Skip to content

[RISCV] Use X0 for VLMax for slide1up/slide1down in lowerVectorIntrinsicScalars. #101384

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 1 commit into from
Jul 31, 2024
Merged

[RISCV] Use X0 for VLMax for slide1up/slide1down in lowerVectorIntrinsicScalars. #101384

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
9 changes: 1 addition & 8 deletions llvm/lib/Target/RISCV/RISCVISelLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8857,14 +8857,7 @@ static SDValue lowerVectorIntrinsicScalars(SDValue Op, SelectionDAG &DAG,
I32VL = DAG.getConstant(2 * AVLInt, DL, XLenVT);
} else if (AVLInt >= 2 * MaxVLMAX) {
// Just set vl to VLMAX in this situation
RISCVII::VLMUL Lmul = RISCVTargetLowering::getLMUL(I32VT);
SDValue LMUL = DAG.getConstant(Lmul, DL, XLenVT);
unsigned Sew = RISCVVType::encodeSEW(I32VT.getScalarSizeInBits());
SDValue SEW = DAG.getConstant(Sew, DL, XLenVT);
SDValue SETVLMAX = DAG.getTargetConstant(
Intrinsic::riscv_vsetvlimax, DL, MVT::i32);
I32VL = DAG.getNode(ISD::INTRINSIC_WO_CHAIN, DL, XLenVT, SETVLMAX, SEW,
LMUL);
I32VL = DAG.getRegister(RISCV::X0, XLenVT);
} else {
// For AVL between (MinVLMAX, 2 * MaxVLMAX), the actual working vl
// is related to the hardware implementation.
Expand Down
44 changes: 29 additions & 15 deletions llvm/test/CodeGen/RISCV/rvv/vslide1down-constant-vl-rv32.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,7 @@ define <vscale x 1 x i64> @intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl2(<vsc
;
; CHECK-64-LABEL: intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl2:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-64-NEXT: vsetivli zero, 2, e32, m1, ta, ma
; CHECK-64-NEXT: vslide1down.vx v8, v8, a0
; CHECK-64-NEXT: vslide1down.vx v8, v8, a1
; CHECK-64-NEXT: ret
Expand Down Expand Up @@ -84,7 +84,7 @@ define <vscale x 1 x i64> @intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl3(<vsc
;
; CHECK-64-LABEL: intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl3:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-64-NEXT: vsetivli zero, 2, e32, m1, ta, ma
; CHECK-64-NEXT: vslide1down.vx v8, v8, a0
; CHECK-64-NEXT: vslide1down.vx v8, v8, a1
; CHECK-64-NEXT: ret
Expand Down Expand Up @@ -117,7 +117,7 @@ define <vscale x 1 x i64> @intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl8(<vsc
;
; CHECK-64-LABEL: intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl8:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-64-NEXT: vsetivli zero, 2, e32, m1, ta, ma
; CHECK-64-NEXT: vslide1down.vx v8, v8, a0
; CHECK-64-NEXT: vslide1down.vx v8, v8, a1
; CHECK-64-NEXT: ret
Expand Down Expand Up @@ -152,7 +152,7 @@ define <vscale x 1 x i64> @intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl9(<vsc
;
; CHECK-64-LABEL: intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl9:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-64-NEXT: vsetivli zero, 2, e32, m1, ta, ma
; CHECK-64-NEXT: vslide1down.vx v8, v8, a0
; CHECK-64-NEXT: vslide1down.vx v8, v8, a1
; CHECK-64-NEXT: ret
Expand Down Expand Up @@ -187,7 +187,7 @@ define <vscale x 1 x i64> @intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl15(<vs
;
; CHECK-64-LABEL: intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl15:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-64-NEXT: vsetivli zero, 2, e32, m1, ta, ma
; CHECK-64-NEXT: vslide1down.vx v8, v8, a0
; CHECK-64-NEXT: vslide1down.vx v8, v8, a1
; CHECK-64-NEXT: ret
Expand All @@ -213,14 +213,14 @@ define <vscale x 1 x i64> @intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl16(<vs
;
; CHECK-512-LABEL: intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl16:
; CHECK-512: # %bb.0: # %entry
; CHECK-512-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-512-NEXT: vsetivli zero, 16, e32, m1, ta, ma
; CHECK-512-NEXT: vslide1down.vx v8, v8, a0
; CHECK-512-NEXT: vslide1down.vx v8, v8, a1
; CHECK-512-NEXT: ret
;
; CHECK-64-LABEL: intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl16:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-64-NEXT: vsetivli zero, 2, e32, m1, ta, ma
; CHECK-64-NEXT: vslide1down.vx v8, v8, a0
; CHECK-64-NEXT: vslide1down.vx v8, v8, a1
; CHECK-64-NEXT: ret
Expand All @@ -247,14 +247,14 @@ define <vscale x 1 x i64> @intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl2047(<
;
; CHECK-512-LABEL: intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl2047:
; CHECK-512: # %bb.0: # %entry
; CHECK-512-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-512-NEXT: vsetivli zero, 16, e32, m1, ta, ma
; CHECK-512-NEXT: vslide1down.vx v8, v8, a0
; CHECK-512-NEXT: vslide1down.vx v8, v8, a1
; CHECK-512-NEXT: ret
;
; CHECK-64-LABEL: intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl2047:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-64-NEXT: vsetivli zero, 2, e32, m1, ta, ma
; CHECK-64-NEXT: vslide1down.vx v8, v8, a0
; CHECK-64-NEXT: vslide1down.vx v8, v8, a1
; CHECK-64-NEXT: ret
Expand All @@ -269,12 +269,26 @@ entry:
}

define <vscale x 1 x i64> @intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl2048(<vscale x 1 x i64> %0, i64 %1) nounwind {
; CHECK-LABEL: intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl2048:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-NEXT: vslide1down.vx v8, v8, a0
; CHECK-NEXT: vslide1down.vx v8, v8, a1
; CHECK-NEXT: ret
; CHECK-128-65536-LABEL: intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl2048:
; CHECK-128-65536: # %bb.0: # %entry
; CHECK-128-65536-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-128-65536-NEXT: vslide1down.vx v8, v8, a0
; CHECK-128-65536-NEXT: vslide1down.vx v8, v8, a1
; CHECK-128-65536-NEXT: ret
;
; CHECK-512-LABEL: intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl2048:
; CHECK-512: # %bb.0: # %entry
; CHECK-512-NEXT: vsetivli zero, 16, e32, m1, ta, ma
; CHECK-512-NEXT: vslide1down.vx v8, v8, a0
; CHECK-512-NEXT: vslide1down.vx v8, v8, a1
; CHECK-512-NEXT: ret
;
; CHECK-64-LABEL: intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64_vl2048:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: vsetivli zero, 2, e32, m1, ta, ma
; CHECK-64-NEXT: vslide1down.vx v8, v8, a0
; CHECK-64-NEXT: vslide1down.vx v8, v8, a1
; CHECK-64-NEXT: ret
entry:
%a = call <vscale x 1 x i64> @llvm.riscv.vslide1down.nxv1i64.i64(
<vscale x 1 x i64> undef,
Expand Down
44 changes: 29 additions & 15 deletions llvm/test/CodeGen/RISCV/rvv/vslide1up-constant-vl-rv32.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,7 @@ define <vscale x 1 x i64> @intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl2(<vscal
;
; CHECK-64-LABEL: intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl2:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-64-NEXT: vsetivli zero, 2, e32, m1, ta, ma
; CHECK-64-NEXT: vslide1up.vx v9, v8, a1
; CHECK-64-NEXT: vslide1up.vx v8, v9, a0
; CHECK-64-NEXT: ret
Expand Down Expand Up @@ -84,7 +84,7 @@ define <vscale x 1 x i64> @intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl3(<vscal
;
; CHECK-64-LABEL: intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl3:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-64-NEXT: vsetivli zero, 2, e32, m1, ta, ma
; CHECK-64-NEXT: vslide1up.vx v9, v8, a1
; CHECK-64-NEXT: vslide1up.vx v8, v9, a0
; CHECK-64-NEXT: ret
Expand Down Expand Up @@ -117,7 +117,7 @@ define <vscale x 1 x i64> @intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl8(<vscal
;
; CHECK-64-LABEL: intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl8:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-64-NEXT: vsetivli zero, 2, e32, m1, ta, ma
; CHECK-64-NEXT: vslide1up.vx v9, v8, a1
; CHECK-64-NEXT: vslide1up.vx v8, v9, a0
; CHECK-64-NEXT: ret
Expand Down Expand Up @@ -152,7 +152,7 @@ define <vscale x 1 x i64> @intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl9(<vscal
;
; CHECK-64-LABEL: intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl9:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-64-NEXT: vsetivli zero, 2, e32, m1, ta, ma
; CHECK-64-NEXT: vslide1up.vx v9, v8, a1
; CHECK-64-NEXT: vslide1up.vx v8, v9, a0
; CHECK-64-NEXT: ret
Expand Down Expand Up @@ -187,7 +187,7 @@ define <vscale x 1 x i64> @intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl15(<vsca
;
; CHECK-64-LABEL: intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl15:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-64-NEXT: vsetivli zero, 2, e32, m1, ta, ma
; CHECK-64-NEXT: vslide1up.vx v9, v8, a1
; CHECK-64-NEXT: vslide1up.vx v8, v9, a0
; CHECK-64-NEXT: ret
Expand All @@ -213,14 +213,14 @@ define <vscale x 1 x i64> @intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl16(<vsca
;
; CHECK-512-LABEL: intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl16:
; CHECK-512: # %bb.0: # %entry
; CHECK-512-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-512-NEXT: vsetivli zero, 16, e32, m1, ta, ma
; CHECK-512-NEXT: vslide1up.vx v9, v8, a1
; CHECK-512-NEXT: vslide1up.vx v8, v9, a0
; CHECK-512-NEXT: ret
;
; CHECK-64-LABEL: intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl16:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-64-NEXT: vsetivli zero, 2, e32, m1, ta, ma
; CHECK-64-NEXT: vslide1up.vx v9, v8, a1
; CHECK-64-NEXT: vslide1up.vx v8, v9, a0
; CHECK-64-NEXT: ret
Expand All @@ -247,14 +247,14 @@ define <vscale x 1 x i64> @intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl2047(<vs
;
; CHECK-512-LABEL: intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl2047:
; CHECK-512: # %bb.0: # %entry
; CHECK-512-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-512-NEXT: vsetivli zero, 16, e32, m1, ta, ma
; CHECK-512-NEXT: vslide1up.vx v9, v8, a1
; CHECK-512-NEXT: vslide1up.vx v8, v9, a0
; CHECK-512-NEXT: ret
;
; CHECK-64-LABEL: intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl2047:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-64-NEXT: vsetivli zero, 2, e32, m1, ta, ma
; CHECK-64-NEXT: vslide1up.vx v9, v8, a1
; CHECK-64-NEXT: vslide1up.vx v8, v9, a0
; CHECK-64-NEXT: ret
Expand All @@ -269,12 +269,26 @@ entry:
}

define <vscale x 1 x i64> @intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl2048(<vscale x 1 x i64> %0, i64 %1) nounwind {
; CHECK-LABEL: intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl2048:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-NEXT: vslide1up.vx v9, v8, a1
; CHECK-NEXT: vslide1up.vx v8, v9, a0
; CHECK-NEXT: ret
; CHECK-128-65536-LABEL: intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl2048:
; CHECK-128-65536: # %bb.0: # %entry
; CHECK-128-65536-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-128-65536-NEXT: vslide1up.vx v9, v8, a1
; CHECK-128-65536-NEXT: vslide1up.vx v8, v9, a0
; CHECK-128-65536-NEXT: ret
;
; CHECK-512-LABEL: intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl2048:
; CHECK-512: # %bb.0: # %entry
; CHECK-512-NEXT: vsetivli zero, 16, e32, m1, ta, ma
; CHECK-512-NEXT: vslide1up.vx v9, v8, a1
; CHECK-512-NEXT: vslide1up.vx v8, v9, a0
; CHECK-512-NEXT: ret
;
; CHECK-64-LABEL: intrinsic_vslide1up_vx_nxv1i64_nxv1i64_i64_vl2048:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: vsetivli zero, 2, e32, m1, ta, ma
; CHECK-64-NEXT: vslide1up.vx v9, v8, a1
; CHECK-64-NEXT: vslide1up.vx v8, v9, a0
; CHECK-64-NEXT: ret
entry:
%a = call <vscale x 1 x i64> @llvm.riscv.vslide1up.nxv1i64.i64(
<vscale x 1 x i64> undef,
Expand Down
Loading