Optimizing: Add direct calls to math intrinsics
Support the double forms of:
cos, sin, acos, asin, atan, atan2, cbrt, cosh, exp, expm1,
hypot, log, log10, nextAfter, sinh, tan, tanh
Add these entries to the vector addressed off the thread pointer. Call
the libc routines directly, which means that we have to implement the
native ABI, not the ART one. For x86_64, that includes saving XMM12-15
as the native ABI considers them caller-save, while the ART ABI
considers them callee-save. We save them by marking them as used by the
call to the math function. For x86, this is not an issue, as all the XMM
registers are caller-save.
Other architectures will call Java as before until they are ready to
implement the new intrinsics.
Bump the OAT version since we are incompatible with old boot.oat files.
Change-Id: Ic6332c3555c09393a17d1ad4daf62932488722fb
Signed-off-by: Mark Mendell <mark.p.mendell@intel.com>
diff --git a/compiler/optimizing/code_generator_x86_64.h b/compiler/optimizing/code_generator_x86_64.h
index 145b1f3..7351fed 100644
--- a/compiler/optimizing/code_generator_x86_64.h
+++ b/compiler/optimizing/code_generator_x86_64.h
@@ -47,6 +47,12 @@
static constexpr size_t kRuntimeParameterFpuRegistersLength =
arraysize(kRuntimeParameterFpuRegisters);
+// These XMM registers are non-volatile in ART ABI, but volatile in native ABI.
+// If the ART ABI changes, this list must be updated. It is used to ensure that
+// these are not clobbered by any direct call to native code (such as math intrinsics).
+static constexpr FloatRegister non_volatile_xmm_regs[] = { XMM12, XMM13, XMM14, XMM15 };
+
+
class InvokeRuntimeCallingConvention : public CallingConvention<Register, FloatRegister> {
public:
InvokeRuntimeCallingConvention()