A speculative mechanism to accelerate long-latency off-chip load requests by removing on-chip cache access latency from their critical path, as described by MICRO 2022 paper by Bera et al. (https://arxiv.org/pdf/2209.00188.pdf)
Hi all,
It's great to know this project and the github instructions are in great detailed.
We are working on research and trying to replicate their results; however, the experiments take forever for us to get the result.
I'm wondering could you kindly share the CSV files rollup.csv and rollup_mcpat.csvwith us so that we can start to analyze the results.
It's will be really helpful if you can sent those files to my email: [email protected] or whatever way you feel comfortable.
Thank you.
While browsing the project, I noticed a small typo in the README.md file. The first sentence on line 98 reads Build Hermes the using build script as follows. I bet it should better be something like Build Hermes using build script as follows.