ART: Add entrypoint and intrinsic for Math.pow().

MathBenchmarks.java#timePow results on taimen's little cores
fixed at frequency 1401600 with forced JIT compilation:
  - before:
    - X32: 356.33 (@FastNative), 315.39 (@CriticalNative)
    - X64: 357.31 (@FastNative), 315.37 (@CriticalNative)
  - after (LICM defeats the benchmark):
    - X32: 2.88
    - X64: 2.87
  - after but with kAllSideEffects to prevent LICM:
    - X32: 275.42
    - X64: 275.67

Test: Rely on TreeHugger.
Bug: 70727450
Change-Id: Iaa31f70acabbd57c163cfeafe02eed67c1348861

1 files changed, 9 insertions, 0 deletions

diff --git a/compiler/optimizing/intrinsics_mips.cc b/compiler/optimizing/intrinsics_mips.cc
index 113c9de5a2..cafa5228d9 100644
--- a/compiler/optimizing/intrinsics_mips.cc
+++ b/compiler/optimizing/intrinsics_mips.cc
@@ -2835,6 +2835,15 @@ void IntrinsicCodeGeneratorMIPS::VisitMathAtan2(HInvoke* invoke) {
   GenFPFPToFPCall(invoke, codegen_, kQuickAtan2);
 }
 
+// static double java.lang.Math.pow(double y, double x)
+void IntrinsicLocationsBuilderMIPS::VisitMathPow(HInvoke* invoke) {
+  CreateFPFPToFPCallLocations(allocator_, invoke);
+}
+
+void IntrinsicCodeGeneratorMIPS::VisitMathPow(HInvoke* invoke) {
+  GenFPFPToFPCall(invoke, codegen_, kQuickPow);
+}
+
 // static double java.lang.Math.cbrt(double a)
 void IntrinsicLocationsBuilderMIPS::VisitMathCbrt(HInvoke* invoke) {
   CreateFPToFPCallLocations(allocator_, invoke);