User Details
- User Since
- Jan 26 2021, 7:22 PM (111 w, 5 d)
Mar 30 2022
rebase and update
Mar 10 2022
Comments addressed before commit. Thanks.
Mar 2 2022
Gently ping.
Feb 24 2022
Address comments
Feb 22 2022
Hi, any comments? :)
Feb 15 2022
Nov 8 2021
Nov 5 2021
Gently ping.
Oct 29 2021
Oct 28 2021
So sorry for my bad herald script.
So sorry for my bad herald script.
So sorry for my bad herald script.
So sorry for my bad herald script.
So sorry for my bad herald script.
So sorry for my bad herald script.
So sorry for my bad herald script.
So sorry for my bad herald script.
Oct 27 2021
Oct 26 2021
Update
Oct 4 2021
@craig.topper It seems for intrinsic llvm.masked.gather.xxx, the backend will produce similar assembly instructions.
Eg, llvm.masked.gather.v8f64.v8p0f64 will get
vsetivli zero, 8, e64, m4, tu, mu vluxei64.v v12, (zero), v8, v0.t vmv4r.v v8, v12
, and llvm.masked.gather.v4f64.v4p0f64 will get
vsetivli zero, 4, e64, m2, tu, mu vluxei64.v v10, (zero), v8, v0.t vmv2r.v v8, v10
So why the cost is calculated by element number? I'm not quite clear about this. Can you give some reference or clue? Thanks.
Sep 28 2021
May I ask a question, why is RISCV::RVVBitsPerBlock set to 64? Any clue(RFC) to this concept? Thanks.
Sep 27 2021
Update
Clang tidy
Sep 6 2021
ping
Aug 31 2021
Should we implement method unsigned getMinVectorRegisterBitWidth() to avoid potential errors?
Aug 28 2021
Update
Aug 18 2021
ping
Aug 11 2021
Update
Jul 30 2021
Jul 29 2021
Jul 27 2021
ping
Jul 24 2021
Update
Jun 29 2021
Jun 17 2021
Jun 16 2021
Jun 7 2021
Jun 6 2021
LGTM
May 28 2021
ping
May 20 2021
Rebase and update.
May 19 2021
rebase
May 18 2021
ping
Apr 29 2021
Apr 28 2021
ping
Apr 22 2021
Apr 15 2021
ping