Sold by: Aurora Labs
Deployed on AWS
LOCI Large Code Language Model (LCLM) for Time Prediction on ARMv8 AArch64 ASM
The model takes ARM 64-bit assembly language blocks as input and provides cycle time and its standard deviation for the given block
Overview
The model takes ARMv8 AArch64 assembly blocks as input and predicts execution time and standard deviation for each block on the Cortex-A53 core.
Highlights
- Predicts mean execution time (in nanoseconds) on the ARM Cortex-A53 core
- Estimates standard deviation to capture timing variability
- Supports timing-aware code optimization and performance tuning
Details
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.g5.xlarge Inference (Batch) Recommended | Model inference on the ml.g5.xlarge instance type, batch mode | $5.00 |
ml.g5.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g5.xlarge instance type, real-time mode | $5.00 |
Dimensions summary
You pay by the hour on the ml.g5.xlarge instance, billed for the time the model runs. Two options split by how you send work. Batch mode processes grouped inputs together, suited to jobs you can queue. Real-Time mode handles requests as they arrive, suited to interactive use. Both run on the same instance type, so your cost depends on which mode you pick and how many host hours you use. There are no per-call charges beyond the hourly host rate.
Top-of-mind questions for buyers
Both modes bill by host hour on the same instance type. Batch mode groups inputs and processes them together, suited to queued jobs. Real-Time mode handles each request as it arrives, suited to interactive use. Your mode choice affects how the instance runs, not the per-hour metering method.
Software charges accrue per host hour while the instance runs. A fully stopped instance does not accrue software host charges. Underlying AWS infrastructure fees, such as storage, may still apply separately based on your AWS account resources.
The model predicts execution behavior from compiled binaries, including per-function response time, energy cost, worst-case stack depth, throughput, and cache miss rates. It reads the binary rather than source code. These predictions run on the ml.g5.xlarge instance in either batch or real-time mode.
www.auroralabs.com
Helpful?
Vendor refund policy
no refunds
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Initial ML model release for Amazon SageMaker through AWS Marketplace
Additional details
Inputs
- Summary
The input has to be a csv file, with one column named 'r.asm'. Each row can be assembly code based on the ARMv8 aarch64 architecture. The code snippet below shows how to load the data in Python using the pandas package.
data = pandas.read_csv('../data/arm_dataset.csv')
More detailed example is available in the Jupyter notebooks.
- Limitations for input type
- The csv file should have less than 2000 rows, for optimal performance. It is recommended that the length of one sample of assembly code is not longer than 500 instructions.
https://github.com/auroralabs-loci/auroralabs_loci_marketplace/blob/main/data/arm_dataset.csv
https://github.com/auroralabs-loci/auroralabs_loci_marketplace/blob/main/data/arm_dataset.csv
Support
Vendor support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
The Loci-Stream CFD code is a scalable parallel tool for fluid-flow and heat transfer simulations in large scale industrial applications. Many of the common features found in other standard CFD tools such as ANSYS-Fluent and Star-CCM+ are available. If you are interested in testing Loci-Stream, see the tutorials page on our website which contains run control and grid files for a number of cases that can be run directly.
LOCI, Line-of-Code Intelligence platform, transforms observability and shift-left approach by extracting deep performance insights from compiled binaries (e.g., C/C++, Go, Rust), without requiring source code. Traditional static analysis and observability tools fail to detect performance issues in compiled BIN files due to missing execution context, hardware interactions, and real-time software behavior analysis. LOCI bridges this gap by modeling compiled binaries with real-world execution data, enabling early detection of performance degradations, power inefficiencies, and test coverage prediction, after project build.
LOCI LCLM for Time prediction on TriCore 64-bit assembly code.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.