[optimizing] Implement x86/x86_64 math intrinsics
Implement floor/ceil/round/RoundFloat on x86 and x86_64.
Implement RoundDouble on x86_64.
Add support for roundss and roundsd on both architectures. Support them
in the disassembler as well.
Add the instruction set features for x86, as the 'round' instruction is
only supported if SSE4.1 is supported.
Fix the tests to handle the addition of passing the instruction set
features to x86 and x86_64.
Add assembler tests for roundsd and roundss to x86_64 assembler tests.
Change-Id: I9742d5930befb0bbc23f3d6c83ce0183ed9fe04f
Signed-off-by: Mark Mendell <mark.p.mendell@intel.com>
diff --git a/compiler/optimizing/code_generator_x86.h b/compiler/optimizing/code_generator_x86.h
index 6a4d42d..7cdbd62 100644
--- a/compiler/optimizing/code_generator_x86.h
+++ b/compiler/optimizing/code_generator_x86.h
@@ -185,7 +185,9 @@
class CodeGeneratorX86 : public CodeGenerator {
public:
- CodeGeneratorX86(HGraph* graph, const CompilerOptions& compiler_options);
+ CodeGeneratorX86(HGraph* graph,
+ const X86InstructionSetFeatures& isa_features,
+ const CompilerOptions& compiler_options);
virtual ~CodeGeneratorX86() {}
void GenerateFrameEntry() OVERRIDE;
@@ -271,6 +273,10 @@
Label* GetFrameEntryLabel() { return &frame_entry_label_; }
+ const X86InstructionSetFeatures& GetInstructionSetFeatures() const {
+ return isa_features_;
+ }
+
private:
// Labels for each block that will be compiled.
GrowableArray<Label> block_labels_;
@@ -279,6 +285,7 @@
InstructionCodeGeneratorX86 instruction_visitor_;
ParallelMoveResolverX86 move_resolver_;
X86Assembler assembler_;
+ const X86InstructionSetFeatures& isa_features_;
DISALLOW_COPY_AND_ASSIGN(CodeGeneratorX86);
};