[RISCV] Teach vsetvli insertion pass that it doesn't need to insert vsetvli for unit...

For unit-stride and strided load/stores we set the SEW operand of
the pseudo instruction equal the EEW in the opcode. The LMUL
of the pseudo instruction is the LMUL we want.

These instructions calculate EMUL=(EEW/SEW) * LMUL. We can use
this to avoid changing vtype if the SEW/LMUL of the previous
vtype matches the EEW/EMUL ratio we need for the instruction.

Due to how the global analysis works, we can only do this
optimization when the previous vsetvli was produced in the block
containing the store. We need to know in the first phase if the
vsetvli will be inserted so we can propagate information to
the successors in the second phase correctly. This means we can't
depend on predecessors.

Reviewed By: rogfer01

Differential Revision: https://reviews.llvm.org/D106601

diff --git a/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp b/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp
index b8ff072..8bd39b9 100644 (file)
--- a/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp
+++ b/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp
@@ -148,10 +148,7 @@ public:
                     Other.MaskAgnostic);
   }
 
-  // Convert VLMUL to a fixed point value with 3 bits of fraction.
-  unsigned getSEWLMULRatio() const {
-    assert(isValid() && !isUnknown() &&
-           "Can't use VTYPE for uninitialized or unknown");
+  static unsigned getSEWLMULRatio(unsigned SEW, RISCVII::VLMUL VLMul) {
     unsigned LMul;
     bool Fractional;
     std::tie(LMul, Fractional) = RISCVVType::decodeVLMUL(VLMul);
@@ -163,6 +160,12 @@ public:
     return (SEW * 8) / LMul;
   }
 
+  unsigned getSEWLMULRatio() const {
+    assert(isValid() && !isUnknown() &&
+           "Can't use VTYPE for uninitialized or unknown");
+    return getSEWLMULRatio(SEW, VLMul);
+  }
+
   // Check if the VTYPE for these two VSETVLIInfos produce the same VLMAX.
   bool hasSameVLMAX(const VSETVLIInfo &Other) const {
     assert(isValid() && Other.isValid() &&
@@ -208,6 +211,29 @@ public:
     return hasSameAVL(InstrInfo);
   }
 
+  bool isCompatibleWithLoadStoreEEW(unsigned EEW,
+                                    const VSETVLIInfo &InstrInfo) const {
+    assert(isValid() && InstrInfo.isValid() &&
+           "Can't compare invalid VSETVLIInfos");
+    assert(!InstrInfo.SEWLMULRatioOnly &&
+           "Expected a valid VTYPE for instruction!");
+    assert(EEW == InstrInfo.SEW && "Mismatched EEW/SEW for store");
+
+    if (isUnknown() || hasSEWLMULRatioOnly())
+      return false;
+
+    if (!hasSameAVL(InstrInfo))
+      return false;
+
+    // TODO: This check isn't required for stores. But we should ignore for all
+    // stores not just unit-stride and strided so leaving it for now.
+    if (TailAgnostic != InstrInfo.TailAgnostic ||
+        MaskAgnostic != InstrInfo.MaskAgnostic)
+      return false;
+
+    return getSEWLMULRatio() == getSEWLMULRatio(EEW, InstrInfo.VLMul);
+  }
+
   bool operator==(const VSETVLIInfo &Other) const {
     // Uninitialized is only equal to another Uninitialized.
     if (!isValid())
@@ -515,6 +541,202 @@ bool RISCVInsertVSETVLI::needVSETVLI(const VSETVLIInfo &Require,
   return true;
 }
 
+bool canSkipVSETVLIForLoadStore(const MachineInstr &MI,
+                                const VSETVLIInfo &Require,
+                                const VSETVLIInfo &CurInfo) {
+  unsigned EEW;
+  switch (MI.getOpcode()) {
+  default:
+    return false;
+  case RISCV::PseudoVLE8_V_M1:
+  case RISCV::PseudoVLE8_V_M1_MASK:
+  case RISCV::PseudoVLE8_V_M2:
+  case RISCV::PseudoVLE8_V_M2_MASK:
+  case RISCV::PseudoVLE8_V_M4:
+  case RISCV::PseudoVLE8_V_M4_MASK:
+  case RISCV::PseudoVLE8_V_M8:
+  case RISCV::PseudoVLE8_V_M8_MASK:
+  case RISCV::PseudoVLE8_V_MF2:
+  case RISCV::PseudoVLE8_V_MF2_MASK:
+  case RISCV::PseudoVLE8_V_MF4:
+  case RISCV::PseudoVLE8_V_MF4_MASK:
+  case RISCV::PseudoVLE8_V_MF8:
+  case RISCV::PseudoVLE8_V_MF8_MASK:
+  case RISCV::PseudoVLSE8_V_M1:
+  case RISCV::PseudoVLSE8_V_M1_MASK:
+  case RISCV::PseudoVLSE8_V_M2:
+  case RISCV::PseudoVLSE8_V_M2_MASK:
+  case RISCV::PseudoVLSE8_V_M4:
+  case RISCV::PseudoVLSE8_V_M4_MASK:
+  case RISCV::PseudoVLSE8_V_M8:
+  case RISCV::PseudoVLSE8_V_M8_MASK:
+  case RISCV::PseudoVLSE8_V_MF2:
+  case RISCV::PseudoVLSE8_V_MF2_MASK:
+  case RISCV::PseudoVLSE8_V_MF4:
+  case RISCV::PseudoVLSE8_V_MF4_MASK:
+  case RISCV::PseudoVLSE8_V_MF8:
+  case RISCV::PseudoVLSE8_V_MF8_MASK:
+  case RISCV::PseudoVSE8_V_M1:
+  case RISCV::PseudoVSE8_V_M1_MASK:
+  case RISCV::PseudoVSE8_V_M2:
+  case RISCV::PseudoVSE8_V_M2_MASK:
+  case RISCV::PseudoVSE8_V_M4:
+  case RISCV::PseudoVSE8_V_M4_MASK:
+  case RISCV::PseudoVSE8_V_M8:
+  case RISCV::PseudoVSE8_V_M8_MASK:
+  case RISCV::PseudoVSE8_V_MF2:
+  case RISCV::PseudoVSE8_V_MF2_MASK:
+  case RISCV::PseudoVSE8_V_MF4:
+  case RISCV::PseudoVSE8_V_MF4_MASK:
+  case RISCV::PseudoVSE8_V_MF8:
+  case RISCV::PseudoVSE8_V_MF8_MASK:
+  case RISCV::PseudoVSSE8_V_M1:
+  case RISCV::PseudoVSSE8_V_M1_MASK:
+  case RISCV::PseudoVSSE8_V_M2:
+  case RISCV::PseudoVSSE8_V_M2_MASK:
+  case RISCV::PseudoVSSE8_V_M4:
+  case RISCV::PseudoVSSE8_V_M4_MASK:
+  case RISCV::PseudoVSSE8_V_M8:
+  case RISCV::PseudoVSSE8_V_M8_MASK:
+  case RISCV::PseudoVSSE8_V_MF2:
+  case RISCV::PseudoVSSE8_V_MF2_MASK:
+  case RISCV::PseudoVSSE8_V_MF4:
+  case RISCV::PseudoVSSE8_V_MF4_MASK:
+  case RISCV::PseudoVSSE8_V_MF8:
+  case RISCV::PseudoVSSE8_V_MF8_MASK:
+    EEW = 8;
+    break;
+  case RISCV::PseudoVLE16_V_M1:
+  case RISCV::PseudoVLE16_V_M1_MASK:
+  case RISCV::PseudoVLE16_V_M2:
+  case RISCV::PseudoVLE16_V_M2_MASK:
+  case RISCV::PseudoVLE16_V_M4:
+  case RISCV::PseudoVLE16_V_M4_MASK:
+  case RISCV::PseudoVLE16_V_M8:
+  case RISCV::PseudoVLE16_V_M8_MASK:
+  case RISCV::PseudoVLE16_V_MF2:
+  case RISCV::PseudoVLE16_V_MF2_MASK:
+  case RISCV::PseudoVLE16_V_MF4:
+  case RISCV::PseudoVLE16_V_MF4_MASK:
+  case RISCV::PseudoVLSE16_V_M1:
+  case RISCV::PseudoVLSE16_V_M1_MASK:
+  case RISCV::PseudoVLSE16_V_M2:
+  case RISCV::PseudoVLSE16_V_M2_MASK:
+  case RISCV::PseudoVLSE16_V_M4:
+  case RISCV::PseudoVLSE16_V_M4_MASK:
+  case RISCV::PseudoVLSE16_V_M8:
+  case RISCV::PseudoVLSE16_V_M8_MASK:
+  case RISCV::PseudoVLSE16_V_MF2:
+  case RISCV::PseudoVLSE16_V_MF2_MASK:
+  case RISCV::PseudoVLSE16_V_MF4:
+  case RISCV::PseudoVLSE16_V_MF4_MASK:
+  case RISCV::PseudoVSE16_V_M1:
+  case RISCV::PseudoVSE16_V_M1_MASK:
+  case RISCV::PseudoVSE16_V_M2:
+  case RISCV::PseudoVSE16_V_M2_MASK:
+  case RISCV::PseudoVSE16_V_M4:
+  case RISCV::PseudoVSE16_V_M4_MASK:
+  case RISCV::PseudoVSE16_V_M8:
+  case RISCV::PseudoVSE16_V_M8_MASK:
+  case RISCV::PseudoVSE16_V_MF2:
+  case RISCV::PseudoVSE16_V_MF2_MASK:
+  case RISCV::PseudoVSE16_V_MF4:
+  case RISCV::PseudoVSE16_V_MF4_MASK:
+  case RISCV::PseudoVSSE16_V_M1:
+  case RISCV::PseudoVSSE16_V_M1_MASK:
+  case RISCV::PseudoVSSE16_V_M2:
+  case RISCV::PseudoVSSE16_V_M2_MASK:
+  case RISCV::PseudoVSSE16_V_M4:
+  case RISCV::PseudoVSSE16_V_M4_MASK:
+  case RISCV::PseudoVSSE16_V_M8:
+  case RISCV::PseudoVSSE16_V_M8_MASK:
+  case RISCV::PseudoVSSE16_V_MF2:
+  case RISCV::PseudoVSSE16_V_MF2_MASK:
+  case RISCV::PseudoVSSE16_V_MF4:
+  case RISCV::PseudoVSSE16_V_MF4_MASK:
+    EEW = 16;
+    break;
+  case RISCV::PseudoVLE32_V_M1:
+  case RISCV::PseudoVLE32_V_M1_MASK:
+  case RISCV::PseudoVLE32_V_M2:
+  case RISCV::PseudoVLE32_V_M2_MASK:
+  case RISCV::PseudoVLE32_V_M4:
+  case RISCV::PseudoVLE32_V_M4_MASK:
+  case RISCV::PseudoVLE32_V_M8:
+  case RISCV::PseudoVLE32_V_M8_MASK:
+  case RISCV::PseudoVLE32_V_MF2:
+  case RISCV::PseudoVLE32_V_MF2_MASK:
+  case RISCV::PseudoVLSE32_V_M1:
+  case RISCV::PseudoVLSE32_V_M1_MASK:
+  case RISCV::PseudoVLSE32_V_M2:
+  case RISCV::PseudoVLSE32_V_M2_MASK:
+  case RISCV::PseudoVLSE32_V_M4:
+  case RISCV::PseudoVLSE32_V_M4_MASK:
+  case RISCV::PseudoVLSE32_V_M8:
+  case RISCV::PseudoVLSE32_V_M8_MASK:
+  case RISCV::PseudoVLSE32_V_MF2:
+  case RISCV::PseudoVLSE32_V_MF2_MASK:
+  case RISCV::PseudoVSE32_V_M1:
+  case RISCV::PseudoVSE32_V_M1_MASK:
+  case RISCV::PseudoVSE32_V_M2:
+  case RISCV::PseudoVSE32_V_M2_MASK:
+  case RISCV::PseudoVSE32_V_M4:
+  case RISCV::PseudoVSE32_V_M4_MASK:
+  case RISCV::PseudoVSE32_V_M8:
+  case RISCV::PseudoVSE32_V_M8_MASK:
+  case RISCV::PseudoVSE32_V_MF2:
+  case RISCV::PseudoVSE32_V_MF2_MASK:
+  case RISCV::PseudoVSSE32_V_M1:
+  case RISCV::PseudoVSSE32_V_M1_MASK:
+  case RISCV::PseudoVSSE32_V_M2:
+  case RISCV::PseudoVSSE32_V_M2_MASK:
+  case RISCV::PseudoVSSE32_V_M4:
+  case RISCV::PseudoVSSE32_V_M4_MASK:
+  case RISCV::PseudoVSSE32_V_M8:
+  case RISCV::PseudoVSSE32_V_M8_MASK:
+  case RISCV::PseudoVSSE32_V_MF2:
+  case RISCV::PseudoVSSE32_V_MF2_MASK:
+    EEW = 32;
+    break;
+  case RISCV::PseudoVLE64_V_M1:
+  case RISCV::PseudoVLE64_V_M1_MASK:
+  case RISCV::PseudoVLE64_V_M2:
+  case RISCV::PseudoVLE64_V_M2_MASK:
+  case RISCV::PseudoVLE64_V_M4:
+  case RISCV::PseudoVLE64_V_M4_MASK:
+  case RISCV::PseudoVLE64_V_M8:
+  case RISCV::PseudoVLE64_V_M8_MASK:
+  case RISCV::PseudoVLSE64_V_M1:
+  case RISCV::PseudoVLSE64_V_M1_MASK:
+  case RISCV::PseudoVLSE64_V_M2:
+  case RISCV::PseudoVLSE64_V_M2_MASK:
+  case RISCV::PseudoVLSE64_V_M4:
+  case RISCV::PseudoVLSE64_V_M4_MASK:
+  case RISCV::PseudoVLSE64_V_M8:
+  case RISCV::PseudoVLSE64_V_M8_MASK:
+  case RISCV::PseudoVSE64_V_M1:
+  case RISCV::PseudoVSE64_V_M1_MASK:
+  case RISCV::PseudoVSE64_V_M2:
+  case RISCV::PseudoVSE64_V_M2_MASK:
+  case RISCV::PseudoVSE64_V_M4:
+  case RISCV::PseudoVSE64_V_M4_MASK:
+  case RISCV::PseudoVSE64_V_M8:
+  case RISCV::PseudoVSE64_V_M8_MASK:
+  case RISCV::PseudoVSSE64_V_M1:
+  case RISCV::PseudoVSSE64_V_M1_MASK:
+  case RISCV::PseudoVSSE64_V_M2:
+  case RISCV::PseudoVSSE64_V_M2_MASK:
+  case RISCV::PseudoVSSE64_V_M4:
+  case RISCV::PseudoVSSE64_V_M4_MASK:
+  case RISCV::PseudoVSSE64_V_M8:
+  case RISCV::PseudoVSSE64_V_M8_MASK:
+    EEW = 64;
+    break;
+  }
+
+  return CurInfo.isCompatibleWithLoadStoreEEW(EEW, Require);
+}
+
 bool RISCVInsertVSETVLI::computeVLVTYPEChanges(const MachineBasicBlock &MBB) {
   bool HadVectorOp = false;
 
@@ -539,7 +761,13 @@ bool RISCVInsertVSETVLI::computeVLVTYPEChanges(const MachineBasicBlock &MBB) {
       } else {
         // If this instruction isn't compatible with the previous VL/VTYPE
         // we need to insert a VSETVLI.
-        if (needVSETVLI(NewInfo, BBInfo.Change))
+        // If this is a unit-stride or strided load/store, we may be able to use
+        // the EMUL=(EEW/SEW)*LMUL relationship to avoid changing vtype.
+        // NOTE: We only do this if the vtype we're comparing against was
+        // created in this block. We need the first and third phase to treat
+        // the store the same way.
+        if (!canSkipVSETVLIForLoadStore(MI, NewInfo, BBInfo.Change) &&
+            needVSETVLI(NewInfo, BBInfo.Change))
           BBInfo.Change = NewInfo;
       }
     }
@@ -692,7 +920,13 @@ void RISCVInsertVSETVLI::emitVSETVLIs(MachineBasicBlock &MBB) {
       } else {
         // If this instruction isn't compatible with the previous VL/VTYPE
         // we need to insert a VSETVLI.
-        if (needVSETVLI(NewInfo, CurInfo)) {
+        // If this is a unit-stride or strided load/store, we may be able to use
+        // the EMUL=(EEW/SEW)*LMUL relationship to avoid changing vtype.
+        // NOTE: We can't use predecessor information for the store. We must
+        // treat it the same as the first phase so that we produce the correct
+        // vl/vtype for succesor blocks.
+        if (!canSkipVSETVLIForLoadStore(MI, NewInfo, CurInfo) &&
+            needVSETVLI(NewInfo, CurInfo)) {
           // If the previous VL/VTYPE is set by VSETVLI and do not use, Merge it
           // with current VL/VTYPE.
           bool NeedInsertVSETVLI = true;

diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-conv.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-conv.ll
index 7903075..91fa3c4 100644 (file)
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-conv.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-conv.ll
@@ -10,7 +10,6 @@ define void @fpext_v2f16_v2f32(<2 x half>* %x, <2 x float>* %y) {
 ; CHECK-NEXT:    vsetivli zero, 2, e16, mf4, ta, mu
 ; CHECK-NEXT:    vle16.v v25, (a0)
 ; CHECK-NEXT:    vfwcvt.f.f.v v26, v25
-; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vse32.v v26, (a1)
 ; CHECK-NEXT:    ret
   %a = load <2 x half>, <2 x half>* %x
@@ -27,7 +26,6 @@ define void @fpext_v2f16_v2f64(<2 x half>* %x, <2 x double>* %y) {
 ; CHECK-NEXT:    vfwcvt.f.f.v v26, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfwcvt.f.f.v v25, v26
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vse64.v v25, (a1)
 ; CHECK-NEXT:    ret
   %a = load <2 x half>, <2 x half>* %x
@@ -42,7 +40,6 @@ define void @fpext_v8f16_v8f32(<8 x half>* %x, <8 x float>* %y) {
 ; LMULMAX8-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
 ; LMULMAX8-NEXT:    vle16.v v25, (a0)
 ; LMULMAX8-NEXT:    vfwcvt.f.f.v v26, v25
-; LMULMAX8-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; LMULMAX8-NEXT:    vse32.v v26, (a1)
 ; LMULMAX8-NEXT:    ret
 ;
@@ -56,7 +53,6 @@ define void @fpext_v8f16_v8f32(<8 x half>* %x, <8 x float>* %y) {
 ; LMULMAX1-NEXT:    vfwcvt.f.f.v v27, v26
 ; LMULMAX1-NEXT:    vfwcvt.f.f.v v26, v25
 ; LMULMAX1-NEXT:    addi a0, a1, 16
-; LMULMAX1-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
 ; LMULMAX1-NEXT:    vse32.v v27, (a0)
 ; LMULMAX1-NEXT:    vse32.v v26, (a1)
 ; LMULMAX1-NEXT:    ret
@@ -74,7 +70,6 @@ define void @fpext_v8f16_v8f64(<8 x half>* %x, <8 x double>* %y) {
 ; LMULMAX8-NEXT:    vfwcvt.f.f.v v26, v25
 ; LMULMAX8-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
 ; LMULMAX8-NEXT:    vfwcvt.f.f.v v28, v26
-; LMULMAX8-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; LMULMAX8-NEXT:    vse64.v v28, (a1)
 ; LMULMAX8-NEXT:    ret
 ;
@@ -105,7 +100,6 @@ define void @fpext_v8f16_v8f64(<8 x half>* %x, <8 x double>* %y) {
 ; LMULMAX1-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; LMULMAX1-NEXT:    vfwcvt.f.f.v v25, v29
 ; LMULMAX1-NEXT:    addi a0, a1, 32
-; LMULMAX1-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; LMULMAX1-NEXT:    vse64.v v27, (a0)
 ; LMULMAX1-NEXT:    vse64.v v25, (a1)
 ; LMULMAX1-NEXT:    addi a0, a1, 48

diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-shuffles.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-shuffles.ll
index ced3d6d..0aa4397 100644 (file)
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-shuffles.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-shuffles.ll
@@ -172,12 +172,11 @@ define <4 x double> @vrgather_shuffle_xv_v4f64(<4 x double> %x) {
 ; RV32-NEXT:    vsetivli zero, 1, e8, mf8, ta, mu
 ; RV32-NEXT:    vmv.s.x v0, a0
 ; RV32-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
-; RV32-NEXT:    vid.v v25
-; RV32-NEXT:    vrsub.vi v25, v25, 4
 ; RV32-NEXT:    lui a0, %hi(.LCPI7_0)
 ; RV32-NEXT:    addi a0, a0, %lo(.LCPI7_0)
-; RV32-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
 ; RV32-NEXT:    vlse64.v v26, (a0), zero
+; RV32-NEXT:    vid.v v25
+; RV32-NEXT:    vrsub.vi v25, v25, 4
 ; RV32-NEXT:    vsetvli zero, zero, e64, m2, tu, mu
 ; RV32-NEXT:    vrgatherei16.vv v26, v8, v25, v0.t
 ; RV32-NEXT:    vmv2r.v v8, v26

diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp.ll
index a58488b..13f8a30 100644 (file)
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp.ll
@@ -437,12 +437,10 @@ define void @copysign_neg_trunc_v4f16_v4f32(<4 x half>* %x, <4 x float>* %y) {
 ; CHECK-LABEL: copysign_neg_trunc_v4f16_v4f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
-; CHECK-NEXT:    vle16.v v25, (a0)
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
-; CHECK-NEXT:    vle32.v v26, (a1)
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
-; CHECK-NEXT:    vfncvt.f.f.w v27, v26
-; CHECK-NEXT:    vfsgnjn.vv v25, v25, v27
+; CHECK-NEXT:    vle32.v v25, (a1)
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vfncvt.f.f.w v27, v25
+; CHECK-NEXT:    vfsgnjn.vv v25, v26, v27
 ; CHECK-NEXT:    vse16.v v25, (a0)
 ; CHECK-NEXT:    ret
   %a = load <4 x half>, <4 x half>* %x
@@ -459,12 +457,12 @@ define void @copysign_neg_ext_v2f64_v2f32(<2 x double>* %x, <2 x float>* %y) {
 ; CHECK-LABEL: copysign_neg_ext_v2f64_v2f32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, mu
-; CHECK-NEXT:    vle64.v v25, (a0)
+; CHECK-NEXT:    vle32.v v25, (a1)
+; CHECK-NEXT:    vle64.v v26, (a0)
 ; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
-; CHECK-NEXT:    vle32.v v26, (a1)
-; CHECK-NEXT:    vfwcvt.f.f.v v27, v26
+; CHECK-NEXT:    vfwcvt.f.f.v v27, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
-; CHECK-NEXT:    vfsgnjn.vv v25, v25, v27
+; CHECK-NEXT:    vfsgnjn.vv v25, v26, v27
 ; CHECK-NEXT:    vse64.v v25, (a0)
 ; CHECK-NEXT:    ret
   %a = load <2 x double>, <2 x double>* %x

diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i.ll
index fee37eb..1846ffb 100644 (file)
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i.ll
@@ -200,7 +200,6 @@ define void @fp2si_v2f32_v2i64(<2 x float>* %x, <2 x i64>* %y) {
 ; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
 ; CHECK-NEXT:    vle32.v v25, (a0)
 ; CHECK-NEXT:    vfwcvt.rtz.x.f.v v26, v25
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vse64.v v26, (a1)
 ; CHECK-NEXT:    ret
   %a = load <2 x float>, <2 x float>* %x
@@ -215,7 +214,6 @@ define void @fp2ui_v2f32_v2i64(<2 x float>* %x, <2 x i64>* %y) {
 ; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
 ; CHECK-NEXT:    vle32.v v25, (a0)
 ; CHECK-NEXT:    vfwcvt.rtz.xu.f.v v26, v25
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vse64.v v26, (a1)
 ; CHECK-NEXT:    ret
   %a = load <2 x float>, <2 x float>* %x
@@ -230,7 +228,6 @@ define void @fp2si_v8f32_v8i64(<8 x float>* %x, <8 x i64>* %y) {
 ; LMULMAX8-NEXT:    vsetivli zero, 8, e32, m2, ta, mu
 ; LMULMAX8-NEXT:    vle32.v v26, (a0)
 ; LMULMAX8-NEXT:    vfwcvt.rtz.x.f.v v28, v26
-; LMULMAX8-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; LMULMAX8-NEXT:    vse64.v v28, (a1)
 ; LMULMAX8-NEXT:    ret
 ;
@@ -251,7 +248,6 @@ define void @fp2si_v8f32_v8i64(<8 x float>* %x, <8 x i64>* %y) {
 ; LMULMAX1-NEXT:    vfwcvt.rtz.x.f.v v27, v25
 ; LMULMAX1-NEXT:    vfwcvt.rtz.x.f.v v25, v26
 ; LMULMAX1-NEXT:    addi a0, a1, 16
-; LMULMAX1-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; LMULMAX1-NEXT:    vse64.v v29, (a0)
 ; LMULMAX1-NEXT:    vse64.v v25, (a1)
 ; LMULMAX1-NEXT:    addi a0, a1, 48
@@ -271,7 +267,6 @@ define void @fp2ui_v8f32_v8i64(<8 x float>* %x, <8 x i64>* %y) {
 ; LMULMAX8-NEXT:    vsetivli zero, 8, e32, m2, ta, mu
 ; LMULMAX8-NEXT:    vle32.v v26, (a0)
 ; LMULMAX8-NEXT:    vfwcvt.rtz.xu.f.v v28, v26
-; LMULMAX8-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
 ; LMULMAX8-NEXT:    vse64.v v28, (a1)
 ; LMULMAX8-NEXT:    ret
 ;
@@ -292,7 +287,6 @@ define void @fp2ui_v8f32_v8i64(<8 x float>* %x, <8 x i64>* %y) {
 ; LMULMAX1-NEXT:    vfwcvt.rtz.xu.f.v v27, v25
 ; LMULMAX1-NEXT:    vfwcvt.rtz.xu.f.v v25, v26
 ; LMULMAX1-NEXT:    addi a0, a1, 16
-; LMULMAX1-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; LMULMAX1-NEXT:    vse64.v v29, (a0)
 ; LMULMAX1-NEXT:    vse64.v v25, (a1)
 ; LMULMAX1-NEXT:    addi a0, a1, 48
@@ -314,7 +308,6 @@ define void @fp2si_v2f16_v2i64(<2 x half>* %x, <2 x i64>* %y) {
 ; CHECK-NEXT:    vfwcvt.f.f.v v26, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfwcvt.rtz.x.f.v v25, v26
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vse64.v v25, (a1)
 ; CHECK-NEXT:    ret
   %a = load <2 x half>, <2 x half>* %x
@@ -331,7 +324,6 @@ define void @fp2ui_v2f16_v2i64(<2 x half>* %x, <2 x i64>* %y) {
 ; CHECK-NEXT:    vfwcvt.f.f.v v26, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
 ; CHECK-NEXT:    vfwcvt.rtz.xu.f.v v25, v26
-; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
 ; CHECK-NEXT:    vse64.v v25, (a1)
 ; CHECK-NEXT:    ret
   %a = load <2 x half>, <2 x half>* %x

diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmul.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmul.ll
index eb5cfd1..58395e2 100644 (file)
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmul.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmul.ll
@@ -376,8 +376,8 @@ define <4 x i32> @vwmul_v4i32_v4i8_v4i16(<4 x i8>* %x, <4 x i16>* %y) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, mu
 ; CHECK-NEXT:    vle8.v v25, (a0)
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vsext.vf2 v27, v25
 ; CHECK-NEXT:    vwmul.vv v8, v27, v26
 ; CHECK-NEXT:    ret
@@ -393,12 +393,10 @@ define <4 x i64> @vwmul_v4i64_v4i32_v4i8(<4 x i32>* %x, <4 x i8>* %y) {
 ; CHECK-LABEL: vwmul_v4i64_v4i32_v4i8:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
-; CHECK-NEXT:    vle32.v v25, (a0)
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf4, ta, mu
-; CHECK-NEXT:    vle8.v v26, (a1)
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
-; CHECK-NEXT:    vsext.vf4 v27, v26
-; CHECK-NEXT:    vwmul.vv v8, v25, v27
+; CHECK-NEXT:    vle8.v v25, (a1)
+; CHECK-NEXT:    vle32.v v26, (a0)
+; CHECK-NEXT:    vsext.vf4 v27, v25
+; CHECK-NEXT:    vwmul.vv v8, v26, v27
 ; CHECK-NEXT:    ret
   %a = load <4 x i32>, <4 x i32>* %x
   %b = load <4 x i8>, <4 x i8>* %y

diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmulu.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmulu.ll
index 90b0113..5c95f9f 100644 (file)
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmulu.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmulu.ll
@@ -376,8 +376,8 @@ define <4 x i32> @vwmulu_v4i32_v4i8_v4i16(<4 x i8>* %x, <4 x i16>* %y) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, mu
 ; CHECK-NEXT:    vle8.v v25, (a0)
-; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
 ; CHECK-NEXT:    vzext.vf2 v27, v25
 ; CHECK-NEXT:    vwmulu.vv v8, v27, v26
 ; CHECK-NEXT:    ret
@@ -393,12 +393,10 @@ define <4 x i64> @vwmulu_v4i64_v4i32_v4i8(<4 x i32>* %x, <4 x i8>* %y) {
 ; CHECK-LABEL: vwmulu_v4i64_v4i32_v4i8:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
-; CHECK-NEXT:    vle32.v v25, (a0)
-; CHECK-NEXT:    vsetvli zero, zero, e8, mf4, ta, mu
-; CHECK-NEXT:    vle8.v v26, (a1)
-; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
-; CHECK-NEXT:    vzext.vf4 v27, v26
-; CHECK-NEXT:    vwmulu.vv v8, v25, v27
+; CHECK-NEXT:    vle8.v v25, (a1)
+; CHECK-NEXT:    vle32.v v26, (a0)
+; CHECK-NEXT:    vzext.vf4 v27, v25
+; CHECK-NEXT:    vwmulu.vv v8, v26, v27
 ; CHECK-NEXT:    ret
   %a = load <4 x i32>, <4 x i32>* %x
   %b = load <4 x i8>, <4 x i8>* %y