Skip to content

Architecture & Engine

From existing code to parallel placement.

A plain technical view of how ORIQX connects beneath your stack, partitions workloads across five steps, and respects clear operational boundaries.

The problem

Hardware capability climbs. Capacity sits idle.

Static placement pins mixed workloads onto one processor type. Data moves unnecessarily between nodes while expensive accelerators stall waiting on sequential code—and AI agent loops multiply that waste.

The compute world is changing, fast.

More potential than ever. Used poorly, it gets expensive.

Each mark is a new kind of chip, or a leap in AI.
A new kind of chipA leap in AI
TIME →COMPUTE →POTENTIALWHAT YOU PAYWHAT YOU USE

Fixed placement waste

Mixed math trapped on one-size hardware

A single job mixes sequential logic, sparse solves, memory transfers, and parallel matrix math. Running all of it on one chip class leaves processors underused and stretches wall time.

The agentic multiplier

Short prompts trigger hidden heavy compute

Autonomous agents launch retries, parallel sweeps, and heavy tool calls beneath the surface. Without pre-run pricing and placement, compute bills climb unseen.

Stack fit

Sits beneath your existing stack.

ORIQX is a frictionless solution—no code rewrites are required.

  • Application code, job submission paths, and access boundaries stay as they are.
  • Reach CPUs, GPUs, TPUs, NPUs, and QPUs across data centres, HPC clusters, and cloud accounts.
  • Works underneath existing orchestrators, queues, and agent frameworks without replacing them.

Your code & workloads

Keep solvers, scripts, and applications intact

Queues & agent frameworks

Existing orchestrators keep control of approvals

ORIQX compute engine

Partitions blocks and chooses chip placement

Any reachable compute pool

Fully managed or self-managed across owned clusters and clouds

Preflight · multi-stage compute job
OX

Options scored for time, cost, energy, and accuracy before dispatch.

CPUsGPUsTPUsNPUsQPUs+ more classes added as needed

CPU, GPU, TPU, NPU, and QPU execution

How it works

Five engine steps from code to chips.

Rather than running an entire job monolithically on one processor class, ORIQX breaks programs into compute blocks, predicts each block per chip, and searches for the split that meets your goal.

Inside the engine: how work is partitioned.

ORIQX COMPUTE LANGUAGESays what to compute,not where to run it.Separating compute intent fromplacement lets the engine pickthe right chip for every block.EXISTING CODE INBring code from anylanguage as it is—withno manual rewrite.Python · C++ · Rust · Julia · GoNO REWRITEYOUR PROGRAMFinds math blocks and data flow between themDense linear algebraSparse solvesFFTsAttentionGraph searchQuantum step01 · COMPUTE BLOCKS & DATATime · Cost · Energy · Accuracy per blockCPUGPUTPUNPUQPU02 · PREDICT PER CHIP CLASSMeets your goal across all blocks + data transferSpeedCostEnergyAccuracySELECTED SPLITBlock runtime + inter-chip data movement03 · SEARCH THE SPLITPrepares each block for its chip and executes across lanesCPUGPUTPUNPUQPU+ new chip classes added as customers need them04 · PREPARE & RUN IN PARALLELMeasures what actually happened to sharpen the next predictionDense linear algebraSparse solvesFFTsQuantum step05 · MEASURE & SHARPEN
01

Find compute blocks & data

Reads the program and finds its compute blocks, the kinds of math it does (dense linear algebra, sparse solves, FFTs, attention, graph search), and how data moves between them.

02

Predict per chip class

Predicts each block's time, cost, energy, and accuracy on each chip class it can use.

03

Search the split

Searches for the split that best meets your goal across all blocks, counting the cost of moving data between chips.

04

Prepare & run in parallel

Prepares each block for its chip and runs blocks in parallel across your infrastructure.

05

Measure & sharpen

Measures what actually happened and uses it to sharpen the next prediction.

Compute language & zero-rewrite intake

Bring code as it is—into the ORIQX compute language

The ORIQX compute language describes what to compute rather than where to run it—allowing the engine to choose and combine chip classes freely.

Existing programs written in Python, C++, Rust, Julia, Go, and more enter as they are without rewriting code around specific hardware targets.

Supported hardware

CPUs, GPUs, TPUs, NPUs, and QPUs—plus more as needed

Workloads run on CPUs, GPUs, TPUs, NPUs, and QPUs. ORIQX adds new chip classes as customers need them.

Explicit boundaries

Five plain questions for technical teams.

Every deployment agrees service placement, approval authority, and infrastructure ownership upfront.

What changes in application code?

Nothing. Existing programs and pipelines stay unchanged; ORIQX operates beneath your workflow entrypoints.

Where do workloads execute?

Either on compute ORIQX provides and runs (fully managed) or inside your data centre, HPC cluster, or cloud accounts (self-managed).

Who approves compute spend before execution?

Preflight presents predicted time, cost, energy, and accuracy options first—nothing runs or spends until you or your policy goal approve.

Does Estimate touch or run on unowned hardware?

No. Estimate scores program work against ORIQX chip-class performance profiles with zero candidate hardware access and zero execution.

Which chip classes are supported?

CPUs, GPUs, TPUs, NPUs, and QPUs. ORIQX adds new chip classes as customers need them.