[llvm] [RISCV] Vectorize phi for loop carried @llvm.vp.reduce.* (PR #131974)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Mar 18 22:38:01 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-risc-v
Author: MingYan (NexMing)
<details>
<summary>Changes</summary>
This patch is vector predication version of commit 15b0fabb21af8395c1b810e7d992a869b9ef31d8
---
Patch is 52.25 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/131974.diff
3 Files Affected:
- (modified) llvm/lib/Target/RISCV/RISCVCodeGenPrepare.cpp (+2-1)
- (modified) llvm/test/CodeGen/RISCV/rvv/riscv-codegenprepare-asm.ll (+456)
- (modified) llvm/test/CodeGen/RISCV/rvv/riscv-codegenprepare.ll (+484)
``````````diff
diff --git a/llvm/lib/Target/RISCV/RISCVCodeGenPrepare.cpp b/llvm/lib/Target/RISCV/RISCVCodeGenPrepare.cpp
index 5be5345cca73a..39877fb511ec3 100644
--- a/llvm/lib/Target/RISCV/RISCVCodeGenPrepare.cpp
+++ b/llvm/lib/Target/RISCV/RISCVCodeGenPrepare.cpp
@@ -137,7 +137,8 @@ bool RISCVCodeGenPrepare::visitIntrinsicInst(IntrinsicInst &I) {
if (expandVPStrideLoad(I))
return true;
- if (I.getIntrinsicID() != Intrinsic::vector_reduce_fadd)
+ if (I.getIntrinsicID() != Intrinsic::vector_reduce_fadd &&
+ !isa<VPReductionIntrinsic>(&I))
return false;
auto *PHI = dyn_cast<PHINode>(I.getOperand(0));
diff --git a/llvm/test/CodeGen/RISCV/rvv/riscv-codegenprepare-asm.ll b/llvm/test/CodeGen/RISCV/rvv/riscv-codegenprepare-asm.ll
index 3bbdd1a257fdb..4e5f6e0f65489 100644
--- a/llvm/test/CodeGen/RISCV/rvv/riscv-codegenprepare-asm.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/riscv-codegenprepare-asm.ll
@@ -42,3 +42,459 @@ vector.body:
exit:
ret float %acc
}
+
+define i32 @vp_reduce_add(ptr %a) {
+; CHECK-LABEL: vp_reduce_add:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: li a1, 0
+; CHECK-NEXT: vsetvli a2, zero, e32, m1, ta, ma
+; CHECK-NEXT: vmv.s.x v8, zero
+; CHECK-NEXT: li a2, 1024
+; CHECK-NEXT: .LBB1_1: # %vector.body
+; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT: vsetvli a3, a2, e32, m2, ta, ma
+; CHECK-NEXT: slli a4, a1, 2
+; CHECK-NEXT: add a4, a0, a4
+; CHECK-NEXT: vle32.v v10, (a4)
+; CHECK-NEXT: sub a2, a2, a3
+; CHECK-NEXT: vredsum.vs v8, v10, v8
+; CHECK-NEXT: add a1, a1, a3
+; CHECK-NEXT: bnez a2, .LBB1_1
+; CHECK-NEXT: # %bb.2: # %for.cond.cleanup
+; CHECK-NEXT: vmv.x.s a0, v8
+; CHECK-NEXT: ret
+entry:
+ br label %vector.body
+
+vector.body: ; preds = %vector.body, %entry
+ %trip.count = phi i64 [ 1024, %entry ], [ %remaining.trip.count, %vector.body ]
+ %scalar.ind = phi i64 [ 0, %entry ], [ %next.ind, %vector.body ]
+ %red.phi = phi i32 [ 0, %entry ], [ %red, %vector.body ]
+ %evl = tail call i32 @llvm.experimental.get.vector.length.i64(i64 %trip.count, i32 4, i1 true)
+ %evl2 = zext i32 %evl to i64
+ %arrayidx6 = getelementptr inbounds i32, ptr %a, i64 %scalar.ind
+ %wide.load = tail call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr %arrayidx6, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %red = tail call i32 @llvm.vp.reduce.add.nxv4i32(i32 %red.phi, <vscale x 4 x i32> %wide.load, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %remaining.trip.count = sub nuw i64 %trip.count, %evl2
+ %next.ind = add i64 %scalar.ind, %evl2
+ %m = icmp eq i64 %remaining.trip.count, 0
+ br i1 %m, label %for.cond.cleanup, label %vector.body
+
+for.cond.cleanup: ; preds = %vector.body
+ ret i32 %red
+}
+
+define i32 @vp_reduce_and(ptr %a) {
+; CHECK-LABEL: vp_reduce_and:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: li a1, 0
+; CHECK-NEXT: lui a2, 524288
+; CHECK-NEXT: vsetvli a3, zero, e32, m1, ta, ma
+; CHECK-NEXT: vmv.s.x v8, a2
+; CHECK-NEXT: li a2, 1024
+; CHECK-NEXT: .LBB2_1: # %vector.body
+; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT: vsetvli a3, a2, e32, m2, ta, ma
+; CHECK-NEXT: slli a4, a1, 2
+; CHECK-NEXT: add a4, a0, a4
+; CHECK-NEXT: vle32.v v10, (a4)
+; CHECK-NEXT: sub a2, a2, a3
+; CHECK-NEXT: vredand.vs v8, v10, v8
+; CHECK-NEXT: add a1, a1, a3
+; CHECK-NEXT: bnez a2, .LBB2_1
+; CHECK-NEXT: # %bb.2: # %for.cond.cleanup
+; CHECK-NEXT: vmv.x.s a0, v8
+; CHECK-NEXT: ret
+entry:
+ br label %vector.body
+
+vector.body: ; preds = %vector.body, %entry
+ %trip.count = phi i64 [ 1024, %entry ], [ %remaining.trip.count, %vector.body ]
+ %scalar.ind = phi i64 [ 0, %entry ], [ %next.ind, %vector.body ]
+ %red.phi = phi i32 [ -2147483648, %entry ], [ %red, %vector.body ]
+ %evl = tail call i32 @llvm.experimental.get.vector.length.i64(i64 %trip.count, i32 4, i1 true)
+ %evl2 = zext i32 %evl to i64
+ %arrayidx6 = getelementptr inbounds i32, ptr %a, i64 %scalar.ind
+ %wide.load = tail call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr %arrayidx6, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %red = tail call i32 @llvm.vp.reduce.and.nxv4i32(i32 %red.phi, <vscale x 4 x i32> %wide.load, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %remaining.trip.count = sub nuw i64 %trip.count, %evl2
+ %next.ind = add i64 %scalar.ind, %evl2
+ %m = icmp eq i64 %remaining.trip.count, 0
+ br i1 %m, label %for.cond.cleanup, label %vector.body
+
+for.cond.cleanup: ; preds = %vector.body
+ ret i32 %red
+}
+
+define i32 @vp_reduce_or(ptr %a) {
+; CHECK-LABEL: vp_reduce_or:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: li a1, 0
+; CHECK-NEXT: vsetvli a2, zero, e32, m1, ta, ma
+; CHECK-NEXT: vmv.s.x v8, zero
+; CHECK-NEXT: li a2, 1024
+; CHECK-NEXT: .LBB3_1: # %vector.body
+; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT: vsetvli a3, a2, e32, m2, ta, ma
+; CHECK-NEXT: slli a4, a1, 2
+; CHECK-NEXT: add a4, a0, a4
+; CHECK-NEXT: vle32.v v10, (a4)
+; CHECK-NEXT: sub a2, a2, a3
+; CHECK-NEXT: vredor.vs v8, v10, v8
+; CHECK-NEXT: add a1, a1, a3
+; CHECK-NEXT: bnez a2, .LBB3_1
+; CHECK-NEXT: # %bb.2: # %for.cond.cleanup
+; CHECK-NEXT: vmv.x.s a0, v8
+; CHECK-NEXT: ret
+entry:
+ br label %vector.body
+
+vector.body: ; preds = %vector.body, %entry
+ %trip.count = phi i64 [ 1024, %entry ], [ %remaining.trip.count, %vector.body ]
+ %scalar.ind = phi i64 [ 0, %entry ], [ %next.ind, %vector.body ]
+ %red.phi = phi i32 [ 0, %entry ], [ %red, %vector.body ]
+ %evl = tail call i32 @llvm.experimental.get.vector.length.i64(i64 %trip.count, i32 4, i1 true)
+ %evl2 = zext i32 %evl to i64
+ %arrayidx6 = getelementptr inbounds i32, ptr %a, i64 %scalar.ind
+ %wide.load = tail call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr %arrayidx6, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %red = tail call i32 @llvm.vp.reduce.or.nxv4i32(i32 %red.phi, <vscale x 4 x i32> %wide.load, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %remaining.trip.count = sub nuw i64 %trip.count, %evl2
+ %next.ind = add i64 %scalar.ind, %evl2
+ %m = icmp eq i64 %remaining.trip.count, 0
+ br i1 %m, label %for.cond.cleanup, label %vector.body
+
+for.cond.cleanup: ; preds = %vector.body
+ ret i32 %red
+}
+
+define i32 @vp_reduce_xor(ptr %a) {
+; CHECK-LABEL: vp_reduce_xor:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: li a1, 0
+; CHECK-NEXT: vsetvli a2, zero, e32, m1, ta, ma
+; CHECK-NEXT: vmv.s.x v8, zero
+; CHECK-NEXT: li a2, 1024
+; CHECK-NEXT: .LBB4_1: # %vector.body
+; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT: vsetvli a3, a2, e32, m2, ta, ma
+; CHECK-NEXT: slli a4, a1, 2
+; CHECK-NEXT: add a4, a0, a4
+; CHECK-NEXT: vle32.v v10, (a4)
+; CHECK-NEXT: sub a2, a2, a3
+; CHECK-NEXT: vredxor.vs v8, v10, v8
+; CHECK-NEXT: add a1, a1, a3
+; CHECK-NEXT: bnez a2, .LBB4_1
+; CHECK-NEXT: # %bb.2: # %for.cond.cleanup
+; CHECK-NEXT: vmv.x.s a0, v8
+; CHECK-NEXT: ret
+entry:
+ br label %vector.body
+
+vector.body: ; preds = %vector.body, %entry
+ %trip.count = phi i64 [ 1024, %entry ], [ %remaining.trip.count, %vector.body ]
+ %scalar.ind = phi i64 [ 0, %entry ], [ %next.ind, %vector.body ]
+ %red.phi = phi i32 [ 0, %entry ], [ %red, %vector.body ]
+ %evl = tail call i32 @llvm.experimental.get.vector.length.i64(i64 %trip.count, i32 4, i1 true)
+ %evl2 = zext i32 %evl to i64
+ %arrayidx6 = getelementptr inbounds i32, ptr %a, i64 %scalar.ind
+ %wide.load = tail call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr %arrayidx6, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %red = tail call i32 @llvm.vp.reduce.xor.nxv4i32(i32 %red.phi, <vscale x 4 x i32> %wide.load, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %remaining.trip.count = sub nuw i64 %trip.count, %evl2
+ %next.ind = add i64 %scalar.ind, %evl2
+ %m = icmp eq i64 %remaining.trip.count, 0
+ br i1 %m, label %for.cond.cleanup, label %vector.body
+
+for.cond.cleanup: ; preds = %vector.body
+ ret i32 %red
+}
+
+define i32 @vp_reduce_smax(ptr %a) {
+; CHECK-LABEL: vp_reduce_smax:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: li a1, 0
+; CHECK-NEXT: lui a2, 524288
+; CHECK-NEXT: vsetvli a3, zero, e32, m1, ta, ma
+; CHECK-NEXT: vmv.s.x v8, a2
+; CHECK-NEXT: li a2, 1024
+; CHECK-NEXT: .LBB5_1: # %vector.body
+; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT: vsetvli a3, a2, e32, m2, ta, ma
+; CHECK-NEXT: slli a4, a1, 2
+; CHECK-NEXT: add a4, a0, a4
+; CHECK-NEXT: vle32.v v10, (a4)
+; CHECK-NEXT: sub a2, a2, a3
+; CHECK-NEXT: vredmax.vs v8, v10, v8
+; CHECK-NEXT: add a1, a1, a3
+; CHECK-NEXT: bnez a2, .LBB5_1
+; CHECK-NEXT: # %bb.2: # %for.cond.cleanup
+; CHECK-NEXT: vmv.x.s a0, v8
+; CHECK-NEXT: ret
+entry:
+ br label %vector.body
+
+vector.body: ; preds = %vector.body, %entry
+ %trip.count = phi i64 [ 1024, %entry ], [ %remaining.trip.count, %vector.body ]
+ %scalar.ind = phi i64 [ 0, %entry ], [ %next.ind, %vector.body ]
+ %red.phi = phi i32 [ -2147483648, %entry ], [ %red, %vector.body ]
+ %evl = tail call i32 @llvm.experimental.get.vector.length.i64(i64 %trip.count, i32 4, i1 true)
+ %evl2 = zext i32 %evl to i64
+ %arrayidx6 = getelementptr inbounds i32, ptr %a, i64 %scalar.ind
+ %wide.load = tail call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr %arrayidx6, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %red = tail call i32 @llvm.vp.reduce.smax.nxv4i32(i32 %red.phi, <vscale x 4 x i32> %wide.load, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %remaining.trip.count = sub nuw i64 %trip.count, %evl2
+ %next.ind = add i64 %scalar.ind, %evl2
+ %m = icmp eq i64 %remaining.trip.count, 0
+ br i1 %m, label %for.cond.cleanup, label %vector.body
+
+for.cond.cleanup: ; preds = %vector.body
+ ret i32 %red
+}
+
+define i32 @vp_reduce_smin(ptr %a) {
+; CHECK-LABEL: vp_reduce_smin:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: li a1, 0
+; CHECK-NEXT: lui a2, 524288
+; CHECK-NEXT: addi a2, a2, -1
+; CHECK-NEXT: vsetvli a3, zero, e32, m1, ta, ma
+; CHECK-NEXT: vmv.s.x v8, a2
+; CHECK-NEXT: li a2, 1024
+; CHECK-NEXT: .LBB6_1: # %vector.body
+; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT: vsetvli a3, a2, e32, m2, ta, ma
+; CHECK-NEXT: slli a4, a1, 2
+; CHECK-NEXT: add a4, a0, a4
+; CHECK-NEXT: vle32.v v10, (a4)
+; CHECK-NEXT: sub a2, a2, a3
+; CHECK-NEXT: vredmin.vs v8, v10, v8
+; CHECK-NEXT: add a1, a1, a3
+; CHECK-NEXT: bnez a2, .LBB6_1
+; CHECK-NEXT: # %bb.2: # %for.cond.cleanup
+; CHECK-NEXT: vmv.x.s a0, v8
+; CHECK-NEXT: ret
+entry:
+ br label %vector.body
+
+vector.body: ; preds = %vector.body, %entry
+ %trip.count = phi i64 [ 1024, %entry ], [ %remaining.trip.count, %vector.body ]
+ %scalar.ind = phi i64 [ 0, %entry ], [ %next.ind, %vector.body ]
+ %red.phi = phi i32 [ 2147483647, %entry ], [ %red, %vector.body ]
+ %evl = tail call i32 @llvm.experimental.get.vector.length.i64(i64 %trip.count, i32 4, i1 true)
+ %evl2 = zext i32 %evl to i64
+ %arrayidx6 = getelementptr inbounds i32, ptr %a, i64 %scalar.ind
+ %wide.load = tail call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr %arrayidx6, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %red = tail call i32 @llvm.vp.reduce.smin.nxv4i32(i32 %red.phi, <vscale x 4 x i32> %wide.load, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %remaining.trip.count = sub nuw i64 %trip.count, %evl2
+ %next.ind = add i64 %scalar.ind, %evl2
+ %m = icmp eq i64 %remaining.trip.count, 0
+ br i1 %m, label %for.cond.cleanup, label %vector.body
+
+for.cond.cleanup: ; preds = %vector.body
+ ret i32 %red
+}
+
+define i32 @vp_reduce_umax(ptr %a) {
+; CHECK-LABEL: vp_reduce_umax:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: li a1, 0
+; CHECK-NEXT: vsetvli a2, zero, e32, m1, ta, ma
+; CHECK-NEXT: vmv.s.x v8, zero
+; CHECK-NEXT: li a2, 1024
+; CHECK-NEXT: .LBB7_1: # %vector.body
+; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT: vsetvli a3, a2, e32, m2, ta, ma
+; CHECK-NEXT: slli a4, a1, 2
+; CHECK-NEXT: add a4, a0, a4
+; CHECK-NEXT: vle32.v v10, (a4)
+; CHECK-NEXT: sub a2, a2, a3
+; CHECK-NEXT: vredmaxu.vs v8, v10, v8
+; CHECK-NEXT: add a1, a1, a3
+; CHECK-NEXT: bnez a2, .LBB7_1
+; CHECK-NEXT: # %bb.2: # %for.cond.cleanup
+; CHECK-NEXT: vmv.x.s a0, v8
+; CHECK-NEXT: ret
+entry:
+ br label %vector.body
+
+vector.body: ; preds = %vector.body, %entry
+ %trip.count = phi i64 [ 1024, %entry ], [ %remaining.trip.count, %vector.body ]
+ %scalar.ind = phi i64 [ 0, %entry ], [ %next.ind, %vector.body ]
+ %red.phi = phi i32 [ 0, %entry ], [ %red, %vector.body ]
+ %evl = tail call i32 @llvm.experimental.get.vector.length.i64(i64 %trip.count, i32 4, i1 true)
+ %evl2 = zext i32 %evl to i64
+ %arrayidx6 = getelementptr inbounds i32, ptr %a, i64 %scalar.ind
+ %wide.load = tail call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr %arrayidx6, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %red = tail call i32 @llvm.vp.reduce.umax.nxv4i32(i32 %red.phi, <vscale x 4 x i32> %wide.load, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %remaining.trip.count = sub nuw i64 %trip.count, %evl2
+ %next.ind = add i64 %scalar.ind, %evl2
+ %m = icmp eq i64 %remaining.trip.count, 0
+ br i1 %m, label %for.cond.cleanup, label %vector.body
+
+for.cond.cleanup: ; preds = %vector.body
+ ret i32 %red
+}
+
+define i32 @vp_reduce_umin(ptr %a) {
+; CHECK-LABEL: vp_reduce_umin:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: li a1, 0
+; CHECK-NEXT: lui a2, 524288
+; CHECK-NEXT: vsetvli a3, zero, e32, m1, ta, ma
+; CHECK-NEXT: vmv.s.x v8, a2
+; CHECK-NEXT: li a2, 1024
+; CHECK-NEXT: .LBB8_1: # %vector.body
+; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT: vsetvli a3, a2, e32, m2, ta, ma
+; CHECK-NEXT: slli a4, a1, 2
+; CHECK-NEXT: add a4, a0, a4
+; CHECK-NEXT: vle32.v v10, (a4)
+; CHECK-NEXT: sub a2, a2, a3
+; CHECK-NEXT: vredminu.vs v8, v10, v8
+; CHECK-NEXT: add a1, a1, a3
+; CHECK-NEXT: bnez a2, .LBB8_1
+; CHECK-NEXT: # %bb.2: # %for.cond.cleanup
+; CHECK-NEXT: vmv.x.s a0, v8
+; CHECK-NEXT: ret
+entry:
+ br label %vector.body
+
+vector.body: ; preds = %vector.body, %entry
+ %trip.count = phi i64 [ 1024, %entry ], [ %remaining.trip.count, %vector.body ]
+ %scalar.ind = phi i64 [ 0, %entry ], [ %next.ind, %vector.body ]
+ %red.phi = phi i32 [ -2147483648, %entry ], [ %red, %vector.body ]
+ %evl = tail call i32 @llvm.experimental.get.vector.length.i64(i64 %trip.count, i32 4, i1 true)
+ %evl2 = zext i32 %evl to i64
+ %arrayidx6 = getelementptr inbounds i32, ptr %a, i64 %scalar.ind
+ %wide.load = tail call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr %arrayidx6, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %red = tail call i32 @llvm.vp.reduce.umin.nxv4i32(i32 %red.phi, <vscale x 4 x i32> %wide.load, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %remaining.trip.count = sub nuw i64 %trip.count, %evl2
+ %next.ind = add i64 %scalar.ind, %evl2
+ %m = icmp eq i64 %remaining.trip.count, 0
+ br i1 %m, label %for.cond.cleanup, label %vector.body
+
+for.cond.cleanup: ; preds = %vector.body
+ ret i32 %red
+}
+
+define float @vp_reduce_fadd(ptr %a) {
+; CHECK-LABEL: vp_reduce_fadd:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: li a1, 0
+; CHECK-NEXT: vsetvli a2, zero, e32, m1, ta, ma
+; CHECK-NEXT: vmv.s.x v8, zero
+; CHECK-NEXT: li a2, 1024
+; CHECK-NEXT: .LBB9_1: # %vector.body
+; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT: vsetvli a3, a2, e32, m2, ta, ma
+; CHECK-NEXT: slli a4, a1, 2
+; CHECK-NEXT: add a4, a0, a4
+; CHECK-NEXT: vle32.v v10, (a4)
+; CHECK-NEXT: sub a2, a2, a3
+; CHECK-NEXT: vfredosum.vs v8, v10, v8
+; CHECK-NEXT: add a1, a1, a3
+; CHECK-NEXT: bnez a2, .LBB9_1
+; CHECK-NEXT: # %bb.2: # %for.cond.cleanup
+; CHECK-NEXT: vfmv.f.s fa0, v8
+; CHECK-NEXT: ret
+entry:
+ br label %vector.body
+
+vector.body: ; preds = %vector.body, %entry
+ %trip.count = phi i64 [ 1024, %entry ], [ %remaining.trip.count, %vector.body ]
+ %scalar.ind = phi i64 [ 0, %entry ], [ %next.ind, %vector.body ]
+ %red.phi = phi float [ 0.000000e+00, %entry ], [ %red, %vector.body ]
+ %evl = tail call i32 @llvm.experimental.get.vector.length.i64(i64 %trip.count, i32 4, i1 true)
+ %evl2 = zext i32 %evl to i64
+ %arrayidx6 = getelementptr inbounds float, ptr %a, i64 %scalar.ind
+ %wide.load = tail call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr %arrayidx6, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %red = tail call float @llvm.vp.reduce.fadd.nxv4f32(float %red.phi, <vscale x 4 x float> %wide.load, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %remaining.trip.count = sub nuw i64 %trip.count, %evl2
+ %next.ind = add i64 %scalar.ind, %evl2
+ %m = icmp eq i64 %remaining.trip.count, 0
+ br i1 %m, label %for.cond.cleanup, label %vector.body
+
+for.cond.cleanup: ; preds = %vector.body
+ ret float %red
+}
+
+define float @vp_reduce_fmax(ptr %a) {
+; CHECK-LABEL: vp_reduce_fmax:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: li a1, 0
+; CHECK-NEXT: vsetvli a2, zero, e32, m1, ta, ma
+; CHECK-NEXT: vmv.s.x v8, zero
+; CHECK-NEXT: li a2, 1024
+; CHECK-NEXT: .LBB10_1: # %vector.body
+; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT: vsetvli a3, a2, e32, m2, ta, ma
+; CHECK-NEXT: slli a4, a1, 2
+; CHECK-NEXT: add a4, a0, a4
+; CHECK-NEXT: vle32.v v10, (a4)
+; CHECK-NEXT: sub a2, a2, a3
+; CHECK-NEXT: vfredmax.vs v8, v10, v8
+; CHECK-NEXT: add a1, a1, a3
+; CHECK-NEXT: bnez a2, .LBB10_1
+; CHECK-NEXT: # %bb.2: # %for.cond.cleanup
+; CHECK-NEXT: vfmv.f.s fa0, v8
+; CHECK-NEXT: ret
+entry:
+ br label %vector.body
+
+vector.body: ; preds = %vector.body, %entry
+ %trip.count = phi i64 [ 1024, %entry ], [ %remaining.trip.count, %vector.body ]
+ %scalar.ind = phi i64 [ 0, %entry ], [ %next.ind, %vector.body ]
+ %red.phi = phi float [ 0.000000e+00, %entry ], [ %red, %vector.body ]
+ %evl = tail call i32 @llvm.experimental.get.vector.length.i64(i64 %trip.count, i32 4, i1 true)
+ %evl2 = zext i32 %evl to i64
+ %arrayidx6 = getelementptr inbounds float, ptr %a, i64 %scalar.ind
+ %wide.load = tail call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr %arrayidx6, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %red = tail call float @llvm.vp.reduce.fmax.nxv4f32(float %red.phi, <vscale x 4 x float> %wide.load, <vscale x 4 x i1> splat (i1 true), i32 %evl)
+ %remaining.trip.count = sub nuw i64 %trip.count, %evl2
+ %next.ind = add i64 %scalar.ind, %evl2
+ %m = icmp eq i64 %remaining.trip.count, 0
+ br i1 %m, label %for.cond.cleanup, label %vector.body
+
+for.cond.cleanup: ; preds = %vector.body
+ ret float %red
+}
+
+define float @vp_reduce_fmin(ptr %a) {
+; CHECK-LABEL: vp_reduce_fmin:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: li a1, 0
+; CHECK-NEXT: vsetvli a2, zero, e32, m1, ta, ma
+; CHECK-NEXT: vmv.s.x v8, zero
+; CHECK-NEXT: li a2, 1024
+; CHECK-NEXT: .LBB11_1: # %vector.body
+; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT: vsetvli a3, a2, e32, m2, ta, ma
+; CHECK-NEXT: slli a4, a1, 2
+; CHECK-NEXT: add a4, a0, a4
+; CHECK-NEXT: vle32.v v10, (a4)
+; CHECK-NEXT: sub a2, a2, a3
+; CHECK-NEXT: vfredmin.vs v8, v10, v8
+; CHECK-NEXT: add a1, a1, a3
+; CHECK-NEXT: bnez a2, .LBB11_1
+; CHECK-NEXT: # %bb.2: # %for.cond.cleanup
+; CHECK-NEXT: vfmv.f.s fa0, v8
+; CHECK-NEXT: ret
+entry:
+ br label %vector.body
+
+vector.body: ; preds = %vector.body, %entry
+ %trip.count = phi i64 [ 1024, %entry ], [ %r...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/131974
More information about the llvm-commits
mailing list