Skip to content

[RISCV] Support fixed vector vp.reverse/splice with Zvfhmin/Zvfbfmin. #145596

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jun 25, 2025
Merged

[RISCV] Support fixed vector vp.reverse/splice with Zvfhmin/Zvfbfmin. #145596

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
64ba497
[RISCV] Support fixed vector vp.reverse/splice with Zvfhmin/Zvfbfmin.
topperc Jun 24, 2025
872e8b9
Merge remote-tracking branch 'origin/main' into pr/fixed-splice-revert
topperc Jun 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions llvm/lib/Target/RISCV/RISCVISelLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -756,8 +756,7 @@ RISCVTargetLowering::RISCVTargetLowering(const TargetMachine &TM,
ISD::VP_FROUNDEVEN, ISD::VP_FCOPYSIGN, ISD::VP_FROUNDTOZERO,
ISD::VP_FRINT, ISD::VP_FNEARBYINT, ISD::VP_IS_FPCLASS,
ISD::VP_FMINIMUM, ISD::VP_FMAXIMUM, ISD::VP_LRINT,
ISD::VP_LLRINT, ISD::EXPERIMENTAL_VP_REVERSE,
ISD::EXPERIMENTAL_VP_SPLICE, ISD::VP_REDUCE_FMINIMUM,
ISD::VP_LLRINT, ISD::VP_REDUCE_FMINIMUM,
ISD::VP_REDUCE_FMAXIMUM, ISD::EXPERIMENTAL_VP_SPLAT};

static const unsigned IntegerVecReduceOps[] = {
Expand Down Expand Up @@ -1112,6 +1111,8 @@ RISCVTargetLowering::RISCVTargetLowering(const TargetMachine &TM,
setOperationAction(ISD::VECTOR_INTERLEAVE, VT, Custom);

setOperationAction({ISD::VECTOR_REVERSE, ISD::VECTOR_SPLICE}, VT, Custom);
setOperationAction(ISD::EXPERIMENTAL_VP_SPLICE, VT, Custom);
setOperationAction(ISD::EXPERIMENTAL_VP_REVERSE, VT, Custom);

setOperationAction(FloatingPointVPOps, VT, Custom);

Expand Down Expand Up @@ -1420,6 +1421,8 @@ RISCVTargetLowering::RISCVTargetLowering(const TargetMachine &TM,
ISD::EXTRACT_SUBVECTOR, ISD::VECTOR_REVERSE,
ISD::VECTOR_SHUFFLE, ISD::VECTOR_COMPRESS},
VT, Custom);
setOperationAction(ISD::EXPERIMENTAL_VP_SPLICE, VT, Custom);
setOperationAction(ISD::EXPERIMENTAL_VP_REVERSE, VT, Custom);

setOperationAction({ISD::VECTOR_INTERLEAVE, ISD::VECTOR_DEINTERLEAVE},
VT, Custom);
Expand Down
33 changes: 32 additions & 1 deletion ...CV/rvv/fixed-vectors-vp-reverser-float.ll → ...SCV/rvv/fixed-vectors-vp-reverse-float.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv64 -mattr=+m,+f,+d,+v,+zvfh -verify-machineinstrs -riscv-v-vector-bits-min=128 \
; RUN: llc -mtriple=riscv64 -mattr=+m,+f,+d,+v,+zvfh,+zvfbfmin -verify-machineinstrs -riscv-v-vector-bits-min=128 \
; RUN: < %s | FileCheck %s
; RUN: llc -mtriple=riscv64 -mattr=+m,+f,+d,+v,+zvfhmin,+zvfbfmin -verify-machineinstrs -riscv-v-vector-bits-min=128 \
; RUN: < %s | FileCheck %s

define <2 x double> @test_vp_reverse_v2f64_masked(<2 x double> %src, <2 x i1> %mask, i32 zeroext %evl) {
Expand Down Expand Up @@ -88,3 +90,32 @@ define <4 x half> @test_vp_reverse_v4f16(<4 x half> %src, i32 zeroext %evl) {
%dst = call <4 x half> @llvm.experimental.vp.reverse.v4f16(<4 x half> %src, <4 x i1> splat (i1 1), i32 %evl)
ret <4 x half> %dst
}

define <4 x bfloat> @test_vp_reverse_v4bf16_masked(<4 x bfloat> %src, <4 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v4bf16_masked:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
; CHECK-NEXT: vid.v v9, v0.t
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vrsub.vx v10, v9, a0, v0.t
; CHECK-NEXT: vrgather.vv v9, v8, v10, v0.t
; CHECK-NEXT: vmv1r.v v8, v9
; CHECK-NEXT: ret
%dst = call <4 x bfloat> @llvm.experimental.vp.reverse.v4bf16(<4 x bfloat> %src, <4 x i1> %mask, i32 %evl)
ret <4 x bfloat> %dst
}

define <4 x bfloat> @test_vp_reverse_v4bf16(<4 x bfloat> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v4bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: addi a1, a0, -1
; CHECK-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
; CHECK-NEXT: vid.v v9
; CHECK-NEXT: vrsub.vx v10, v9, a1
; CHECK-NEXT: vrgather.vv v9, v8, v10
; CHECK-NEXT: vmv1r.v v8, v9
; CHECK-NEXT: ret

%dst = call <4 x bfloat> @llvm.experimental.vp.reverse.v4bf16(<4 x bfloat> %src, <4 x i1> splat (i1 1), i32 %evl)
ret <4 x bfloat> %dst
}
0 ...ISCV/rvv/fixed-vectors-vp-reverser-int.ll → ...RISCV/rvv/fixed-vectors-vp-reverse-int.ll
View file
Open in desktop
File renamed without changes.
69 changes: 61 additions & 8 deletions llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vp-splice.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple riscv64 -mattr=+f,+d,+v,+zvfh -verify-machineinstrs -riscv-v-vector-bits-min=128 \
; RUN: < %s | FileCheck %s
; RUN: llc -mtriple riscv64 -mattr=+f,+d,+v,+zvfh,+zvfbfmin -verify-machineinstrs -riscv-v-vector-bits-min=128 \
; RUN: < %s | FileCheck %s --check-prefixes=CHECK,ZVFH
; RUN: llc -mtriple riscv64 -mattr=+f,+d,+v,+zvfhmin,+zvfbfmin -verify-machineinstrs -riscv-v-vector-bits-min=128 \
; RUN: < %s | FileCheck %s --check-prefixes=CHECK,ZVFHMIN

define <2 x i64> @test_vp_splice_v2i64(<2 x i64> %va, <2 x i64> %vb, i32 zeroext %evla, i32 zeroext %evlb) {
; CHECK-LABEL: test_vp_splice_v2i64:
Expand Down Expand Up @@ -338,13 +340,64 @@ define <4 x float> @test_vp_splice_nxv2f32_with_firstelt(float %first, <4 x floa
}

define <4 x half> @test_vp_splice_nxv2f16_with_firstelt(half %first, <4 x half> %vb, <4 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_splice_nxv2f16_with_firstelt:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
; CHECK-NEXT: vfslide1up.vf v9, v8, fa0, v0.t
; CHECK-NEXT: vmv1r.v v8, v9
; CHECK-NEXT: ret
; ZVFH-LABEL: test_vp_splice_nxv2f16_with_firstelt:
; ZVFH: # %bb.0:
; ZVFH-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
; ZVFH-NEXT: vfslide1up.vf v9, v8, fa0, v0.t
; ZVFH-NEXT: vmv1r.v v8, v9
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: test_vp_splice_nxv2f16_with_firstelt:
; ZVFHMIN: # %bb.0:
; ZVFHMIN-NEXT: fmv.x.w a1, fa0
; ZVFHMIN-NEXT: vsetivli zero, 4, e16, m1, ta, ma
; ZVFHMIN-NEXT: vmv.s.x v9, a1
; ZVFHMIN-NEXT: vsetvli zero, a0, e16, mf2, ta, mu
; ZVFHMIN-NEXT: vslideup.vi v9, v8, 1, v0.t
; ZVFHMIN-NEXT: vmv1r.v v8, v9
; ZVFHMIN-NEXT: ret
%va = insertelement <4 x half> poison, half %first, i32 0
%v = call <4 x half> @llvm.experimental.vp.splice.nxv2f16(<4 x half> %va, <4 x half> %vb, i32 0, <4 x i1> %mask, i32 1, i32 %evl)
ret <4 x half> %v
}

define <8 x bfloat> @test_vp_splice_v8bf16(<8 x bfloat> %va, <8 x bfloat> %vb, i32 zeroext %evla, i32 zeroext %evlb) {
; CHECK-LABEL: test_vp_splice_v8bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: addi a0, a0, -5
; CHECK-NEXT: vsetvli zero, a0, e16, m1, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 5
; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
; CHECK-NEXT: vslideup.vx v8, v9, a0
; CHECK-NEXT: ret

%v = call <8 x bfloat> @llvm.experimental.vp.splice.v8bf16(<8 x bfloat> %va, <8 x bfloat> %vb, i32 5, <8 x i1> splat (i1 1), i32 %evla, i32 %evlb)
ret <8 x bfloat> %v
}

define <8 x bfloat> @test_vp_splice_v8bf16_negative_offset(<8 x bfloat> %va, <8 x bfloat> %vb, i32 zeroext %evla, i32 zeroext %evlb) {
; CHECK-LABEL: test_vp_splice_v8bf16_negative_offset:
; CHECK: # %bb.0:
; CHECK-NEXT: addi a0, a0, -5
; CHECK-NEXT: vsetivli zero, 5, e16, m1, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
; CHECK-NEXT: vslideup.vi v8, v9, 5
; CHECK-NEXT: ret

%v = call <8 x bfloat> @llvm.experimental.vp.splice.v8bf16(<8 x bfloat> %va, <8 x bfloat> %vb, i32 -5, <8 x i1> splat (i1 1), i32 %evla, i32 %evlb)
ret <8 x bfloat> %v
}

define <8 x bfloat> @test_vp_splice_v8bf16_masked(<8 x bfloat> %va, <8 x bfloat> %vb, <8 x i1> %mask, i32 zeroext %evla, i32 zeroext %evlb) {
; CHECK-LABEL: test_vp_splice_v8bf16_masked:
; CHECK: # %bb.0:
; CHECK-NEXT: addi a0, a0, -5
; CHECK-NEXT: vsetvli zero, a0, e16, m1, ta, ma
; CHECK-NEXT: vslidedown.vi v8, v8, 5, v0.t
; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, mu
; CHECK-NEXT: vslideup.vx v8, v9, a0, v0.t
; CHECK-NEXT: ret
%v = call <8 x bfloat> @llvm.experimental.vp.splice.v8bf16(<8 x bfloat> %va, <8 x bfloat> %vb, i32 5, <8 x i1> %mask, i32 %evla, i32 %evlb)
ret <8 x bfloat> %v
}
Loading