[WebAssembly] Handle undefined lane indices in SIMD patterns

Summary:
Undefined indices in shuffles can be used when not all lanes of the
output vector will be used. This happens for example in the expansion
of vector reduce operations. Regardless, undefs are legal as lane
indices in IR and should be supported.

Reviewers: aheejin, dschuff

Subscribers: sbc100, jgravelle-google, sunfish, llvm-commits

Differential Revision: https://reviews.llvm.org/D53057

llvm-svn: 344803

2 files changed, 40 insertions, 2 deletions

diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp
index 30c2e843408..6ca619c910a 100644
--- a/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp
@@ -990,8 +990,10 @@ WebAssemblyTargetLowering::LowerVECTOR_SHUFFLE(SDValue Op,
   // Expand mask indices to byte indices and materialize them as operands
   for (size_t I = 0, Lanes = Mask.size(); I < Lanes; ++I) {
     for (size_t J = 0; J < LaneBytes; ++J) {
-      Ops[OpIdx++] =
-          DAG.getConstant((uint64_t)Mask[I] * LaneBytes + J, DL, MVT::i32);
+      // Lower undefs (represented by -1 in mask) to zero
+      uint64_t ByteIndex =
+          Mask[I] == -1 ? 0 : (uint64_t)Mask[I] * LaneBytes + J;
+      Ops[OpIdx++] = DAG.getConstant(ByteIndex, DL, MVT::i32);
     }
   }
 
diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyInstrSIMD.td b/llvm/lib/Target/WebAssembly/WebAssemblyInstrSIMD.td
index b0fd6cab229..95c87266273 100644
--- a/llvm/lib/Target/WebAssembly/WebAssemblyInstrSIMD.td
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyInstrSIMD.td
@@ -181,6 +181,28 @@ def : Pat<(i32 (vector_extract (v16i8 V128:$vec), (i32 LaneIdx16:$idx))),
 def : Pat<(i32 (vector_extract (v8i16 V128:$vec), (i32 LaneIdx8:$idx))),
           (EXTRACT_LANE_v8i16_u V128:$vec, (i32 LaneIdx8:$idx))>;
 
+// Lower undef lane indices to zero
+def : Pat<(and (i32 (vector_extract (v16i8 V128:$vec), undef)), (i32 0xff)),
+          (EXTRACT_LANE_v16i8_u V128:$vec, 0)>;
+def : Pat<(and (i32 (vector_extract (v8i16 V128:$vec), undef)), (i32 0xffff)),
+          (EXTRACT_LANE_v8i16_u V128:$vec, 0)>;
+def : Pat<(i32 (vector_extract (v16i8 V128:$vec), undef)),
+          (EXTRACT_LANE_v16i8_u V128:$vec, 0)>;
+def : Pat<(i32 (vector_extract (v8i16 V128:$vec), undef)),
+          (EXTRACT_LANE_v8i16_u V128:$vec, 0)>;
+def : Pat<(sext_inreg (i32 (vector_extract (v16i8 V128:$vec), undef)), i8),
+          (EXTRACT_LANE_v16i8_s V128:$vec, 0)>;
+def : Pat<(sext_inreg (i32 (vector_extract (v8i16 V128:$vec), undef)), i16),
+          (EXTRACT_LANE_v8i16_s V128:$vec, 0)>;
+def : Pat<(vector_extract (v4i32 V128:$vec), undef),
+          (EXTRACT_LANE_v4i32 V128:$vec, 0)>;
+def : Pat<(vector_extract (v2i64 V128:$vec), undef),
+          (EXTRACT_LANE_v2i64 V128:$vec, 0)>;
+def : Pat<(vector_extract (v4f32 V128:$vec), undef),
+          (EXTRACT_LANE_v4f32 V128:$vec, 0)>;
+def : Pat<(vector_extract (v2f64 V128:$vec), undef),
+          (EXTRACT_LANE_v2f64 V128:$vec, 0)>;
+
 // Replace lane value: replace_lane
 multiclass ReplaceLane<ValueType vec_t, string vec, ImmLeaf imm_t,
                        WebAssemblyRegClass reg_t, ValueType lane_t,
@@ -201,6 +223,20 @@ defm "" : ReplaceLane<v2i64, "i64x2", LaneIdx2, I64, i64, 20>;
 defm "" : ReplaceLane<v4f32, "f32x4", LaneIdx4, F32, f32, 21>;
 defm "" : ReplaceLane<v2f64, "f64x2", LaneIdx2, F64, f64, 22>;
 
+// Lower undef lane indices to zero
+def : Pat<(vector_insert (v16i8 V128:$vec), I32:$x, undef),
+          (REPLACE_LANE_v16i8 V128:$vec, 0, I32:$x)>;
+def : Pat<(vector_insert (v8i16 V128:$vec), I32:$x, undef),
+          (REPLACE_LANE_v8i16 V128:$vec, 0, I32:$x)>;
+def : Pat<(vector_insert (v4i32 V128:$vec), I32:$x, undef),
+          (REPLACE_LANE_v4i32 V128:$vec, 0, I32:$x)>;
+def : Pat<(vector_insert (v2i64 V128:$vec), I64:$x, undef),
+          (REPLACE_LANE_v2i64 V128:$vec, 0, I64:$x)>;
+def : Pat<(vector_insert (v4f32 V128:$vec), F32:$x, undef),
+          (REPLACE_LANE_v4f32 V128:$vec, 0, F32:$x)>;
+def : Pat<(vector_insert (v2f64 V128:$vec), F64:$x, undef),
+          (REPLACE_LANE_v2f64 V128:$vec, 0, F64:$x)>;
+
 // Arbitrary other BUILD_VECTOR patterns
 def : Pat<(v16i8 (build_vector
             (i32 I32:$x0), (i32 I32:$x1), (i32 I32:$x2), (i32 I32:$x3),