[PATCH] D137530: [RISCV] Splat scalar to be of length VL instead of 1 for reductions

[Wang Pengcheng via Phabricator via llvm-commits]

pcwang-thead added inline comments.


================
Comment at: llvm/test/CodeGen/RISCV/rvv/fixed-vectors-reduction-fp.ll:41
 ; CHECK-NEXT:    vle16.v v8, (a0)
-; CHECK-NEXT:    vfmv.s.f v9, fa0
+; CHECK-NEXT:    fmv.h.x ft0, zero
+; CHECK-NEXT:    fneg.h ft0, ft0
----------------
Floating-point regressions here.


================
Comment at: llvm/test/CodeGen/RISCV/rvv/fixed-vectors-reduction-fp.ll:1534
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    addi a1, a0, 256
----------------
Spilling because of increasing of register pressure.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D137530/new/

https://reviews.llvm.org/D137530