[WebAssembly] Optimize convert_iKxN_u into convert_iKxN_s

convert_iKxN_s is canonicalized into convert_iKxN_u when the argument is
known to have sign bit 0. This results in emitting Wasm opcodes that, on
some targets (like x86_64), are dramatically slower than signed versions
on major engines.

Similarly to X86, we now fix this up in isel when the instruction has
nonneg flag from canonicalization or if we know the source has zero sign
bit.

Author: zeux

llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp

@@ -2934,6 +2934,25 @@ performVectorExtendToFPCombine(SDNode *N,
   return DAG.getNode(N->getOpcode(), SDLoc(N), ResVT, Conv);
 }
 
+static SDValue
+performVectorNonNegToFPCombine(SDNode *N,
+                               TargetLowering::DAGCombinerInfo &DCI) {
+  auto &DAG = DCI.DAG;
+
+  SDNodeFlags Flags = N->getFlags();
+  SDValue Op0 = N->getOperand(0);
+  EVT VT = N->getValueType(0);
+
+  // Optimize uitofp to sitofp when the sign bit is known to be zero.
+  // Depending on the target (runtime) backend, this might be performance
+  // neutral (e.g. AArch64) or a significant improvement (e.g. x86_64).
+  if (VT.isVector() && (Flags.hasNonNeg() || DAG.SignBitIsZero(Op0))) {
+    return DAG.getNode(ISD::SINT_TO_FP, SDLoc(N), VT, Op0);
+  }
+
+  return SDValue();
+}
+
 static SDValue
 performVectorExtendCombine(SDNode *N, TargetLowering::DAGCombinerInfo &DCI) {
   auto &DAG = DCI.DAG;
@@ -3515,6 +3534,9 @@ WebAssemblyTargetLowering::PerformDAGCombine(SDNode *N,
   case ISD::ZERO_EXTEND:
     return performVectorExtendCombine(N, DCI);
   case ISD::UINT_TO_FP:
+    if (auto ExtCombine = performVectorExtendToFPCombine(N, DCI))
+      return ExtCombine;
+    return performVectorNonNegToFPCombine(N, DCI);
   case ISD::SINT_TO_FP:
     return performVectorExtendToFPCombine(N, DCI);
   case ISD::FP_TO_SINT_SAT:

llvm/test/CodeGen/WebAssembly/simd-conversions.ll

@@ -441,3 +441,31 @@ define <2 x double> @promote_mixed_v2f64(<4 x float> %x, <4 x float> %y) {
   %a = fpext <2 x float> %v to <2 x double>
   ret <2 x double> %a
 }
+
+define <4 x float> @convert_u_v4f32_maybeneg(<4 x i32> %x) {
+; CHECK-LABEL: convert_u_v4f32_maybeneg:
+; CHECK:         .functype convert_u_v4f32_maybeneg (v128) -> (v128)
+; CHECK-NEXT:  # %bb.0:
+; CHECK-NEXT:    local.get 0
+; CHECK-NEXT:    i32.const 1
+; CHECK-NEXT:    i32x4.shr_s
+; CHECK-NEXT:    f32x4.convert_i32x4_u
+; CHECK-NEXT:    # fallthrough-return
+  %a = ashr <4 x i32> %x, <i32 1, i32 1, i32 1, i32 1>
+  %b = uitofp <4 x i32> %a to <4 x float>
+  ret <4 x float> %b
+}
+
+define <4 x float> @convert_u_v4f32_nonneg(<4 x i32> %x) {
+; CHECK-LABEL: convert_u_v4f32_nonneg:
+; CHECK:         .functype convert_u_v4f32_nonneg (v128) -> (v128)
+; CHECK-NEXT:  # %bb.0:
+; CHECK-NEXT:    local.get 0
+; CHECK-NEXT:    i32.const 1
+; CHECK-NEXT:    i32x4.shr_u
+; CHECK-NEXT:    f32x4.convert_i32x4_s
+; CHECK-NEXT:    # fallthrough-return
+  %a = lshr <4 x i32> %x, <i32 1, i32 1, i32 1, i32 1>
+  %b = uitofp <4 x i32> %a to <4 x float>
+  ret <4 x float> %b
+}

llvm/test/CodeGen/WebAssembly/simd-extending-convert.ll

@@ -12,7 +12,7 @@ define <4 x float> @extend_to_float_low_i16x8_u(<8 x i16> %x) {
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    local.get 0
 ; CHECK-NEXT:    i32x4.extend_low_i16x8_u
-; CHECK-NEXT:    f32x4.convert_i32x4_u
+; CHECK-NEXT:    f32x4.convert_i32x4_s
 ; CHECK-NEXT:    # fallthrough-return
   %low = shufflevector <8 x i16> %x, <8 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
   %extended = uitofp <4 x i16> %low to <4 x float>
@@ -25,7 +25,7 @@ define <4 x float> @extend_to_float_high_i16x8_u(<8 x i16> %x) {
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    local.get 0
 ; CHECK-NEXT:    i32x4.extend_high_i16x8_u
-; CHECK-NEXT:    f32x4.convert_i32x4_u
+; CHECK-NEXT:    f32x4.convert_i32x4_s
 ; CHECK-NEXT:    # fallthrough-return
   %high = shufflevector <8 x i16> %x, <8 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   %extended = uitofp <4 x i16> %high to <4 x float>
@@ -39,7 +39,7 @@ define <4 x float> @extend_to_float_low_i8x16_u(<8 x i8> %x) {
 ; CHECK-NEXT:    local.get 0
 ; CHECK-NEXT:    i16x8.extend_low_i8x16_u
 ; CHECK-NEXT:    i32x4.extend_low_i16x8_u
-; CHECK-NEXT:    f32x4.convert_i32x4_u
+; CHECK-NEXT:    f32x4.convert_i32x4_s
 ; CHECK-NEXT:    # fallthrough-return
   %low = shufflevector <8 x i8> %x, <8 x i8> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
   %extended = uitofp <4 x i8> %low to <4 x float>
@@ -55,7 +55,7 @@ define <4 x float> @extend_to_float_high_i8x16_u(<8 x i8> %x) {
 ; CHECK-NEXT:    i8x16.shuffle 4, 5, 6, 7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
 ; CHECK-NEXT:    i16x8.extend_low_i8x16_u
 ; CHECK-NEXT:    i32x4.extend_low_i16x8_u
-; CHECK-NEXT:    f32x4.convert_i32x4_u
+; CHECK-NEXT:    f32x4.convert_i32x4_s
 ; CHECK-NEXT:    # fallthrough-return
   %high = shufflevector <8 x i8> %x, <8 x i8> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   %extended = uitofp <4 x i8> %high to <4 x float>
@@ -136,7 +136,7 @@ define <2 x double> @extend_to_double_low_i16x4_u(<4 x i16> %x) {
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    local.get 0
 ; CHECK-NEXT:    i32x4.extend_low_i16x8_u
-; CHECK-NEXT:    f64x2.convert_low_i32x4_u
+; CHECK-NEXT:    f64x2.convert_low_i32x4_s
 ; CHECK-NEXT:    # fallthrough-return
   %low = shufflevector <4 x i16> %x, <4 x i16> undef, <2 x i32> <i32 0, i32 1>
   %extended = uitofp <2 x i16> %low to <2 x double>