Arithmetic is the design choice. pre spin changes the datapath arithmetic at RTL and proves the change with a formal error bound.
How it works
RTL in, formal error bound, optimised RTL out.
-
Your RTL
The datapath block as it stands. Start with a throwaway block if you prefer.
- Format
- RTL
- Confidentiality
- Can be agreed upfront
-
A formal error bound
The datapath arithmetic changes, and a formal error bound proves the change.
- Bound
- Formal
- Level
- RTL
-
Three things back
Optimised RTL, a bit-exact Python model and test vectors, so you can check it yourself.
- Optimised RTL
- Yes
- Python model
- Bit-exact
- Test vectors
- Yes
The result
Timing met. Area and power down.
| Measure | Scope | Change |
|---|---|---|
| Area | Whole MXCore | −9.7% |
| Power | MXFP8 engine | −6.0% |
| Perplexity | No measurable change | −0.005% |
| Timing | MXCore | Met |
MXCore, patched against baseline. One design so far.
Baseline
Patched
Baseline
Patched
One design. Yours next.
N = 1 MXCore is the only design so far. We say so first.
Notes
Notes from the bench. Titles are placeholders until the posts are written.
Team
Two founders. “We” on this page means Tom and Leo.
-
Tom de Vrieze
Founder
tom@prespin.com -
Leo Strijbos
Founder
leo@prespin.com
The error bound is yours to check.
Email the founders
Start with a throwaway block of RTL or a conversation about your flow. Confidentiality can be agreed upfront.