPS of FP4 performance, 288GB of HBM3E memory, and 8 TB/s of bandwidth. These systems can scale to 128 GPUs per rack with liquid cooling, reaching 2.6 exaFLOPS of AI compute and supporting models with more than 500 billion parameters.

In practical terms, a single Helios rack with 128 MI355X GPUs can train a 500-billion-parameter model without sending data to another rack. For enterprise teams with strict compliance needs, such as financial institutions, healthcare providers, or defense contractors, keeping training within a single secure, isolated rack is not just helpful—it is required.

AMD’s Instinct GPU clusters also have a strong competitive angle. The Helios rack-scale solution will use 72 MI400 Series GPUs, next-generation EPYC Venice CPUs, and Pensando Vulcano network adapters. Compared to the prerelease specs of NVIDIA’s Vera Rubin NVL72, Helios is expected to offer the same scale-up bandwidth and similar FP4 and FP8 performance, but with 50% more HBM4 memory capacity, memory bandwidth, and scale-out bandwidth.

Having more memory in each rack changes how models are served. Operators do not have to split models across many nodes as much, which lowers the delays users notice during inference.

Rethinking the Data Center Ecosystem

The main challenge in the past was building faster GPUs. Now, the focus is on creating a well-integrated data center ecosystem around those GPUs. AMD is tackling this with a multi-layered, open-standards strategy that spans the rack, software, and networking layers.

AMD leads to open standards like the Open Compute Project (OCP), Ultra Accelerator Link (UALink), and Ultra Ethernet Consortium (UEC). This leadership helps the industry scale through collaboration, enabling the development of open, high-performance systems for both scale-up and scale-out AI clusters.

AMD’s data center ecosystem is built to avoid the vendor lock-in seen with NVIDIA’s GB200 NVL72 systems. While NVIDIA’s NVLink fabric keeps customers tied to one vendor, AMD’s approach lets operators choose networking, cooling, and power equipment from different suppliers. For large-scale operators spending billions, this pliability has real financial benefits.

The market has responded quickly. Oracle plans to launch a public AI supercluster with 50,000 Instinct MI450 Series GPUs in Q3 2026, using the Helios rack design, next-gen EPYC Venice CPUs, and Pensando Vulcano networking. Vultr is also building a 50 MW AI supercluster in Ohio with 24,000 Instinct MI355X GPUs. These are full-scale projects, not just tests.

Solving Network Transport: The Hidden Bottleneck

The most important technical announcement from the June summit received little attention in mainstream coverage. Network transport, or how data moves between accelerators during distributed training, is now the main limit on cluster efficiency. AMD is addressing this issue directly.

AMD helped start the UALink Consortium, which is creating an open standard for GPU-to-GPU communication across servers and racks. UALink provides 260 TB/s of bandwidth within a rack, offering greater scalability and openness than proprietary options like NVLink. AMD also plans to support UALink over Ultra Ethernet, combining high performance with Ethernet’s flexibility.

The network transport issue is very real. When training large models on hundreds of GPUs, the interconnections among GPUs affect how much time is spent waiting for data updates rather than computing. Cutting interconnect latency by 10% can reduce training time by the same amount, yielding considerable cost savings for long training runs.

With the Helios reference design, performance scales smoothly across 72 GPUs using UALink. UALink connects the GPUs and scale-out NICs, and when used over Ethernet, links all the GPUs in the rack, so they work together as a single system.

AMD Accelerates Rack Scale Infrastructure for Enterprise AI Training

The most consequential implication of all this activity is the enterprise angle. AMD accelerates rack-scale infrastructure for enterprise AI training, making it available not only to hyperscalers but also to thousands of mid-sized organizations, such as regional banks, pharmaceutical companies, and national labs. These groups cannot build massive data centers but still need to handle demanding training jobs.

AMD is well-positioned to support every part of the AI stack, from Instinct GPUs and EPYC CPUs to Pensando DPUs and scale-out networking. All of this is built on open, flexible, and programmable infrastructure made for today’s AI needs.

AMD’s open-ecosystem approach is especially valuable in the enterprise market. For example, a hospital using AI for medical imaging cannot spend months integrating a proprietary system. A financial institution training credit-risk models on sensitive data needs full control over its deployment. AMD’s open-standard solutions, like OCP-compliant racks, UEC-compliant NICs, and ROCm open-source software, help remove the barriers that have kept enterprise AI from moving beyond the testing phase.

The $10 Billion Question

In the first quarter of 2026, AMD reported strong results. Demand for AI infrastructure drove data center revenue up 57% from the previous year. Total revenue hit $10.3 billion, thanks to hyperscalers and enterprise customers expanding their AI capacity. Wall Street analysts expect AMD’s AI GPU revenue for the year to be between $10 billion and $12 billion.

AMD and Meta have signed a multi-year deal to power Meta’s AI infrastructure with up to 6GW of AMD Instinct GPUs. Shipments will start in the second half of 2026, using the Helios rack-scale architecture.

These developments do not guarantee that AMD will catch up to NVIDIA. NVIDIA’s software ecosystem, including CUDA’s long lead time, developer tools, and optimization libraries, remains a major advantage. However, AMD is now competing on more than just chip performance. The company argues that the future of AI infrastructure lies in open systems and that enterprises seeking flexibility should have a supply chain that supports it.

The real test will come when Helios systems are shipped in large numbers in late 2026. AMD’s ability to deliver the combined quality and software reliability that enterprise customers expect will decide if this strategy leads to lasting market share or just a memorable keynote.

Source: AMD Newsroom
Buying Guides

Santa Clara, California

Every enterprise technology officer has felt the same bottleneck: a GPU cluster powerful enough to run large language models at scale, throttled not by compute but by the network traffic choking between servers. That friction is not a minor inconvenience. It is a billion-dollar drag on AI ambitions. AMD advancing AI infrastructure at its June 2025 summit in Santa Clara offered what looked, on paper, like a direct answer to that problem — and the scale of the bet AMD is placing makes the proposal worth taking seriously.

AMD Advancing AI: From Chips to Systems

At the Advancing AI 2025 event on June 12, AMD CEO Dr. Lisa Su introduced more than just a new processor. She announced a change in approach. Instead of focusing on having the best GPU, AMD now aims to have the best overall rack system.

This change is important. For years, discussions about AI infrastructure focused on individual accelerator benchmarks like FLOPS, memory bandwidth, and chip size. Now, AMD’s approach is different: it argues that a chip performance does not matter if the system around it cannot move data quickly enough.

At Advancing AI 2025, AMD showed a complete, open-standards rack-scale AI infrastructure. This system is already being used with AMD Instinct MI350 Series GPUs, 5th Gen AMD EPYC processors, and AMD Pensando Pollara NICs in extensive deployments like Oracle Cloud Infrastructure. These are not just future plans—these systems are already running.

The Instinct GPU Arrays Powering the Next Phase

The main hardware feature is the Instinct GPU clusters using the MI350 Series. The Instinct MI355X GPU, built on AMD’s CDNA 4 architecture, offers up to 20 PFLOPS of FP4 performance, 288GB of HBM3E memory, and 8 TB/s of bandwidth. These systems can scale to 128 GPUs per rack with liquid cooling, reaching 2.6 exaFLOPS of AI compute and supporting models with more than 500 billion parameters.

In practical terms, a single Helios rack with 128 MI355X GPUs can train a 500-billion-parameter model without sending data to another rack. For enterprise teams with strict compliance needs, such as financial institutions, healthcare providers, or defense contractors, keeping training within a single secure, isolated rack is not just helpful—it is required.

AMD’s Instinct GPU clusters also have a strong competitive angle. The Helios rack-scale solution will use 72 MI400 Series GPUs, next-generation EPYC Venice CPUs, and Pensando Vulcano network adapters. Compared to the prerelease specs of NVIDIA’s Vera Rubin NVL72, Helios is expected to offer the same scale-up bandwidth and similar FP4 and FP8 performance, but with 50% more HBM4 memory capacity, memory bandwidth, and scale-out bandwidth.

Having more memory in each rack changes how models are served. Operators do not have to split models across many nodes as much, which lowers the delays users notice during inference.

Rethinking the Data Center Ecosystem

The main challenge in the past was building faster GPUs. Now, the focus is on creating a well-integrated data center ecosystem around those GPUs. AMD is tackling this with a multi-layered, open-standards strategy that spans the rack, software, and networking layers.

AMD leads to open standards like the Open Compute Project (OCP), Ultra Accelerator Link (UALink), and Ultra Ethernet Consortium (UEC). This leadership helps the industry scale through collaboration, enabling the development of open, high-performance systems for both scale-up and scale-out AI clusters.

AMD’s data center ecosystem is built to avoid the vendor lock-in seen with NVIDIA’s GB200 NVL72 systems. While NVIDIA’s NVLink fabric keeps customers tied to one vendor, AMD’s approach lets operators choose networking, cooling, and power equipment from different suppliers. For large-scale operators spending billions, this pliability has real financial benefits.

The market has responded quickly. Oracle plans to launch a public AI supercluster with 50,000 Instinct MI450 Series GPUs in Q3 2026, using the Helios rack design, next-gen EPYC Venice CPUs, and Pensando Vulcano networking. Vultr is also building a 50 MW AI supercluster in Ohio with 24,000 Instinct MI355X GPUs. These are full-scale projects, not just tests.

Solving Network Transport: The Hidden Bottleneck

The most important technical announcement from the June summit received little attention in mainstream coverage. Network transport, or how data moves between accelerators during distributed training, is now the main limit on cluster efficiency. AMD is addressing this issue directly.

AMD helped start the UALink Consortium, which is creating an open standard for GPU-to-GPU communication across servers and racks. UALink provides 260 TB/s of bandwidth within a rack, offering greater scalability and openness than proprietary options like NVLink. AMD also plans to support UALink over Ultra Ethernet, combining high performance with Ethernet’s flexibility.

The network transport issue is very real. When training large models on hundreds of GPUs, the interconnections among GPUs affect how much time is spent waiting for data updates rather than computing. Cutting interconnect latency by 10% can reduce training time by the same amount, yielding considerable cost savings for long training runs.

With the Helios reference design, performance scales smoothly across 72 GPUs using UALink. UALink connects the GPUs and scale-out NICs, and when used over Ethernet, links all the GPUs in the rack, so they work together as a single system.

AMD Accelerates Rack Scale Infrastructure for Enterprise AI Training

The most consequential implication of all this activity is the enterprise angle. AMD accelerates rack-scale infrastructure for enterprise AI training, making it available not only to hyperscalers but also to thousands of mid-sized organizations, such as regional banks, pharmaceutical companies, and national labs. These groups cannot build massive data centers but still need to handle demanding training jobs.

AMD is well-positioned to support every part of the AI stack, from Instinct GPUs and EPYC CPUs to Pensando DPUs and scale-out networking. All of this is built on open, flexible, and programmable infrastructure made for today’s AI needs.

AMD’s open-ecosystem approach is especially valuable in the enterprise market. For example, a hospital using AI for medical imaging cannot spend months integrating a proprietary system. A financial institution training credit-risk models on sensitive data needs full control over its deployment. AMD’s open-standard solutions, like OCP-compliant racks, UEC-compliant NICs, and ROCm open-source software, help remove the barriers that have kept enterprise AI from moving beyond the testing phase.

The $10 Billion Question

In the first quarter of 2026, AMD reported strong results. Demand for AI infrastructure drove data center revenue up 57% from the previous year. Total revenue hit $10.3 billion, thanks to hyperscalers and enterprise customers expanding their AI capacity. Wall Street analysts expect AMD’s AI GPU revenue for the year to be between $10 billion and $12 billion.

AMD and Meta have signed a multi-year deal to power Meta’s AI infrastructure with up to 6GW of AMD Instinct GPUs. Shipments will start in the second half of 2026, using the Helios rack-scale architecture.

These developments do not guarantee that AMD will catch up to NVIDIA. NVIDIA’s software ecosystem, including CUDA’s long lead time, developer tools, and optimization libraries, remains a major advantage. However, AMD is now competing on more than just chip performance. The company argues that the future of AI infrastructure lies in open systems and that enterprises seeking flexibility should have a supply chain that supports it.

The real test will come when Helios systems are shipped in large numbers in late 2026. AMD’s ability to deliver the combined quality and software reliability that enterprise customers expect will decide if this strategy leads to lasting market share or just a memorable keynote.

Source: AMD Newsroom
Comparison

Santa Clara, California

Every enterprise technology officer has felt the same bottleneck: a GPU cluster powerful enough to run large language models at scale, throttled not by compute but by the network traffic choking between servers. That friction is not a minor inconvenience. It is a billion-dollar drag on AI ambitions. AMD advancing AI infrastructure at its June 2025 summit in Santa Clara offered what looked, on paper, like a direct answer to that problem — and the scale of the bet AMD is placing makes the proposal worth taking seriously.

AMD Advancing AI: From Chips to Systems

At the Advancing AI 2025 event on June 12, AMD CEO Dr. Lisa Su introduced more than just a new processor. She announced a change in approach. Instead of focusing on having the best GPU, AMD now aims to have the best overall rack system.

This change is important. For years, discussions about AI infrastructure focused on individual accelerator benchmarks like FLOPS, memory bandwidth, and chip size. Now, AMD’s approach is different: it argues that a chip performance does not matter if the system around it cannot move data quickly enough.

At Advancing AI 2025, AMD showed a complete, open-standards rack-scale AI infrastructure. This system is already being used with AMD Instinct MI350 Series GPUs, 5th Gen AMD EPYC processors, and AMD Pensando Pollara NICs in extensive deployments like Oracle Cloud Infrastructure. These are not just future plans—these systems are already running.

The Instinct GPU Arrays Powering the Next Phase

The main hardware feature is the Instinct GPU clusters using the MI350 Series. The Instinct MI355X GPU, built on AMD’s CDNA 4 architecture, offers up to 20 PFLOPS of FP4 performance, 288GB of HBM3E memory, and 8 TB/s of bandwidth. These systems can scale to 128 GPUs per rack with liquid cooling, reaching 2.6 exaFLOPS of AI compute and supporting models with more than 500 billion parameters.

In practical terms, a single Helios rack with 128 MI355X GPUs can train a 500-billion-parameter model without sending data to another rack. For enterprise teams with strict compliance needs, such as financial institutions, healthcare providers, or defense contractors, keeping training within a single secure, isolated rack is not just helpful—it is required.

AMD’s Instinct GPU clusters also have a strong competitive angle. The Helios rack-scale solution will use 72 MI400 Series GPUs, next-generation EPYC Venice CPUs, and Pensando Vulcano network adapters. Compared to the prerelease specs of NVIDIA’s Vera Rubin NVL72, Helios is expected to offer the same scale-up bandwidth and similar FP4 and FP8 performance, but with 50% more HBM4 memory capacity, memory bandwidth, and scale-out bandwidth.

Having more memory in each rack changes how models are served. Operators do not have to split models across many nodes as much, which lowers the delays users notice during inference.

Rethinking the Data Center Ecosystem

The main challenge in the past was building faster GPUs. Now, the focus is on creating a well-integrated data center ecosystem around those GPUs. AMD is tackling this with a multi-layered, open-standards strategy that spans the rack, software, and networking layers.

AMD leads to open standards like the Open Compute Project (OCP), Ultra Accelerator Link (UALink), and Ultra Ethernet Consortium (UEC). This leadership helps the industry scale through collaboration, enabling the development of open, high-performance systems for both scale-up and scale-out AI clusters.

AMD’s data center ecosystem is built to avoid the vendor lock-in seen with NVIDIA’s GB200 NVL72 systems. While NVIDIA’s NVLink fabric keeps customers tied to one vendor, AMD’s approach lets operators choose networking, cooling, and power equipment from different suppliers. For large-scale operators spending billions, this pliability has real financial benefits.

The market has responded quickly. Oracle plans to launch a public AI supercluster with 50,000 Instinct MI450 Series GPUs in Q3 2026, using the Helios rack design, next-gen EPYC Venice CPUs, and Pensando Vulcano networking. Vultr is also building a 50 MW AI supercluster in Ohio with 24,000 Instinct MI355X GPUs. These are full-scale projects, not just tests.

Solving Network Transport: The Hidden Bottleneck

The most important technical announcement from the June summit received little attention in mainstream coverage. Network transport, or how data moves between accelerators during distributed training, is now the main limit on cluster efficiency. AMD is addressing this issue directly.

AMD helped start the UALink Consortium, which is creating an open standard for GPU-to-GPU communication across servers and racks. UALink provides 260 TB/s of bandwidth within a rack, offering greater scalability and openness than proprietary options like NVLink. AMD also plans to support UALink over Ultra Ethernet, combining high performance with Ethernet’s flexibility.

The network transport issue is very real. When training large models on hundreds of GPUs, the interconnections among GPUs affect how much time is spent waiting for data updates rather than computing. Cutting interconnect latency by 10% can reduce training time by the same amount, yielding considerable cost savings for long training runs.

With the Helios reference design, performance scales smoothly across 72 GPUs using UALink. UALink connects the GPUs and scale-out NICs, and when used over Ethernet, links all the GPUs in the rack, so they work together as a single system.

AMD Accelerates Rack Scale Infrastructure for Enterprise AI Training

The most consequential implication of all this activity is the enterprise angle. AMD accelerates rack-scale infrastructure for enterprise AI training, making it available not only to hyperscalers but also to thousands of mid-sized organizations, such as regional banks, pharmaceutical companies, and national labs. These groups cannot build massive data centers but still need to handle demanding training jobs.

AMD is well-positioned to support every part of the AI stack, from Instinct GPUs and EPYC CPUs to Pensando DPUs and scale-out networking. All of this is built on open, flexible, and programmable infrastructure made for today’s AI needs.

AMD’s open-ecosystem approach is especially valuable in the enterprise market. For example, a hospital using AI for medical imaging cannot spend months integrating a proprietary system. A financial institution training credit-risk models on sensitive data needs full control over its deployment. AMD’s open-standard solutions, like OCP-compliant racks, UEC-compliant NICs, and ROCm open-source software, help remove the barriers that have kept enterprise AI from moving beyond the testing phase.

The $10 Billion Question

In the first quarter of 2026, AMD reported strong results. Demand for AI infrastructure drove data center revenue up 57% from the previous year. Total revenue hit $10.3 billion, thanks to hyperscalers and enterprise customers expanding their AI capacity. Wall Street analysts expect AMD’s AI GPU revenue for the year to be between $10 billion and $12 billion.

AMD and Meta have signed a multi-year deal to power Meta’s AI infrastructure with up to 6GW of AMD Instinct GPUs. Shipments will start in the second half of 2026, using the Helios rack-scale architecture.

These developments do not guarantee that AMD will catch up to NVIDIA. NVIDIA’s software ecosystem, including CUDA’s long lead time, developer tools, and optimization libraries, remains a major advantage. However, AMD is now competing on more than just chip performance. The company argues that the future of AI infrastructure lies in open systems and that enterprises seeking flexibility should have a supply chain that supports it.

The real test will come when Helios systems are shipped in large numbers in late 2026. AMD’s ability to deliver the combined quality and software reliability that enterprise customers expect will decide if this strategy leads to lasting market share or just a memorable keynote.

Source: AMD Newsroom
News

Santa Clara, California

Every enterprise technology officer has felt the same bottleneck: a GPU cluster powerful enough to run large language models at scale, throttled not by compute but by the network traffic choking between servers. That friction is not a minor inconvenience. It is a billion-dollar drag on AI ambitions. AMD advancing AI infrastructure at its June 2025 summit in Santa Clara offered what looked, on paper, like a direct answer to that problem — and the scale of the bet AMD is placing makes the proposal worth taking seriously.

AMD Advancing AI: From Chips to Systems

At the Advancing AI 2025 event on June 12, AMD CEO Dr. Lisa Su introduced more than just a new processor. She announced a change in approach. Instead of focusing on having the best GPU, AMD now aims to have the best overall rack system.

This change is important. For years, discussions about AI infrastructure focused on individual accelerator benchmarks like FLOPS, memory bandwidth, and chip size. Now, AMD’s approach is different: it argues that a chip performance does not matter if the system around it cannot move data quickly enough.

At Advancing AI 2025, AMD showed a complete, open-standards rack-scale AI infrastructure. This system is already being used with AMD Instinct MI350 Series GPUs, 5th Gen AMD EPYC processors, and AMD Pensando Pollara NICs in extensive deployments like Oracle Cloud Infrastructure. These are not just future plans—these systems are already running.

The Instinct GPU Arrays Powering the Next Phase

The main hardware feature is the Instinct GPU clusters using the MI350 Series. The Instinct MI355X GPU, built on AMD’s CDNA 4 architecture, offers up to 20 PFLOPS of FP4 performance, 288GB of HBM3E memory, and 8 TB/s of bandwidth. These systems can scale to 128 GPUs per rack with liquid cooling, reaching 2.6 exaFLOPS of AI compute and supporting models with more than 500 billion parameters.

In practical terms, a single Helios rack with 128 MI355X GPUs can train a 500-billion-parameter model without sending data to another rack. For enterprise teams with strict compliance needs, such as financial institutions, healthcare providers, or defense contractors, keeping training within a single secure, isolated rack is not just helpful—it is required.

AMD’s Instinct GPU clusters also have a strong competitive angle. The Helios rack-scale solution will use 72 MI400 Series GPUs, next-generation EPYC Venice CPUs, and Pensando Vulcano network adapters. Compared to the prerelease specs of NVIDIA’s Vera Rubin NVL72, Helios is expected to offer the same scale-up bandwidth and similar FP4 and FP8 performance, but with 50% more HBM4 memory capacity, memory bandwidth, and scale-out bandwidth.

Having more memory in each rack changes how models are served. Operators do not have to split models across many nodes as much, which lowers the delays users notice during inference.

Rethinking the Data Center Ecosystem

The main challenge in the past was building faster GPUs. Now, the focus is on creating a well-integrated data center ecosystem around those GPUs. AMD is tackling this with a multi-layered, open-standards strategy that spans the rack, software, and networking layers.

AMD leads to open standards like the Open Compute Project (OCP), Ultra Accelerator Link (UALink), and Ultra Ethernet Consortium (UEC). This leadership helps the industry scale through collaboration, enabling the development of open, high-performance systems for both scale-up and scale-out AI clusters.

AMD’s data center ecosystem is built to avoid the vendor lock-in seen with NVIDIA’s GB200 NVL72 systems. While NVIDIA’s NVLink fabric keeps customers tied to one vendor, AMD’s approach lets operators choose networking, cooling, and power equipment from different suppliers. For large-scale operators spending billions, this pliability has real financial benefits.

The market has responded quickly. Oracle plans to launch a public AI supercluster with 50,000 Instinct MI450 Series GPUs in Q3 2026, using the Helios rack design, next-gen EPYC Venice CPUs, and Pensando Vulcano networking. Vultr is also building a 50 MW AI supercluster in Ohio with 24,000 Instinct MI355X GPUs. These are full-scale projects, not just tests.

Solving Network Transport: The Hidden Bottleneck

The most important technical announcement from the June summit received little attention in mainstream coverage. Network transport, or how data moves between accelerators during distributed training, is now the main limit on cluster efficiency. AMD is addressing this issue directly.

AMD helped start the UALink Consortium, which is creating an open standard for GPU-to-GPU communication across servers and racks. UALink provides 260 TB/s of bandwidth within a rack, offering greater scalability and openness than proprietary options like NVLink. AMD also plans to support UALink over Ultra Ethernet, combining high performance with Ethernet’s flexibility.

The network transport issue is very real. When training large models on hundreds of GPUs, the interconnections among GPUs affect how much time is spent waiting for data updates rather than computing. Cutting interconnect latency by 10% can reduce training time by the same amount, yielding considerable cost savings for long training runs.

With the Helios reference design, performance scales smoothly across 72 GPUs using UALink. UALink connects the GPUs and scale-out NICs, and when used over Ethernet, links all the GPUs in the rack, so they work together as a single system.

AMD Accelerates Rack Scale Infrastructure for Enterprise AI Training

The most consequential implication of all this activity is the enterprise angle. AMD accelerates rack-scale infrastructure for enterprise AI training, making it available not only to hyperscalers but also to thousands of mid-sized organizations, such as regional banks, pharmaceutical companies, and national labs. These groups cannot build massive data centers but still need to handle demanding training jobs.

AMD is well-positioned to support every part of the AI stack, from Instinct GPUs and EPYC CPUs to Pensando DPUs and scale-out networking. All of this is built on open, flexible, and programmable infrastructure made for today’s AI needs.

AMD’s open-ecosystem approach is especially valuable in the enterprise market. For example, a hospital using AI for medical imaging cannot spend months integrating a proprietary system. A financial institution training credit-risk models on sensitive data needs full control over its deployment. AMD’s open-standard solutions, like OCP-compliant racks, UEC-compliant NICs, and ROCm open-source software, help remove the barriers that have kept enterprise AI from moving beyond the testing phase.

The $10 Billion Question

In the first quarter of 2026, AMD reported strong results. Demand for AI infrastructure drove data center revenue up 57% from the previous year. Total revenue hit $10.3 billion, thanks to hyperscalers and enterprise customers expanding their AI capacity. Wall Street analysts expect AMD’s AI GPU revenue for the year to be between $10 billion and $12 billion.

AMD and Meta have signed a multi-year deal to power Meta’s AI infrastructure with up to 6GW of AMD Instinct GPUs. Shipments will start in the second half of 2026, using the Helios rack-scale architecture.

These developments do not guarantee that AMD will catch up to NVIDIA. NVIDIA’s software ecosystem, including CUDA’s long lead time, developer tools, and optimization libraries, remains a major advantage. However, AMD is now competing on more than just chip performance. The company argues that the future of AI infrastructure lies in open systems and that enterprises seeking flexibility should have a supply chain that supports it.

The real test will come when Helios systems are shipped in large numbers in late 2026. AMD’s ability to deliver the combined quality and software reliability that enterprise customers expect will decide if this strategy leads to lasting market share or just a memorable keynote.

Source: AMD Newsroom
Contact

Santa Clara, California

Every enterprise technology officer has felt the same bottleneck: a GPU cluster powerful enough to run large language models at scale, throttled not by compute but by the network traffic choking between servers. That friction is not a minor inconvenience. It is a billion-dollar drag on AI ambitions. AMD advancing AI infrastructure at its June 2025 summit in Santa Clara offered what looked, on paper, like a direct answer to that problem — and the scale of the bet AMD is placing makes the proposal worth taking seriously.

AMD Advancing AI: From Chips to Systems

At the Advancing AI 2025 event on June 12, AMD CEO Dr. Lisa Su introduced more than just a new processor. She announced a change in approach. Instead of focusing on having the best GPU, AMD now aims to have the best overall rack system.

This change is important. For years, discussions about AI infrastructure focused on individual accelerator benchmarks like FLOPS, memory bandwidth, and chip size. Now, AMD’s approach is different: it argues that a chip performance does not matter if the system around it cannot move data quickly enough.

At Advancing AI 2025, AMD showed a complete, open-standards rack-scale AI infrastructure. This system is already being used with AMD Instinct MI350 Series GPUs, 5th Gen AMD EPYC processors, and AMD Pensando Pollara NICs in extensive deployments like Oracle Cloud Infrastructure. These are not just future plans—these systems are already running.

The Instinct GPU Arrays Powering the Next Phase

The main hardware feature is the Instinct GPU clusters using the MI350 Series. The Instinct MI355X GPU, built on AMD’s CDNA 4 architecture, offers up to 20 PFLOPS of FP4 performance, 288GB of HBM3E memory, and 8 TB/s of bandwidth. These systems can scale to 128 GPUs per rack with liquid cooling, reaching 2.6 exaFLOPS of AI compute and supporting models with more than 500 billion parameters.

In practical terms, a single Helios rack with 128 MI355X GPUs can train a 500-billion-parameter model without sending data to another rack. For enterprise teams with strict compliance needs, such as financial institutions, healthcare providers, or defense contractors, keeping training within a single secure, isolated rack is not just helpful—it is required.

AMD’s Instinct GPU clusters also have a strong competitive angle. The Helios rack-scale solution will use 72 MI400 Series GPUs, next-generation EPYC Venice CPUs, and Pensando Vulcano network adapters. Compared to the prerelease specs of NVIDIA’s Vera Rubin NVL72, Helios is expected to offer the same scale-up bandwidth and similar FP4 and FP8 performance, but with 50% more HBM4 memory capacity, memory bandwidth, and scale-out bandwidth.

Having more memory in each rack changes how models are served. Operators do not have to split models across many nodes as much, which lowers the delays users notice during inference.

Rethinking the Data Center Ecosystem

The main challenge in the past was building faster GPUs. Now, the focus is on creating a well-integrated data center ecosystem around those GPUs. AMD is tackling this with a multi-layered, open-standards strategy that spans the rack, software, and networking layers.

AMD leads to open standards like the Open Compute Project (OCP), Ultra Accelerator Link (UALink), and Ultra Ethernet Consortium (UEC). This leadership helps the industry scale through collaboration, enabling the development of open, high-performance systems for both scale-up and scale-out AI clusters.

AMD’s data center ecosystem is built to avoid the vendor lock-in seen with NVIDIA’s GB200 NVL72 systems. While NVIDIA’s NVLink fabric keeps customers tied to one vendor, AMD’s approach lets operators choose networking, cooling, and power equipment from different suppliers. For large-scale operators spending billions, this pliability has real financial benefits.

The market has responded quickly. Oracle plans to launch a public AI supercluster with 50,000 Instinct MI450 Series GPUs in Q3 2026, using the Helios rack design, next-gen EPYC Venice CPUs, and Pensando Vulcano networking. Vultr is also building a 50 MW AI supercluster in Ohio with 24,000 Instinct MI355X GPUs. These are full-scale projects, not just tests.

Solving Network Transport: The Hidden Bottleneck

The most important technical announcement from the June summit received little attention in mainstream coverage. Network transport, or how data moves between accelerators during distributed training, is now the main limit on cluster efficiency. AMD is addressing this issue directly.

AMD helped start the UALink Consortium, which is creating an open standard for GPU-to-GPU communication across servers and racks. UALink provides 260 TB/s of bandwidth within a rack, offering greater scalability and openness than proprietary options like NVLink. AMD also plans to support UALink over Ultra Ethernet, combining high performance with Ethernet’s flexibility.

The network transport issue is very real. When training large models on hundreds of GPUs, the interconnections among GPUs affect how much time is spent waiting for data updates rather than computing. Cutting interconnect latency by 10% can reduce training time by the same amount, yielding considerable cost savings for long training runs.

With the Helios reference design, performance scales smoothly across 72 GPUs using UALink. UALink connects the GPUs and scale-out NICs, and when used over Ethernet, links all the GPUs in the rack, so they work together as a single system.

AMD Accelerates Rack Scale Infrastructure for Enterprise AI Training

The most consequential implication of all this activity is the enterprise angle. AMD accelerates rack-scale infrastructure for enterprise AI training, making it available not only to hyperscalers but also to thousands of mid-sized organizations, such as regional banks, pharmaceutical companies, and national labs. These groups cannot build massive data centers but still need to handle demanding training jobs.

AMD is well-positioned to support every part of the AI stack, from Instinct GPUs and EPYC CPUs to Pensando DPUs and scale-out networking. All of this is built on open, flexible, and programmable infrastructure made for today’s AI needs.

AMD’s open-ecosystem approach is especially valuable in the enterprise market. For example, a hospital using AI for medical imaging cannot spend months integrating a proprietary system. A financial institution training credit-risk models on sensitive data needs full control over its deployment. AMD’s open-standard solutions, like OCP-compliant racks, UEC-compliant NICs, and ROCm open-source software, help remove the barriers that have kept enterprise AI from moving beyond the testing phase.

The $10 Billion Question

In the first quarter of 2026, AMD reported strong results. Demand for AI infrastructure drove data center revenue up 57% from the previous year. Total revenue hit $10.3 billion, thanks to hyperscalers and enterprise customers expanding their AI capacity. Wall Street analysts expect AMD’s AI GPU revenue for the year to be between $10 billion and $12 billion.

AMD and Meta have signed a multi-year deal to power Meta’s AI infrastructure with up to 6GW of AMD Instinct GPUs. Shipments will start in the second half of 2026, using the Helios rack-scale architecture.

These developments do not guarantee that AMD will catch up to NVIDIA. NVIDIA’s software ecosystem, including CUDA’s long lead time, developer tools, and optimization libraries, remains a major advantage. However, AMD is now competing on more than just chip performance. The company argues that the future of AI infrastructure lies in open systems and that enterprises seeking flexibility should have a supply chain that supports it.

The real test will come when Helios systems are shipped in large numbers in late 2026. AMD’s ability to deliver the combined quality and software reliability that enterprise customers expect will decide if this strategy leads to lasting market share or just a memorable keynote.

Source: AMD Newsroom

Why Is AMD Building Massive $10 Billion AI Hubs?

Harish Shenoy
June 23, 2026
10 min read
45

Santa Clara, California Every enterprise technology officer has felt the same bottleneck: a GPU cluster powerful enough to run large language models at scale, throttled... Details

Where Can You Download Cisco’s Automatic Virus Shields?

Harish Shenoy
June 23, 2026
8 min read
64

San Jose, California Cisco Live Protect Is Already Running Before the Threat Arrives At 2 a.m., a hospital network in Phoenix finds out that a common... Details

How Will Intel’s New GPU Fix Hot Server Lag Forever?

Harish Shenoy
June 23, 2026
7 min read
57

Santa Clara, California When an inference server is overloaded and struggling with a 400-watt thermal limit, an enterprise’s AI agent can end up waiting for memory bandwidth... Details

How Can New Smart Glasses Run AI With Zero Cloud Lag?

Harish Shenoy
June 23, 2026
9 min read
59

San Diego, California Every instant a smart device waits for a cloud server to respond, another company is working on hardware that responds instantly. This... Details

Which Scary Data Traps Are Trapping 91% Of Bosses?

Harish Shenoy
June 22, 2026
10 min read
64

Armonk, New York Nine out of ten executives at large companies do not actually know which AI systems they rely on. This is not just... Details

Where Are NVIDIA’s Creepy New Heavy-Duty Robots Going?

Harish Shenoy
June 22, 2026
9 min read
49

Santa Clara, California A warehouse forklift that can spot a misplaced pallet, avoid workers, and keep unloading cargo on its own used to seem like... Details

Why Did the US Military Give Dell 9.7 Billion Bucks?

Harish Shenoy
June 22, 2026
9 min read
55

Round Rock, Texas Today’s military operations depend on digital systems just as much as on vehicles or aircraft. If software updates are delayed or email systems... Details

What Secret Chip Deal Did Apple Make With Intel Now?

Harish Shenoy
June 22, 2026
8 min read
57

Cupertino, California The last time Apple and Intel worked closely together, things ended badly. In 2020, Apple stopped using Intel processors and switched to its... Details

Who Is Replacing Google’s Top Nobel Scientist Today?

Harish Shenoy
June 22, 2026
9 min read
77

Mountain View, California Last year, for every three engineers who left Anthropic for Google DeepMind, thirty-seven went the other way. On June 19, 2026, the most... Details

When Can You Win Free Groceries On Prime Day 2026?

Harish Shenoy
June 22, 2026
9 min read
53

Seattle, Washington Moving Prime Day up by just one week can shift billions of dollars in spending. Amazon is counting on this by holding Amazon Prime... Details

Prev.
1
…
12
13
14
15
16
…
190
Next

Latest post

Mallory McMorrow Suspends Michigan Senate Campaign Before August Primary

Russia Kills 15 in Massive Kyiv Missile Strike Before NATO Summit

Dow Jones Hits Record 53000 as Tech Stocks Rebound Sharply

Popular Posts

Best Budget Smartphones 2026: Affordable Phones That Impress (4157)

Best Business Laptops 2025 (3830)

The Future Is Calling: Top Upcoming Smartphones of 2026 You’ll Want to Wait For (3193)

DSLR vs Mirrorless: Which Is Better for Photography Beginners? (2542)

NIST Update Signals Fast Track for Post-Quantum Standards (2349)

Stay Connected

Category: News