[llvm] c1afcaf - [RISCV] Match deinterleave(4,8) shuffles to SHL/TRUNC when legal (#118509)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Dec 3 19:35:55 PST 2024
Author: Philip Reames
Date: 2024-12-03T19:35:52-08:00
New Revision: c1afcaf33b03638fd533d14b0d3f65cd5c50755c
URL: https://github.com/llvm/llvm-project/commit/c1afcaf33b03638fd533d14b0d3f65cd5c50755c
DIFF: https://github.com/llvm/llvm-project/commit/c1afcaf33b03638fd533d14b0d3f65cd5c50755c.diff
LOG: [RISCV] Match deinterleave(4,8) shuffles to SHL/TRUNC when legal (#118509)
We can extend the existing SHL+TRUNC lowering used for deinterleave2 for
deinterleave4, and deinterleave8 when the result types are small enough
to allow the shift to be legal. On RV64, this means i8 and i16 results
for deinterleave4 and i8 results for deinterleave8.
Added:
Modified:
llvm/lib/Target/RISCV/RISCVISelLowering.cpp
llvm/test/CodeGen/RISCV/rvv/fixed-vectors-deinterleave-load.ll
llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll
llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-changes-length.ll
llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-deinterleave.ll
llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shufflevector-vnsrl.ll
llvm/test/CodeGen/RISCV/rvv/vector-deinterleave-fixed.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index 1e185956bd30e4..4544a922def1a3 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -4446,34 +4446,9 @@ static SDValue lowerScalarInsert(SDValue Scalar, SDValue VL, MVT VT,
VL);
}
-// Is this a shuffle extracts either the even or odd elements of a vector?
-// That is, specifically, either (a) or (b) in the options below.
-// Single operand shuffle is easy:
-// a) t35: v8i8 = vector_shuffle<0,2,4,6,u,u,u,u> t34, undef
-// b) t35: v8i8 = vector_shuffle<1,3,5,7,u,u,u,u> t34, undef
-// Double operand shuffle:
-// t34: v8i8 = extract_subvector t11, Constant:i64<0>
-// t33: v8i8 = extract_subvector t11, Constant:i64<8>
-// a) t35: v8i8 = vector_shuffle<0,2,4,6,8,10,12,14> t34, t33
-// b) t35: v8i8 = vector_shuffle<1,3,5,7,9,11,13,15> t34, t33
-static SDValue isDeinterleaveShuffle(MVT VT, MVT ContainerVT, SDValue V1,
- SDValue V2, ArrayRef<int> Mask,
- const RISCVSubtarget &Subtarget) {
- // Need to be able to widen the vector.
- if (VT.getScalarSizeInBits() >= Subtarget.getELen())
- return SDValue();
-
- // First index must be the first even or odd element from V1.
- if (Mask[0] != 0 && Mask[0] != 1)
- return SDValue();
-
- // The others must increase by 2 each time.
- for (unsigned i = 1; i != Mask.size(); ++i)
- if (Mask[i] != -1 && Mask[i] != Mask[0] + (int)i * 2)
- return SDValue();
-
- if (1 == count_if(Mask, [](int Idx) { return Idx != -1; }))
- return SDValue();
+// Can this shuffle be performed on exactly one (possibly larger) input?
+static SDValue getSingleShuffleSrc(MVT VT, MVT ContainerVT, SDValue V1,
+ SDValue V2) {
if (V2.isUndef() &&
RISCVTargetLowering::getLMUL(ContainerVT) != RISCVII::VLMUL::LMUL_8)
@@ -4490,12 +4465,13 @@ static SDValue isDeinterleaveShuffle(MVT VT, MVT ContainerVT, SDValue V1,
return SDValue();
// Src needs to have twice the number of elements.
- if (Src.getValueType().getVectorNumElements() != (Mask.size() * 2))
+ unsigned NumElts = VT.getVectorNumElements();
+ if (Src.getValueType().getVectorNumElements() != (NumElts * 2))
return SDValue();
// The extracts must extract the two halves of the source.
if (V1.getConstantOperandVal(1) != 0 ||
- V2.getConstantOperandVal(1) != Mask.size())
+ V2.getConstantOperandVal(1) != NumElts)
return SDValue();
return Src;
@@ -4612,36 +4588,29 @@ static int isElementRotate(int &LoSrc, int &HiSrc, ArrayRef<int> Mask) {
return Rotation;
}
-// Lower a deinterleave shuffle to vnsrl.
-// [a, p, b, q, c, r, d, s] -> [a, b, c, d] (EvenElts == true)
-// -> [p, q, r, s] (EvenElts == false)
-// VT is the type of the vector to return, <[vscale x ]n x ty>
-// Src is the vector to deinterleave of type <[vscale x ]n*2 x ty>
-static SDValue getDeinterleaveViaVNSRL(const SDLoc &DL, MVT VT, SDValue Src,
- bool EvenElts, SelectionDAG &DAG) {
- // The result is a vector of type <m x n x ty>. The source is a vector of
- // type <m x n*2 x ty> (For the single source case, the high half is undef)
- if (Src.getValueType() == VT) {
- EVT WideVT = VT.getDoubleNumVectorElementsVT();
- Src = DAG.getNode(ISD::INSERT_SUBVECTOR, DL, WideVT, DAG.getUNDEF(WideVT),
- Src, DAG.getVectorIdxConstant(0, DL));
- }
-
- // Bitcast the source vector from <m x n*2 x ty> -> <m x n x ty*2>
- // This also converts FP to int.
+// Lower a deinterleave shuffle to SRL and TRUNC. Factor must be
+// 2, 4, 8 and the integer type Factor-times larger than VT's
+// element type must be a legal element type.
+// [a, p, b, q, c, r, d, s] -> [a, b, c, d] (Factor=2, Index=0)
+// -> [p, q, r, s] (Factor=2, Index=1)
+static SDValue getDeinterleaveShiftAndTrunc(const SDLoc &DL, MVT VT,
+ SDValue Src, unsigned Factor,
+ unsigned Index, SelectionDAG &DAG) {
unsigned EltBits = VT.getScalarSizeInBits();
- MVT WideSrcVT = MVT::getVectorVT(MVT::getIntegerVT(EltBits * 2),
- VT.getVectorElementCount());
+ ElementCount SrcEC = Src.getValueType().getVectorElementCount();
+ MVT WideSrcVT = MVT::getVectorVT(MVT::getIntegerVT(EltBits * Factor),
+ SrcEC.divideCoefficientBy(Factor));
+ MVT ResVT = MVT::getVectorVT(MVT::getIntegerVT(EltBits),
+ SrcEC.divideCoefficientBy(Factor));
Src = DAG.getBitcast(WideSrcVT, Src);
- MVT IntVT = VT.changeVectorElementTypeToInteger();
-
- // If we want even elements, then the shift amount is 0. Otherwise, shift by
- // the original element size.
- unsigned Shift = EvenElts ? 0 : EltBits;
+ unsigned Shift = Index * EltBits;
SDValue Res = DAG.getNode(ISD::SRL, DL, WideSrcVT, Src,
DAG.getConstant(Shift, DL, WideSrcVT));
- Res = DAG.getNode(ISD::TRUNCATE, DL, IntVT, Res);
+ Res = DAG.getNode(ISD::TRUNCATE, DL, ResVT, Res);
+ MVT IntVT = VT.changeVectorElementTypeToInteger();
+ Res = DAG.getNode(ISD::INSERT_SUBVECTOR, DL, IntVT, DAG.getUNDEF(IntVT), Res,
+ DAG.getVectorIdxConstant(0, DL));
return DAG.getBitcast(VT, Res);
}
@@ -5332,11 +5301,24 @@ static SDValue lowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG,
if (ShuffleVectorInst::isReverseMask(Mask, NumElts) && V2.isUndef())
return DAG.getNode(ISD::VECTOR_REVERSE, DL, VT, V1);
- // If this is a deinterleave and we can widen the vector, then we can use
- // vnsrl to deinterleave.
- if (SDValue Src =
- isDeinterleaveShuffle(VT, ContainerVT, V1, V2, Mask, Subtarget))
- return getDeinterleaveViaVNSRL(DL, VT, Src, Mask[0] == 0, DAG);
+ // If this is a deinterleave(2,4,8) and we can widen the vector, then we can
+ // use shift and truncate to perform the shuffle.
+ // TODO: For Factor=6, we can perform the first step of the deinterleave via
+ // shift-and-trunc reducing total cost for everything except an mf8 result.
+ // TODO: For Factor=4,8, we can do the same when the ratio isn't high enough
+ // to do the entire operation.
+ if (VT.getScalarSizeInBits() < Subtarget.getELen()) {
+ const unsigned MaxFactor = Subtarget.getELen() / VT.getScalarSizeInBits();
+ assert(MaxFactor == 2 || MaxFactor == 4 || MaxFactor == 8);
+ for (unsigned Factor = 2; Factor <= MaxFactor; Factor <<= 1) {
+ unsigned Index = 0;
+ if (ShuffleVectorInst::isDeInterleaveMaskOfFactor(Mask, Factor, Index) &&
+ 1 < count_if(Mask, [](int Idx) { return Idx != -1; })) {
+ if (SDValue Src = getSingleShuffleSrc(VT, ContainerVT, V1, V2))
+ return getDeinterleaveShiftAndTrunc(DL, VT, Src, Factor, Index, DAG);
+ }
+ }
+ }
if (SDValue V =
lowerVECTOR_SHUFFLEAsVSlideup(DL, VT, V1, V2, Mask, Subtarget, DAG))
@@ -10739,8 +10721,8 @@ SDValue RISCVTargetLowering::lowerVECTOR_DEINTERLEAVE(SDValue Op,
// We can deinterleave through vnsrl.wi if the element type is smaller than
// ELEN
if (VecVT.getScalarSizeInBits() < Subtarget.getELen()) {
- SDValue Even = getDeinterleaveViaVNSRL(DL, VecVT, Concat, true, DAG);
- SDValue Odd = getDeinterleaveViaVNSRL(DL, VecVT, Concat, false, DAG);
+ SDValue Even = getDeinterleaveShiftAndTrunc(DL, VecVT, Concat, 2, 0, DAG);
+ SDValue Odd = getDeinterleaveShiftAndTrunc(DL, VecVT, Concat, 2, 1, DAG);
return DAG.getMergeValues({Even, Odd}, DL);
}
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-deinterleave-load.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-deinterleave-load.ll
index ae5dbfa4bf30ba..ede25d2c9bb07c 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-deinterleave-load.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-deinterleave-load.ll
@@ -24,19 +24,20 @@ define {<16 x i1>, <16 x i1>} @vector_deinterleave_load_v16i1_v32i1(ptr %p) {
; CHECK-NEXT: vadd.vi v12, v11, -16
; CHECK-NEXT: vsetivli zero, 2, e8, mf4, ta, ma
; CHECK-NEXT: vslidedown.vi v0, v8, 2
-; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT: vadd.vi v11, v11, -15
; CHECK-NEXT: vmerge.vim v13, v10, 1, v0
; CHECK-NEXT: vmv1r.v v0, v8
-; CHECK-NEXT: vmerge.vim v14, v10, 1, v0
-; CHECK-NEXT: vnsrl.wi v8, v14, 0
+; CHECK-NEXT: vmerge.vim v8, v10, 1, v0
+; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
+; CHECK-NEXT: vnsrl.wi v10, v8, 0
+; CHECK-NEXT: vnsrl.wi v8, v8, 8
; CHECK-NEXT: vmv1r.v v0, v9
-; CHECK-NEXT: vrgather.vv v8, v13, v12, v0.t
-; CHECK-NEXT: vnsrl.wi v12, v14, 8
-; CHECK-NEXT: vmsne.vi v10, v8, 0
-; CHECK-NEXT: vrgather.vv v12, v13, v11, v0.t
-; CHECK-NEXT: vmsne.vi v8, v12, 0
-; CHECK-NEXT: vmv.v.v v0, v10
+; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT: vrgather.vv v10, v13, v12, v0.t
+; CHECK-NEXT: vrgather.vv v8, v13, v11, v0.t
+; CHECK-NEXT: vmsne.vi v0, v10, 0
+; CHECK-NEXT: vmsne.vi v8, v8, 0
; CHECK-NEXT: ret
%vec = load <32 x i1>, ptr %p
%retval = call {<16 x i1>, <16 x i1>} @llvm.vector.deinterleave2.v32i1(<32 x i1> %vec)
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll
index 21417fe8deefb7..5d307211ead6e6 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll
@@ -721,24 +721,12 @@ define <8 x i32> @shuffle_v8i32_2(<8 x i32> %x, <8 x i32> %y) {
define <8 x i8> @shuffle_v64i8_v8i8(<64 x i8> %wide.vec) {
; CHECK-LABEL: shuffle_v64i8_v8i8:
; CHECK: # %bb.0:
-; CHECK-NEXT: lui a0, 4112
-; CHECK-NEXT: li a1, 240
-; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
-; CHECK-NEXT: vmv.s.x v0, a1
-; CHECK-NEXT: li a1, 32
-; CHECK-NEXT: addi a0, a0, 257
-; CHECK-NEXT: vmv.s.x v14, a0
-; CHECK-NEXT: lui a0, 98561
-; CHECK-NEXT: vsetvli zero, a1, e8, m2, ta, ma
-; CHECK-NEXT: vcompress.vm v12, v8, v14
-; CHECK-NEXT: vsetvli zero, a1, e8, m4, ta, ma
-; CHECK-NEXT: vslidedown.vx v8, v8, a1
-; CHECK-NEXT: addi a0, a0, -2048
; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma
-; CHECK-NEXT: vmv.v.x v10, a0
-; CHECK-NEXT: vsetvli zero, a1, e8, m2, ta, mu
-; CHECK-NEXT: vrgather.vv v12, v8, v10, v0.t
-; CHECK-NEXT: vmv1r.v v8, v12
+; CHECK-NEXT: vnsrl.wi v12, v8, 0
+; CHECK-NEXT: vsetvli zero, zero, e16, m1, ta, ma
+; CHECK-NEXT: vnsrl.wi v8, v12, 0
+; CHECK-NEXT: vsetvli zero, zero, e8, mf2, ta, ma
+; CHECK-NEXT: vnsrl.wi v8, v8, 0
; CHECK-NEXT: ret
%s = shufflevector <64 x i8> %wide.vec, <64 x i8> poison, <8 x i32> <i32 0, i32 8, i32 16, i32 24, i32 32, i32 40, i32 48, i32 56>
ret <8 x i8> %s
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-changes-length.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-changes-length.ll
index 9d2c722334b080..66f95b70776720 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-changes-length.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-changes-length.ll
@@ -104,7 +104,7 @@ define <4 x i32> @v4i32_v16i32(<16 x i32>) {
; RV32-NEXT: vmv.v.i v0, 10
; RV32-NEXT: vsetivli zero, 2, e16, m1, tu, ma
; RV32-NEXT: vslideup.vi v14, v12, 1
-; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, ma
+; RV32-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; RV32-NEXT: vnsrl.wx v12, v8, a0
; RV32-NEXT: vsetivli zero, 8, e32, m4, ta, ma
; RV32-NEXT: vslidedown.vi v8, v8, 8
@@ -116,9 +116,8 @@ define <4 x i32> @v4i32_v16i32(<16 x i32>) {
; RV64-LABEL: v4i32_v16i32:
; RV64: # %bb.0:
; RV64-NEXT: li a0, 32
-; RV64-NEXT: vsetivli zero, 1, e8, mf8, ta, ma
+; RV64-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; RV64-NEXT: vmv.v.i v0, 10
-; RV64-NEXT: vsetivli zero, 8, e32, m2, ta, ma
; RV64-NEXT: vnsrl.wx v12, v8, a0
; RV64-NEXT: vsetivli zero, 8, e32, m4, ta, ma
; RV64-NEXT: vslidedown.vi v8, v8, 8
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-deinterleave.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-deinterleave.ll
index 6450174d44ca84..08fd4fb85ff3ff 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-deinterleave.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-deinterleave.ll
@@ -67,22 +67,12 @@ define void @deinterleave4_0_i8(ptr %in, ptr %out) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT: vle8.v v8, (a0)
-; CHECK-NEXT: li a0, -1
-; CHECK-NEXT: vmv.v.i v0, 12
-; CHECK-NEXT: vsetivli zero, 4, e8, mf2, ta, ma
-; CHECK-NEXT: vslidedown.vi v9, v8, 4
-; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
-; CHECK-NEXT: vwaddu.vv v10, v8, v9
-; CHECK-NEXT: vwmaccu.vx v10, a0, v9
+; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT: vnsrl.wi v8, v8, 0
+; CHECK-NEXT: vsetvli zero, zero, e8, mf4, ta, ma
+; CHECK-NEXT: vnsrl.wi v8, v8, 0
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
-; CHECK-NEXT: vid.v v9
-; CHECK-NEXT: vsll.vi v9, v9, 2
-; CHECK-NEXT: vadd.vi v9, v9, -8
-; CHECK-NEXT: vsetivli zero, 8, e8, m1, ta, ma
-; CHECK-NEXT: vslidedown.vi v8, v8, 8
-; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
-; CHECK-NEXT: vrgather.vv v10, v8, v9, v0.t
-; CHECK-NEXT: vse8.v v10, (a1)
+; CHECK-NEXT: vse8.v v8, (a1)
; CHECK-NEXT: ret
entry:
%0 = load <16 x i8>, ptr %in, align 1
@@ -96,20 +86,11 @@ define void @deinterleave4_8_i8(ptr %in, ptr %out) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT: vle8.v v8, (a0)
-; CHECK-NEXT: li a0, -1
-; CHECK-NEXT: vsetivli zero, 8, e8, m1, ta, ma
-; CHECK-NEXT: vslidedown.vi v9, v8, 8
-; CHECK-NEXT: vsetivli zero, 4, e8, mf2, ta, ma
-; CHECK-NEXT: vslidedown.vi v10, v9, 4
-; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
-; CHECK-NEXT: vwaddu.vv v11, v9, v10
-; CHECK-NEXT: vwmaccu.vx v11, a0, v10
-; CHECK-NEXT: li a0, 34
-; CHECK-NEXT: vmv.v.i v0, 12
-; CHECK-NEXT: vmv.s.x v9, a0
+; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT: vnsrl.wi v8, v8, 8
+; CHECK-NEXT: vsetvli zero, zero, e8, mf4, ta, ma
+; CHECK-NEXT: vnsrl.wi v8, v8, 0
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
-; CHECK-NEXT: vcompress.vm v10, v8, v9
-; CHECK-NEXT: vmerge.vvm v8, v10, v11, v0
; CHECK-NEXT: vse8.v v8, (a1)
; CHECK-NEXT: ret
entry:
@@ -268,10 +249,12 @@ define void @deinterleave8_0_i8(ptr %in, ptr %out) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT: vle8.v v8, (a0)
-; CHECK-NEXT: vsetivli zero, 8, e8, m1, ta, ma
-; CHECK-NEXT: vslidedown.vi v9, v8, 8
-; CHECK-NEXT: vsetivli zero, 2, e8, mf2, tu, ma
-; CHECK-NEXT: vslideup.vi v8, v9, 1
+; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
+; CHECK-NEXT: vnsrl.wi v8, v8, 0
+; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
+; CHECK-NEXT: vnsrl.wi v8, v8, 0
+; CHECK-NEXT: vsetvli zero, zero, e8, mf8, ta, ma
+; CHECK-NEXT: vnsrl.wi v8, v8, 0
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vse8.v v8, (a1)
; CHECK-NEXT: ret
@@ -287,12 +270,14 @@ define void @deinterleave8_8_i8(ptr %in, ptr %out) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT: vle8.v v8, (a0)
-; CHECK-NEXT: vmv.v.i v0, -3
-; CHECK-NEXT: vsetivli zero, 8, e8, m1, ta, ma
-; CHECK-NEXT: vslidedown.vi v9, v8, 8
-; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
-; CHECK-NEXT: vrgather.vi v9, v8, 1, v0.t
-; CHECK-NEXT: vse8.v v9, (a1)
+; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
+; CHECK-NEXT: vnsrl.wi v8, v8, 8
+; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
+; CHECK-NEXT: vnsrl.wi v8, v8, 0
+; CHECK-NEXT: vsetvli zero, zero, e8, mf8, ta, ma
+; CHECK-NEXT: vnsrl.wi v8, v8, 0
+; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
+; CHECK-NEXT: vse8.v v8, (a1)
; CHECK-NEXT: ret
entry:
%0 = load <16 x i8>, ptr %in, align 1
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shufflevector-vnsrl.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shufflevector-vnsrl.ll
index 312520ae283745..3aa16070470eaf 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shufflevector-vnsrl.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shufflevector-vnsrl.ll
@@ -441,13 +441,25 @@ entry:
}
define void @vnsrl_0_i8_single_src(ptr %in, ptr %out) {
-; CHECK-LABEL: vnsrl_0_i8_single_src:
-; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: vsetivli zero, 8, e8, mf4, ta, ma
-; CHECK-NEXT: vle8.v v8, (a0)
-; CHECK-NEXT: vnsrl.wi v8, v8, 0
-; CHECK-NEXT: vse8.v v8, (a1)
-; CHECK-NEXT: ret
+; V-LABEL: vnsrl_0_i8_single_src:
+; V: # %bb.0: # %entry
+; V-NEXT: vsetivli zero, 8, e8, mf4, ta, ma
+; V-NEXT: vle8.v v8, (a0)
+; V-NEXT: vsetivli zero, 4, e8, mf8, ta, ma
+; V-NEXT: vnsrl.wi v8, v8, 0
+; V-NEXT: vsetivli zero, 8, e8, mf4, ta, ma
+; V-NEXT: vse8.v v8, (a1)
+; V-NEXT: ret
+;
+; ZVE32F-LABEL: vnsrl_0_i8_single_src:
+; ZVE32F: # %bb.0: # %entry
+; ZVE32F-NEXT: vsetivli zero, 8, e8, mf4, ta, ma
+; ZVE32F-NEXT: vle8.v v8, (a0)
+; ZVE32F-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVE32F-NEXT: vnsrl.wi v8, v8, 0
+; ZVE32F-NEXT: vsetivli zero, 8, e8, mf4, ta, ma
+; ZVE32F-NEXT: vse8.v v8, (a1)
+; ZVE32F-NEXT: ret
entry:
%0 = load <8 x i8>, ptr %in, align 1
%shuffle.i5 = shufflevector <8 x i8> %0, <8 x i8> poison, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
@@ -456,13 +468,25 @@ entry:
}
define void @vnsrl_0_i8_single_src2(ptr %in, ptr %out) {
-; CHECK-LABEL: vnsrl_0_i8_single_src2:
-; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: vsetivli zero, 8, e8, mf4, ta, ma
-; CHECK-NEXT: vle8.v v8, (a0)
-; CHECK-NEXT: vnsrl.wi v8, v8, 0
-; CHECK-NEXT: vse8.v v8, (a1)
-; CHECK-NEXT: ret
+; V-LABEL: vnsrl_0_i8_single_src2:
+; V: # %bb.0: # %entry
+; V-NEXT: vsetivli zero, 8, e8, mf4, ta, ma
+; V-NEXT: vle8.v v8, (a0)
+; V-NEXT: vsetivli zero, 4, e8, mf8, ta, ma
+; V-NEXT: vnsrl.wi v8, v8, 0
+; V-NEXT: vsetivli zero, 8, e8, mf4, ta, ma
+; V-NEXT: vse8.v v8, (a1)
+; V-NEXT: ret
+;
+; ZVE32F-LABEL: vnsrl_0_i8_single_src2:
+; ZVE32F: # %bb.0: # %entry
+; ZVE32F-NEXT: vsetivli zero, 8, e8, mf4, ta, ma
+; ZVE32F-NEXT: vle8.v v8, (a0)
+; ZVE32F-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVE32F-NEXT: vnsrl.wi v8, v8, 0
+; ZVE32F-NEXT: vsetivli zero, 8, e8, mf4, ta, ma
+; ZVE32F-NEXT: vse8.v v8, (a1)
+; ZVE32F-NEXT: ret
entry:
%0 = load <8 x i8>, ptr %in, align 1
%shuffle.i5 = shufflevector <8 x i8> %0, <8 x i8> poison, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 undef, i32 undef, i32 undef, i32 undef>
diff --git a/llvm/test/CodeGen/RISCV/rvv/vector-deinterleave-fixed.ll b/llvm/test/CodeGen/RISCV/rvv/vector-deinterleave-fixed.ll
index 41cf886c3ab75d..6de846b2582dac 100644
--- a/llvm/test/CodeGen/RISCV/rvv/vector-deinterleave-fixed.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vector-deinterleave-fixed.ll
@@ -19,18 +19,19 @@ define {<16 x i1>, <16 x i1>} @vector_deinterleave_v16i1_v32i1(<32 x i1> %vec) {
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; CHECK-NEXT: vmv.s.x v9, a0
; CHECK-NEXT: vmv1r.v v0, v8
-; CHECK-NEXT: vsetvli zero, zero, e8, m1, ta, mu
-; CHECK-NEXT: vmerge.vim v14, v10, 1, v0
-; CHECK-NEXT: vadd.vi v8, v12, -16
+; CHECK-NEXT: vsetvli zero, zero, e8, m1, ta, ma
+; CHECK-NEXT: vmerge.vim v8, v10, 1, v0
+; CHECK-NEXT: vadd.vi v10, v12, -16
; CHECK-NEXT: vadd.vi v12, v12, -15
-; CHECK-NEXT: vnsrl.wi v10, v14, 0
+; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
+; CHECK-NEXT: vnsrl.wi v13, v8, 0
+; CHECK-NEXT: vnsrl.wi v8, v8, 8
; CHECK-NEXT: vmv1r.v v0, v9
-; CHECK-NEXT: vrgather.vv v10, v11, v8, v0.t
-; CHECK-NEXT: vnsrl.wi v8, v14, 8
-; CHECK-NEXT: vmsne.vi v10, v10, 0
+; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT: vrgather.vv v13, v11, v10, v0.t
; CHECK-NEXT: vrgather.vv v8, v11, v12, v0.t
+; CHECK-NEXT: vmsne.vi v0, v13, 0
; CHECK-NEXT: vmsne.vi v8, v8, 0
-; CHECK-NEXT: vmv.v.v v0, v10
; CHECK-NEXT: ret
%retval = call {<16 x i1>, <16 x i1>} @llvm.vector.deinterleave2.v32i1(<32 x i1> %vec)
ret {<16 x i1>, <16 x i1>} %retval
More information about the llvm-commits
mailing list