[RISCV] Remove mask from vrgatherei16 in lowerVECTOR_INTERLEAVE.

[craig.topper]

Summary

Unless I'm missing something we need to update the whole vector
not just where OddMask is true.

[luke]

LGTM, not sure what I was thinking.

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

 //===-- RISCVISelLowering.cpp - RISC-V DAG Lowering Implementation  -------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
if (VecVT.getScalarSizeInBits() < Subtarget.getELEN()) {
     //      0      0      1      1      2      2      3      3 ...
     SDValue Idx = DAG.getNode(ISD::SRL, DL, IdxVT, StepVec, Ones);
     //      0      n      1    n+1      2    n+2      3    n+3 ...
     Idx =
         DAG.getNode(RISCVISD::ADD_VL, DL, IdxVT, Idx, VLMax, Idx, OddMask, VL);
 
     // Then perform the interleave
     //   v[0]   v[n]   v[1] v[n+1]   v[2] v[n+2]   v[3] v[n+3] ...
+    SDValue TrueMask = getAllOnesMask(IdxVT, VL, DL, DAG);
     Interleaved = DAG.getNode(RISCVISD::VRGATHEREI16_VV_VL, DL, ConcatVT,
-                              Concat, Idx, DAG.getUNDEF(ConcatVT), OddMask, VL);
+                              Concat, Idx, DAG.getUNDEF(ConcatVT), TrueMask, VL);
   }
 
   // Extract the two halves from the interleaved result
   SDValue Lo = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, VecVT, Interleaved,
                            DAG.getVectorIdxConstant(0, DL));
   SDValue Hi = DAG.getNode(
       ISD::EXTRACT_SUBVECTOR, DL, VecVT, Interleaved,
       DAG.getVectorIdxConstant(VecVT.getVectorMinNumElements(), DL));

llvm/test/CodeGen/RISCV/rvv/vector-interleave.ll

 ; CHECK-NEXT:    srli a0, a0, 2
 ; CHECK-NEXT:    vsetvli a1, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vid.v v12
 ; CHECK-NEXT:    vand.vi v13, v12, 1
 ; CHECK-NEXT:    vmsne.vi v0, v13, 0
 ; CHECK-NEXT:    vsrl.vi v16, v12, 1
 ; CHECK-NEXT:    vadd.vx v16, v16, a0, v0.t
 ; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
-; CHECK-NEXT:    vrgatherei16.vv v12, v8, v16, v0.t
+; CHECK-NEXT:    vrgatherei16.vv v12, v8, v16
 ; CHECK-NEXT:    vmv.v.v v8, v12
 ; CHECK-NEXT:    ret
   %res = call <vscale x 4 x i64> @llvm.experimental.vector.interleave2.nxv4i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
   ret <vscale x 4 x i64> %res
 }
 
 declare <vscale x 32 x i1> @llvm.experimental.vector.interleave2.nxv32i1(<vscale x 16 x i1>, <vscale x 16 x i1>)
 declare <vscale x 32 x i8> @llvm.experimental.vector.interleave2.nxv32i8(<vscale x 16 x i8>, <vscale x 16 x i8>)

 }
 
 define <vscale x 16 x i64> @vector_interleave_nxv16i64_nxv8i64(<vscale x 8 x i64> %a, <vscale x 8 x i64> %b) {
 ; CHECK-LABEL: vector_interleave_nxv16i64_nxv8i64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    addi sp, sp, -16
 ; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 16 * vlenb
-; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
-; CHECK-NEXT:    vs8r.v v8, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT:    sub sp, sp, a0
+; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
+; CHECK-NEXT:    vmv8r.v v0, v8
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    srli a0, a0, 1
 ; CHECK-NEXT:    vsetvli a1, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vid.v v24
 ; CHECK-NEXT:    vand.vi v26, v24, 1
-; CHECK-NEXT:    vmsne.vi v0, v26, 0
-; CHECK-NEXT:    vsrl.vi v2, v24, 1
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 3
-; CHECK-NEXT:    add a1, sp, a1
-; CHECK-NEXT:    addi a1, a1, 16
-; CHECK-NEXT:    vl8r.v v8, (a1) # Unknown-size Folded Reload
-; CHECK-NEXT:    vadd.vx v2, v2, a0, v0.t
-; CHECK-NEXT:    vmv4r.v v12, v16
+; CHECK-NEXT:    vmsne.vi v10, v26, 0
+; CHECK-NEXT:    vsrl.vi v8, v24, 1
+; CHECK-NEXT:    vmv8r.v v24, v0
+; CHECK-NEXT:    vmv4r.v v12, v4
+; CHECK-NEXT:    vmv1r.v v0, v10
+; CHECK-NEXT:    vadd.vx v8, v8, a0, v0.t
+; CHECK-NEXT:    vmv4r.v v28, v16
 ; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vrgatherei16.vv v24, v8, v2, v0.t
+; CHECK-NEXT:    vrgatherei16.vv v0, v24, v8
 ; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vs8r.v v24, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
-; CHECK-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vs8r.v v0, (a0) # Unknown-size Folded Spill
 ; CHECK-NEXT:    vmv4r.v v16, v12
-; CHECK-NEXT:    vrgatherei16.vv v24, v16, v2, v0.t
-; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vrgatherei16.vv v24, v16, v8
 ; CHECK-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
 ; CHECK-NEXT:    vmv.v.v v16, v24
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
+; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    add sp, sp, a0
 ; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    ret
   %res = call <vscale x 16 x i64> @llvm.experimental.vector.interleave2.nxv16i64(<vscale x 8 x i64> %a, <vscale x 8 x i64> %b)
   ret <vscale x 16 x i64> %res
 }
 
 declare <vscale x 128 x i1> @llvm.experimental.vector.interleave2.nxv128i1(<vscale x 64 x i1>, <vscale x 64 x i1>)

 ; CHECK-NEXT:    srli a0, a0, 2
 ; CHECK-NEXT:    vsetvli a1, zero, e16, m1, ta, mu
 ; CHECK-NEXT:    vid.v v12
 ; CHECK-NEXT:    vand.vi v13, v12, 1
 ; CHECK-NEXT:    vmsne.vi v0, v13, 0
 ; CHECK-NEXT:    vsrl.vi v16, v12, 1
 ; CHECK-NEXT:    vadd.vx v16, v16, a0, v0.t
 ; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
-; CHECK-NEXT:    vrgatherei16.vv v12, v8, v16, v0.t
+; CHECK-NEXT:    vrgatherei16.vv v12, v8, v16
 ; CHECK-NEXT:    vmv.v.v v8, v12
 ; CHECK-NEXT:    ret
   %res = call <vscale x 4 x double> @llvm.experimental.vector.interleave2.nxv4f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b)
   ret <vscale x 4 x double> %res
 }
 
 
 declare <vscale x 4 x half> @llvm.experimental.vector.interleave2.nxv4f16(<vscale x 2 x half>, <vscale x 2 x half>)

 }
 
 define <vscale x 16 x double> @vector_interleave_nxv16f64_nxv8f64(<vscale x 8 x double> %a, <vscale x 8 x double> %b) {
 ; CHECK-LABEL: vector_interleave_nxv16f64_nxv8f64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    addi sp, sp, -16
 ; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 16 * vlenb
-; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
-; CHECK-NEXT:    vs8r.v v8, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT:    sub sp, sp, a0
+; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
+; CHECK-NEXT:    vmv8r.v v0, v8
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    srli a0, a0, 1
 ; CHECK-NEXT:    vsetvli a1, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vid.v v24
 ; CHECK-NEXT:    vand.vi v26, v24, 1
-; CHECK-NEXT:    vmsne.vi v0, v26, 0
-; CHECK-NEXT:    vsrl.vi v2, v24, 1
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 3
-; CHECK-NEXT:    add a1, sp, a1
-; CHECK-NEXT:    addi a1, a1, 16
-; CHECK-NEXT:    vl8r.v v8, (a1) # Unknown-size Folded Reload
-; CHECK-NEXT:    vadd.vx v2, v2, a0, v0.t
-; CHECK-NEXT:    vmv4r.v v12, v16
+; CHECK-NEXT:    vmsne.vi v10, v26, 0
+; CHECK-NEXT:    vsrl.vi v8, v24, 1
+; CHECK-NEXT:    vmv8r.v v24, v0
+; CHECK-NEXT:    vmv4r.v v12, v4
+; CHECK-NEXT:    vmv1r.v v0, v10
+; CHECK-NEXT:    vadd.vx v8, v8, a0, v0.t
+; CHECK-NEXT:    vmv4r.v v28, v16
 ; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vrgatherei16.vv v24, v8, v2, v0.t
+; CHECK-NEXT:    vrgatherei16.vv v0, v24, v8
 ; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vs8r.v v24, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 3
-; CHECK-NEXT:    add a0, sp, a0
-; CHECK-NEXT:    addi a0, a0, 16
-; CHECK-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vs8r.v v0, (a0) # Unknown-size Folded Spill
 ; CHECK-NEXT:    vmv4r.v v16, v12
-; CHECK-NEXT:    vrgatherei16.vv v24, v16, v2, v0.t
-; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vrgatherei16.vv v24, v16, v8
 ; CHECK-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
 ; CHECK-NEXT:    vmv.v.v v16, v24
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
+; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    add sp, sp, a0
 ; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    ret
   %res = call <vscale x 16 x double> @llvm.experimental.vector.interleave2.nxv16f64(<vscale x 8 x double> %a, <vscale x 8 x double> %b)
   ret <vscale x 16 x double> %res
 }
 
 declare <vscale x 64 x half> @llvm.experimental.vector.interleave2.nxv64f16(<vscale x 32 x half>, <vscale x 32 x half>)
 declare <vscale x 32 x float> @llvm.experimental.vector.interleave2.nxv32f32(<vscale x 16 x float>, <vscale x 16 x float>)
 declare <vscale x 16 x double> @llvm.experimental.vector.interleave2.nxv16f64(<vscale x 8 x double>, <vscale x 8 x double>)