-
Notifications
You must be signed in to change notification settings - Fork 159
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
Add support for the Zvkb extension #236
Open
charmitro
wants to merge
15
commits into
riscv:vector-dev
Choose a base branch
from
charmitro:zvkb
base: vector-dev
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and old review comments may become outdated.
Open
Conversation
This file contains 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
…iscv#191) * V extension general framework and configuration setting instructions * Update model/riscv_insts_vext_utils.sail fix a typo Co-authored-by: Nicolas Brunie <nibrunie@gmail.com> Signed-off-by: BrighterW <xinlai.w@rioslab.org> * Update model/riscv_insts_vext_vset.sail * Revisions after Nov 22 meeting * Update effect matching for functions in riscv_vlen.sail * Fix code formatting issues * Update model/riscv_insts_vext_utils.sail Co-authored-by: Jessica Clarke <jrtc27@jrtc27.com> Signed-off-by: Xinlai Wan <xinlai.w@rioslab.org> * Fix coding style issues * Update vset instructions Signed-off-by: BrighterW <xinlai.w@rioslab.org> Signed-off-by: Xinlai Wan <xinlai.w@rioslab.org> Co-authored-by: Nicolas Brunie <nibrunie@gmail.com> Co-authored-by: Jessica Clarke <jrtc27@jrtc27.com>
* Add vector load / store instructions * Modify the implementation of SEW, LMUL, VLEN and avoid real numbers in the code * Update vstart setting in vector load / store instructions * Remove unnecessary assert statements in vector instructions * Fix bugs in vleff instructions and revise coding styles * Add guards for vector encdec clauses, Avoid redundant memory access after vector load/store failure
* Add vector arithmetic & mask instructions * Update vector EEW and EMUL checking function * Add vector instruction illegal check functions * Adjust code formatting for vector instruction illegal check functions Merge approved by team at tech-golden-model meeting on 2023-03-14.
Updated the PR:
|
* Add vector floating-point instructions * Update vector floating-point conversion instructions * Update copyright headers for vector extension code --------- Co-authored-by: xwan <xinlai.wan@rivai.ai>
Rebased from |
Updated the patchset:
|
Since this extension was later split into Zvbb + Zvbc and extended with new instructions, is the plan to review / merge it as it is and then update the SAIL with a new PR or to update that PR ? |
* Add vector mask and reduction instructions * Fix register overlap check in vector mask instructions --------- Co-authored-by: xwan <xinlai.wan@rivai.ai>
To support the implementation of Zvkb extensions in SAIL, this creates the necessary infrastructure(i.e., a file to hold it, and the extension macro), preparing the tree for the Zvkb implementation. Signed-off-by: Charalampos Mitrodimas <charalampos.mitrodimas@vrull.eu>
Vector rotate left by vector(.vv) or scalar(.vx). The elements in vs2 are rotated left by the rotate amount specified by either the cotrresponding elements of vs1 (vector-vector), or integer register rs1 (vector-scalar). Only the low log2(SEW) bits of the rotate-amount value are used, all other bits are ignored Signed-off-by: Charalampos Mitrodimas <charalampos.mitrodimas@vrull.eu>
Vector rotate right by vector/scalar/immediate. The elements in vs2 are rotated right by the rotate amount specified by either the corresponding elements of vs1 (vector-vector), integer register rs1 (vector-scalar), or an immediate value (vector-immediate). Only the low log2(SEW) bits of the rotate-amount value are used, all other bits are ignored. Signed-off-by: Charalampos Mitrodimas <charalampos.mitrodimas@vrull.eu>
Vector Reverse Bits in Bytes, a bit reversal is performed on the bits of each byte. Signed-off-by: Charalampos Mitrodimas <charalampos.mitrodimas@vrull.eu>
Vector Reverse Bytes A byte reversal is performed on each element of vs2, effectively performing an endian swap. Signed-off-by: Charalampos Mitrodimas <charalampos.mitrodimas@vrull.eu>
Bitwise And-Not. Each bit of Op1 is inverted and logically ANDed with the corresponding bits in vs2. In the vector- scalar version, "Op1" is the sign-extended or truncated value in scalar register rs1. In the vector-vector version, Op1 is vs1. Signed-off-by: Charalampos Mitrodimas <charalampos.mitrodimas@vrull.eu>
Produces the low half of 128-bit carry-less product. Each 64-bit element in the vs2 vector register is carry-less multiplied by either each 64-bit element in vs1 (vector-vector), or the 64-bit value from integer register rs1 (vector-scalar). The result is the least significant 64 bits of the carry-less product. Signed-off-by: Charalampos Mitrodimas <charalampos.mitrodimas@vrull.eu>
Vector Carry-less Multiply by vector or scalar - returning high half of product. Each 64-bit element in the vs2 vector register is carry-less multiplied by either each 64-bit element in vs1 (vector-vector), or the 64-bit value from integer register rs1 (vector-scalar). The result is the most significant 64 bits of the carry-less product. Signed-off-by: Charalampos Mitrodimas <charalampos.mitrodimas@vrull.eu>
billmcspadden-riscv
force-pushed
the
vector-dev
branch
from
October 17, 2023 19:12
e23be60
to
118ad66
Compare
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.
Implements the Zvkb (Vector Bit-manipulation used in Cryptography) extension, as of version Draft: 20230303
The following instructions are included:
All instructions were tested with VLEN & ELEN being manually adjusted; results were compared with QEMU results of each instruction.
Current revision is rebased with the latest changes of
vector-dev
branch.