[llvm-branch-commits] [llvm] [llvm][LoongArch] Improve loongarch_lasx_xvpermi_q instrinsic (#82984) (PR #83536)

[via llvm-branch-commits]

https://github.com/leecheechen created https://github.com/llvm/llvm-project/pull/83536

For instruction xvpermi.q, only [1:0] and [5:4] bits of operands[3] are used. The unused bits in operands[3] need to be set to 0 to avoid causing undefined behavior.

(cherry picked from commit d7c80bba698bded48c1df4b4bb7424a181aa6195)

>From b093677cef50398942c7b9505d4c742883ee7f93 Mon Sep 17 00:00:00 2001
From: leecheechen <chenli at loongson.cn>
Date: Tue, 27 Feb 2024 15:38:11 +0800
Subject: [PATCH] [llvm][LoongArch] Improve loongarch_lasx_xvpermi_q instrinsic
 (#82984)

For instruction xvpermi.q, only [1:0] and [5:4] bits of operands[3] are
used. The unused bits in operands[3] need to be set to 0 to avoid
causing undefined behavior.

(cherry picked from commit d7c80bba698bded48c1df4b4bb7424a181aa6195)
---
 .../LoongArch/LoongArchISelLowering.cpp       | 25 +++++++++++++++-
 .../CodeGen/LoongArch/lasx/intrinsic-permi.ll | 30 +++++++++++++++++++
 2 files changed, 54 insertions(+), 1 deletion(-)

diff --git a/llvm/lib/Target/LoongArch/LoongArchISelLowering.cpp b/llvm/lib/Target/LoongArch/LoongArchISelLowering.cpp
index 76c1a14fe0156c..3324dd2e8fc217 100644
--- a/llvm/lib/Target/LoongArch/LoongArchISelLowering.cpp
+++ b/llvm/lib/Target/LoongArch/LoongArchISelLowering.cpp
@@ -968,6 +968,28 @@ static SDValue checkIntrinsicImmArg(SDValue Op, unsigned ImmOp,
   return SDValue();
 }
 
+static SDValue checkAndModifyXVPERMI_QIntrinsicImmArg(SDValue Op,
+                                                      SelectionDAG &DAG) {
+  SDValue Op3 = Op->getOperand(3);
+  uint64_t Imm = Op3->getAsZExtVal();
+  // Check the range of ImmArg.
+  if (!isUInt<8>(Imm)) {
+    DAG.getContext()->emitError(Op->getOperationName(0) +
+                                ": argument out of range.");
+    return DAG.getNode(ISD::UNDEF, SDLoc(Op), Op.getValueType());
+  }
+
+  // For instruction xvpermi.q, only [1:0] and [5:4] bits of operands[3]
+  // are used. The unused bits in operands[3] need to be set to 0 to avoid
+  // causing undefined behavior on LA464.
+  if ((Imm & 0x33) != Imm) {
+    Op3 = DAG.getTargetConstant(Imm & 0x33, SDLoc(Op), Op3.getValueType());
+    DAG.UpdateNodeOperands(Op.getNode(), Op->getOperand(0), Op->getOperand(1),
+                           Op->getOperand(2), Op3);
+  }
+  return SDValue();
+}
+
 SDValue
 LoongArchTargetLowering::lowerINTRINSIC_WO_CHAIN(SDValue Op,
                                                  SelectionDAG &DAG) const {
@@ -1225,13 +1247,14 @@ LoongArchTargetLowering::lowerINTRINSIC_WO_CHAIN(SDValue Op,
   case Intrinsic::loongarch_lsx_vextrins_d:
   case Intrinsic::loongarch_lasx_xvshuf4i_d:
   case Intrinsic::loongarch_lasx_xvpermi_w:
-  case Intrinsic::loongarch_lasx_xvpermi_q:
   case Intrinsic::loongarch_lasx_xvbitseli_b:
   case Intrinsic::loongarch_lasx_xvextrins_b:
   case Intrinsic::loongarch_lasx_xvextrins_h:
   case Intrinsic::loongarch_lasx_xvextrins_w:
   case Intrinsic::loongarch_lasx_xvextrins_d:
     return checkIntrinsicImmArg<8>(Op, 3, DAG);
+  case Intrinsic::loongarch_lasx_xvpermi_q:
+    return checkAndModifyXVPERMI_QIntrinsicImmArg(Op, DAG);
   case Intrinsic::loongarch_lsx_vrepli_b:
   case Intrinsic::loongarch_lsx_vrepli_h:
   case Intrinsic::loongarch_lsx_vrepli_w:
diff --git a/llvm/test/CodeGen/LoongArch/lasx/intrinsic-permi.ll b/llvm/test/CodeGen/LoongArch/lasx/intrinsic-permi.ll
index 0d9f9daabc4488..92669d2e589558 100644
--- a/llvm/test/CodeGen/LoongArch/lasx/intrinsic-permi.ll
+++ b/llvm/test/CodeGen/LoongArch/lasx/intrinsic-permi.ll
@@ -36,3 +36,33 @@ entry:
   %res = call <32 x i8> @llvm.loongarch.lasx.xvpermi.q(<32 x i8> %va, <32 x i8> %vb, i32 1)
   ret <32 x i8> %res
 }
+
+define <32 x i8> @lasx_xvpermi_q_204(<32 x i8> %va, <32 x i8> %vb) nounwind {
+; CHECK-LABEL: lasx_xvpermi_q_204:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    xvpermi.q $xr0, $xr1, 0
+; CHECK-NEXT:    ret
+entry:
+  %res = call <32 x i8> @llvm.loongarch.lasx.xvpermi.q(<32 x i8> %va, <32 x i8> %vb, i32 204)
+  ret <32 x i8> %res
+}
+
+define <32 x i8> @lasx_xvpermi_q_221(<32 x i8> %va, <32 x i8> %vb) nounwind {
+; CHECK-LABEL: lasx_xvpermi_q_221:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    xvpermi.q $xr0, $xr1, 17
+; CHECK-NEXT:    ret
+entry:
+  %res = call <32 x i8> @llvm.loongarch.lasx.xvpermi.q(<32 x i8> %va, <32 x i8> %vb, i32 221)
+  ret <32 x i8> %res
+}
+
+define <32 x i8> @lasx_xvpermi_q_255(<32 x i8> %va, <32 x i8> %vb) nounwind {
+; CHECK-LABEL: lasx_xvpermi_q_255:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    xvpermi.q $xr0, $xr1, 51
+; CHECK-NEXT:    ret
+entry:
+  %res = call <32 x i8> @llvm.loongarch.lasx.xvpermi.q(<32 x i8> %va, <32 x i8> %vb, i32 255)
+  ret <32 x i8> %res
+}