[PATCH] D93809: [RISCV] Add intrinsics for vcompress instruction
ShihPo Hung via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Mon Dec 28 01:38:23 PST 2020
arcbbb added inline comments.
================
Comment at: llvm/test/CodeGen/RISCV/rvv/vcompress-rv32.ll:13
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli a0, a0, e8,mf8,ta,mu
+; CHECK-NEXT: vcompress.vm v16, v17, v0
----------------
craig.topper wrote:
> Based on the way this intrinsic is defined, this can't be tail agnostic can it?
Yes, for all intrinsics which maskedoff operand is not Undef, it makes sense to be tail undisturbed.
Since the default vtype is changed to "ta,mu" in D93080,
maybe we can check whether MI.getOperand(MergeOpIndex) is undef or not, and set vtype to corresponding value?
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D93809/new/
https://reviews.llvm.org/D93809
More information about the llvm-commits
mailing list