[wasm]implement simd lowering for simple F32x4 and I32x4 unops

src/compiler/wasm-compiler.cc

 // Copyright 2015 the V8 project authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 #include "src/compiler/wasm-compiler.h"
 
 #include <memory>
 
 #include "src/assembler-inl.h"
 #include "src/base/platform/elapsed-timer.h"
@@ skipping 3365 matching lines @@
     case wasm::kExprF32x4SConvertI32x4:
       return graph()->NewNode(jsgraph()->machine()->Float32x4FromInt32x4(),
                               inputs[0]);
     case wasm::kExprF32x4UConvertI32x4:
       return graph()->NewNode(jsgraph()->machine()->Float32x4FromUint32x4(),
                               inputs[0]);
     case wasm::kExprF32x4Abs:
       return graph()->NewNode(jsgraph()->machine()->Float32x4Abs(), inputs[0]);
     case wasm::kExprF32x4Neg:
       return graph()->NewNode(jsgraph()->machine()->Float32x4Neg(), inputs[0]);
+    case wasm::kExprF32x4Sqrt:
+      return graph()->NewNode(jsgraph()->machine()->Float32x4Sqrt(), inputs[0]);

[bbudge, 2017/03/01 17:36:42]

We're rethinking sqrt support. On some platforms (ARM32) this has to be
simulated by a very slow sequence of scalar square root instructions which can't
be rescheduled. Users would be much better off using the recip and rsqrt
approximation and refinement operations instead, since they can schedule those
to avoid stalls.

     case wasm::kExprF32x4Add:
       return graph()->NewNode(jsgraph()->machine()->Float32x4Add(), inputs[0],
                               inputs[1]);
     case wasm::kExprF32x4Sub:
       return graph()->NewNode(jsgraph()->machine()->Float32x4Sub(), inputs[0],
                               inputs[1]);
     case wasm::kExprF32x4Mul:
       return graph()->NewNode(jsgraph()->machine()->Float32x4Mul(), inputs[0],
                               inputs[1]);
     case wasm::kExprF32x4Div:
@@ skipping 767 matching lines @@
            function_->code_end_offset - function_->code_start_offset,
            codegen_ms);
   }
 
   return code;
 }
 
 }  // namespace compiler
 }  // namespace internal
 }  // namespace v8