-
Notifications
You must be signed in to change notification settings - Fork 22
Add RISC-V for XuanTie C908 #115
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Draft
thisisjube
wants to merge
209
commits into
slothy-optimizer:main
Choose a base branch
from
thisisjube:riscv
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Draft
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…for some instructions The <w>-specifier allows having 32-bit and 64-bit versions of instructions in one class which saves some work. While parsing, mnemonics are compared first to find the matching class for an instruction. Since add<w> would not be identified as an add-instruction, we first must replace <w> (if present) by the corresponding regex pattern and call re.match(srcline, pattern) afterward. A generic solution for parsing specifiers which modify the mnemonic could be a future task.
The method is set as an attribute during each call of parser() atm. This assignment should happen at a proper place.
…asses from a list
* prep for BranchLoop
* WARN: Not well tested (dry-run OK)
…functions - Add comprehensive save_regs/restore_regs macros to all 8 Kyber basemul RVV functions to enable maximum register availability for SLOTHY optimization - Update _example.py to use RISC_V.BranchLoop for all RVV optimization runners - Generate optimized versions of 5 new Kyber basemul RVV functions using C908 target - Standardize stack allocation (120 bytes) across all RVV functions - Enable advanced loop optimization capabilities for RISC-V vector code This change ensures RVV functions are ready for optimal SLOTHY processing with enhanced register renaming and software pipelining support.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Adds an implementation for the RISC-V architecture on the XuanTie C908, initially supporting the RV32/64I and RV32/64M ISA extensions, with plans to include RV32/64V in the future. This PR also introduces a new structure for organizing files, classes, and related components. Additionally, it includes a mechanism to reduce the effort required to add new instructions by dynamically generating instruction classes from a simple list. Overall, the changes also aim to streamline the process of adding new architectures, making it faster and more straightforward.