KeynoteISCA 2026, June 27, 2026

Computing at the Crossroads

In her ISCA 2026 keynote, our CEO, Dr. Debbie Marr, explains why now is the time to build a high-performance, general-purpose RISC-V CPU and which shifts in architecture, economics, and software make it possible.

Watch the keynote ↗
Our mission

Everybody deserves better compute

We are designing a high-performance, general-purpose RISC-V CPU. Our focus is per-core performance, because it sets the pace for AI infrastructure, the data center, and the devices you use every day. A core with higher per-core performance can also match a slower core at a lower voltage and frequency, which reduces power.

A better computer puts its owner's interests ahead of any third party that profits from the owner's data or dependence. It protects the owner's money, time, and attention, and it does what the owner tells it to do. We design our CPUs for computers like that.

AheadComputing coreCycle-level simulation
FIG. 01 Our core running three workloads: each instruction executes as soon as its inputs are ready and retires in program orderEach view replays 300 consecutive instructions from a cycle-level simulation of our core. The segments were selected to show peak behavior and are not averages.
Conventional core
Today's per-core performance
100%Accelerator utilization
Batches completed0
1.5x faster core
1.5x per-core performance
100%Accelerator utilization
Batches completed0
FIG. 02 Same workload and accelerators, with a different CPUThis is a conceptual model, and its values are illustrative.
The constraint

In AI infrastructure, the CPU now sets the pace

Accelerators perform the parallel mathematics of AI. The CPU runs everything around it, including data preparation, scheduling, networking, and the control logic of agentic workloads. When the CPU falls behind, the accelerators wait.

CPU-to-GPU ratio in AI systems
CPU
GPU

FIG. 03 CPU-to-GPU ratio in AI systemsThe ratios come from Lip-Bu Tan, chief executive officer of Intel, in April 2026.

“The most important thing is single-threaded performance... If the CPU gets throttled, then we're holding back a whole bunch of GPUs.”
Jensen Huang, chief executive officer of NVIDIA, GTC 2026, March 2026
“CPUs are making a massive comeback: 35% annual growth.”
Lisa Su, chief executive officer of AMD, May 2026
“Earlier predictions of a 4x increase in CPU core requirements are now being discussed at 8x or even 10x by the industry.”
Rene Haas, chief executive officer of Arm, June 2026
Conventional core, 64 cores15.4x
Faster core, 64 cores23.1x
Conventional cores needed to matchn/a
FIG. 04 Amdahl's Law: speedup = P / (s + (1 − s) / n)Here s is the serial fraction, n is the number of cores, and P is the per-core performance.
The principle

More cores cannot compensate for slower cores

Amdahl's Law sets a limit. The serial portion of a workload caps the speedup that parallel hardware can deliver, so each added core yields a smaller gain. Raising per-core performance raises the speedup at every core count.

At advanced process nodes, every square millimeter of silicon is expensive. For any workload with a serial fraction, higher per-core performance raises throughput at every core count, and system throughput is what you pay for.

Adjust the controls to test the relationship.

The economics

Silicon economics now favor general-purpose design

Leading-edge wafers take longer to fabricate and cost more at every node. Advanced packaging adds months of lead time and significant cost per unit. Under these conditions, hardware returns depend on longevity and time to market. Specialized accelerators face a harder path. General-purpose processors win on workload diversity, longevity, and time to market.

FIG. 05 Wafer fabrication cycle time by technology node, in weeksThe values are approximate.
1 to 2Months for a typical advanced packaging cycle
+9 to 12Months of additional packaging lead time
~$750Packaging cost per unit, NVIDIA H100/H200
$1,100Packaging cost per unit, NVIDIA B100/B200
ImplicationWhen chips take longer to fabricate and cost more to package, every design has to stay useful for longer. General-purpose processors keep serving new workloads long after a specialized design falls behind.
The transition

The architecture transition is underway

Hyperscale cloud providers, including Microsoft, have spent the past decade moving workloads away from x86. The toolchains, memory models, and migration practices built for that transition now apply directly to RISC-V, and GCC, LLVM, and the Linux kernel treat RISC architectures as first-class targets.

1996
Pentium Pro

Intel positioned the Pentium Pro, its first P6-family processor, for servers and workstations. It disproved the belief that x86 could not be fast. Dr. Debbie Marr served as its server architect.

2018
AWS Graviton

Virtually all workloads ran on Intel chips until we invented Graviton in 2018. Andy Jassy, chief executive officer of Amazon, made this statement.

2024
Windows on Arm

Arm-based Windows PCs reach the mainstream with Qualcomm. NVIDIA announced its N1X PC processor at Computex 2026.

2025
Google goes multi-architecture

Google migrated more than 30,000 applications from x86 to Arm and published a path to datacenter-scale RISC-V.

2031 Projected
RISC-V at 33.7%

The SHD Group projects that RISC-V will reach 33.7% of processor revenue in 2031, up from 2.5% in 2021.

FIG. 06 Milestones in the architecture transitionThe 2031 value is a projection by The SHD Group. NVIDIA's N1X announcement was reported by Entrepreneur in June 2026. Google reported the 30,000 applications in “Using AI and automation to migrate between instruction sets,” October 21, 2025.

In 1996, the industry said x86 could not be fast. Today it says the same about RISC-V.

The same toolchains and practices that carried hyperscale software from x86 to Arm now lead to RISC-V.

FIG. 07 How software moves from x86 to Arm to RISC-VOur summary of the path Google described at RISC-V Summit North America, October 2025.
Our approach

We build RISC-V without compromise

We combine the openness and extensibility of RISC-V with a new microarchitecture designed to show that an open instruction set can lead on performance and power efficiency in data center, client, mobile, and embedded markets.

Clean-slate architecture

RISC-V carries no x86 legacy and none of Arm's licensing costs and constraints. We spend our design effort on performance rather than on compatibility.

Per-core performance first

Our core is wide, deep, and out of order, and we design it to hide memory latency and find instruction-level parallelism at low energy per instruction. Per-core performance is the key to multi-core performance.

Server-grade from inception

The architects behind Intel's Pentium Pro, Nehalem, and Haswell generations are designing it, and they build in the reliability that data centers expect from the start.

Investors

Investors in frontier hardware back AheadComputing

AheadComputing has raised $53M to date. The $30M Seed2 round was co-led by Eclipse, Toyota Ventures, and Cambium.

Ecosystem

We develop our first product with leading ecosystem partners

Our first product is in development through collaborations with semiconductor ecosystem partners, alongside design exploration with hyperscalers and compute providers.

Company descriptions are drawn from each organization's public materials. Logos are trademarks of their respective owners.

Featured keynote, ISCA 2026

Computing at the Crossroads: Architecture, Economics, and the Next Era

Dr. Debbie Marr, CEOJune 27, 2026International Symposium on Computer Architecture
Three conclusions

Now is the moment for a new CPU

PART 1

It is a great time to build high-performance CPUs

Agentic AI is creating urgency. CPUs bottleneck accelerator throughput, and agentic workloads run largely on CPUs.

PART 2

It is a great time to build a RISC-V CPU

The software ecosystem is in motion. RISC-V is a clean-slate architecture, and AI-enabled toolchains ease the transition.

PART 3

It is a great time for general-purpose computing

Manufacturing time and cost are rising. General-purpose designs win on workload diversity, longevity, and time to market.

In the news
All news →
Careers

Build the next generation of CPUs from a clean slate

We are hiring CPU architects, performance modelers, and verification engineers who want to define high-performance computing for the next decade.

Portland, OregonAustin, TexasGuadalajara, Mexico