Skip to content
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

RVV 0.9 changes #2477

Merged
merged 4 commits into from May 19, 2020
Merged

RVV 0.9 changes #2477

merged 4 commits into from May 19, 2020

Conversation

aswaterman
Copy link
Member

@aswaterman aswaterman commented May 18, 2020

  • Fractional LMUL
  • Tail-agnostic/mask-agnostic bits
  • EEW loads/stores
  • Some encoding changes
  • Add utilities for bitwise shifts by signed shift amounts

@aswaterman aswaterman requested a review from a0u May 18, 2020 01:12
def VLE8_V = BitPat("b???000?00000?????000?????0000111")
def VLE16_V = BitPat("b???000?00000?????101?????0000111")
def VLE32_V = BitPat("b???000?00000?????110?????0000111")
def VLE64_V = BitPat("b???000?00000?????111?????0000111")
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why did you define VLE... opcodes for every width instead of single VLE opcode and then extracting the width from instruction bits directly?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Note all three funct3 bits get used (bit14 is 0 for VLE8, but it’s 1 for the others). This is because FLH/FLW/FLD/FLQ are in the same major opcode. If I replaced funct3 with ???, then VLE would conflict with the FP loads.

Of course this is just for illegal instruction detection. Once you get past that point, I agree you should just extract bits 13:12 to determine the width, rather than treating these as four separate instructions.

aswaterman added a commit that referenced this pull request Jun 8, 2020
This reverts commit bc949f4, reversing
changes made to 16d49a7.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants