[PATCH] D106286: [RISCV] Add a test showing an incorrect vsetvli insertion

[Fraser Cormack via Phabricator via llvm-commits]

frasercrmck created this revision.
frasercrmck added reviewers: craig.topper, HsiangKai, rogfer01, evandro, khchen, arcbbb.
Herald added subscribers: vkmr, luismarques, apazos, sameer.abuasal, s.egerton, Jim, benna, psnobl, jocewei, PkmX, the_o, brucehoult, MartinMosbeck, edward-jones, zzheng, jrtc27, shiva0217, kito-cheng, niosHD, sabuasal, simoncook, johnrusso, rbar, asb.
frasercrmck requested review of this revision.
Herald added subscribers: llvm-commits, MaskRay.
Herald added a project: LLVM.

This patch adds a reduced test case which identifies an illegal vsetvli
inserted by the compiler. The compiler emits a vsetvli which is intended
to preserve VL with the SEW/LMUL ratio e32/m1 when in fact the VL could
have been set by e64/m2 in a predecessor block.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D106286

Files:
  llvm/test/CodeGen/RISCV/rvv/vsetvli-regression.ll


Index: llvm/test/CodeGen/RISCV/rvv/vsetvli-regression.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/RISCV/rvv/vsetvli-regression.ll
@@ -0,0 +1,84 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=riscv64 -mattr=+experimental-v -riscv-v-vector-bits-min=128 | FileCheck %s
+
+; This test checks a regression in the vsetvli insertion pass.
+; Block .LBB0_4 has an illegal attempt to preserve VL in
+; "vsetvli zero,zero,e32,m1" when the last update of VL may be the vsetvli in block
+; .LBB0_2, "vsetvli zero,zero,e64,m2".
+
+define void @vector_loop(i32* %out, i64 %n, i64 %m) {
+; CHECK-LABEL: vector_loop:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    lui a3, %hi(.LCPI0_0)
+; CHECK-NEXT:    addi a3, a3, %lo(.LCPI0_0)
+; CHECK-NEXT:    vsetivli zero, 4, e64, m2, ta, mu
+; CHECK-NEXT:    vle64.v v26, (a3)
+; CHECK-NEXT:    mv a6, zero
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
+; CHECK-NEXT:    vmv.v.i v25, 0
+; CHECK-NEXT:    j .LBB0_2
+; CHECK-NEXT:  .LBB0_1: # %outer.latch
+; CHECK-NEXT:    # in Loop: Header=BB0_2 Depth=1
+; CHECK-NEXT:    addi a6, a6, 1
+; CHECK-NEXT:    bgeu a6, a1, .LBB0_5
+; CHECK-NEXT:  .LBB0_2: # %outer.loop
+; CHECK-NEXT:    # =>This Loop Header: Depth=1
+; CHECK-NEXT:    # Child Loop BB0_4 Depth 2
+; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
+; CHECK-NEXT:    vmsne.vx v28, v26, a6
+; CHECK-NEXT:    vpopc.m a4, v28
+; CHECK-NEXT:    beqz a4, .LBB0_1
+; CHECK-NEXT:  # %bb.3: # %inner.loop.preheader
+; CHECK-NEXT:    # in Loop: Header=BB0_2 Depth=1
+; CHECK-NEXT:    mv a4, zero
+; CHECK-NEXT:    vmv1r.v v28, v25
+; CHECK-NEXT:  .LBB0_4: # %inner.loop
+; CHECK-NEXT:    # Parent Loop BB0_2 Depth=1
+; CHECK-NEXT:    # => This Inner Loop Header: Depth=2
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
+; CHECK-NEXT:    vmv.x.s a5, v28
+; CHECK-NEXT:    slli a3, a5, 2
+; CHECK-NEXT:    add a3, a0, a3
+; CHECK-NEXT:    sw a5, 0(a3)
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
+; CHECK-NEXT:    addi a4, a4, 1
+; CHECK-NEXT:    vadd.vi v28, v28, 1
+; CHECK-NEXT:    bltu a4, a2, .LBB0_4
+; CHECK-NEXT:    j .LBB0_1
+; CHECK-NEXT:  .LBB0_5: # %exit
+; CHECK-NEXT:    ret
+entry:
+  %index = tail call <4 x i64> @llvm.experimental.stepvector.v4i64()
+  %neg.index = sub <4 x i64> zeroinitializer, %index
+  br label %outer.loop
+
+outer.loop:
+  %iv = phi i64 [ 0, %entry ], [ %inc, %outer.latch ]
+  %splatinsert = insertelement <4 x i64> poison, i64 %iv, i32 0
+  %splat = shufflevector <4 x i64> %splatinsert, <4 x i64> poison, <4 x i32> zeroinitializer
+  %c = icmp ne <4 x i64> %splat, %neg.index
+  %reduce = tail call i1 @llvm.vector.reduce.or.nxv4i1(<4 x i1> %c)
+  br i1 %reduce, label %inner.loop, label %outer.latch
+
+inner.loop:
+  %inner.iv = phi i64 [ 0, %outer.loop ], [ %inner.inc, %inner.loop ]
+  %vec.iv = phi <4 x i32> [ zeroinitializer, %outer.loop ], [ %vec.iv.inc, %inner.loop ]
+  %v30 = extractelement <4 x i32> %vec.iv, i64 0
+  %addr = getelementptr inbounds i32, i32* %out, i32 %v30
+  store i32 %v30, i32* %addr, align 4
+  %vec.iv.inc = add <4 x i32> %vec.iv, <i32 1, i32 1, i32 1, i32 1>
+  %inner.inc = add i64 %inner.iv, 1
+  %cmp = icmp ult i64 %inner.inc, %m
+  br i1 %cmp, label %inner.loop, label %outer.latch
+
+outer.latch:
+  %inc = add i64 %iv, 1
+  %atlimit = icmp ult i64 %inc, %n
+  br i1 %atlimit, label %outer.loop, label %exit
+
+exit:
+  ret void
+}
+
+declare i1 @llvm.vector.reduce.or.nxv4i1(<4 x i1>)
+declare <4 x i64> @llvm.experimental.stepvector.v4i64()


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D106286.359814.patch
Type: text/x-patch
Size: 3606 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210719/07fe0748/attachment.bin>