Fix math.round with SSE4.1.

src/x64/lithium-codegen-x64.cc

 // Copyright 2013 the V8 project authors. All rights reserved.
 // Redistribution and use in source and binary forms, with or without
 // modification, are permitted provided that the following conditions are
 // met:
 //
 //     * Redistributions of source code must retain the above copyright
 //       notice, this list of conditions and the following disclaimer.
 //     * Redistributions in binary form must reproduce the above
 //       copyright notice, this list of conditions and the following
 //       disclaimer in the documentation and/or other materials provided
@@ skipping 3525 matching lines @@
 
   bool minus_zero_check =
       instr->hydrogen()->CheckFlag(HValue::kBailoutOnMinusZero);
 
   __ movq(kScratchRegister, one_half, RelocInfo::NONE64);
   __ movq(xmm_scratch, kScratchRegister);
 
   if (CpuFeatures::IsSupported(SSE4_1) && !minus_zero_check) {
     CpuFeatures::Scope scope(SSE4_1);
     __ addsd(xmm_scratch, input_reg);
-    __ roundsd(xmm_scratch, input_reg, Assembler::kRoundDown);
+    __ roundsd(xmm_scratch, xmm_scratch, Assembler::kRoundDown);
     __ cvttsd2si(output_reg, xmm_scratch);
     // Overflow is signalled with minint.
     __ cmpl(output_reg, Immediate(0x80000000));
     __ RecordComment("D2I conversion overflow");
     DeoptimizeIf(equal, instr->environment());
   } else {
     Label done, round_to_zero, below_one_half, do_not_compensate;
     __ ucomisd(xmm_scratch, input_reg);
     __ j(above, &below_one_half);
 
@@ skipping 2265 matching lines @@
                                FixedArray::kHeaderSize - kPointerSize));
   __ bind(&done);
 }
 
 
 #undef __
 
 } }  // namespace v8::internal
 
 #endif  // V8_TARGET_ARCH_X64