Inline IRT frame push/pop into JNI stubs.
Golem results for art-opt-cc (higher is better):
linux-ia32 before after
NativeDowncallStaticNormal 25.704 26.839 (+4.414%)
NativeDowncallStaticNormal6 23.857 25.086 (+5.152%)
NativeDowncallStaticNormalRefs6 23.704 25.248 (+6.513%)
NativeDowncallVirtualNormal 25.578 27.000 (+5.560%)
NativeDowncallVirtualNormal6 23.704 24.925 (+5.153%)
NativeDowncallVirtualNormalRefs6 23.704 25.074 (+5.870%)
NativeDowncallStaticFast 100.65 149.13 (+48.17%)
NativeDowncallStaticFast6 78.304 107.39 (+37.71%)
NativeDowncallStaticFastRefs6 76.962 104.45 (+35.71%)
NativeDowncallVirtualFast 100.40 147.28 (+46.69%)
NativeDowncallVirtualFast6 79.302 106.34 (+34.10%)
NativeDowncallVirtualFastRef26 76.617 103.29 (+34.82%)
linux-x64 before after
NativeDowncallStaticNormal 26.083 26.987 (+3.465%)
NativeDowncallStaticNormal6 24.606 25.411 (+3.271%)
NativeDowncallStaticNormalRefs6 24.150 25.086 (+3.877%)
NativeDowncallVirtualNormal 25.743 26.812 (+4.156%)
NativeDowncallVirtualNormal6 24.294 25.248 (+3.927%)
NativeDowncallVirtualNormalRefs6 23.857 25.086 (+5.152%)
NativeDowncallStaticFast 109.95 133.10 (+21.06%)
NativeDowncallStaticFast6 90.274 109.12 (+20.87%)
NativeDowncallStaticFastRefs6 87.282 105.29 (+20.63%)
NativeDowncallVirtualFast 104.00 127.55 (+22.65%)
NativeDowncallVirtualFast6 88.191 106.73 (+21.02%)
NativeDowncallVirtualFastRef26 85.530 102.09 (+19.36%)
linux-armv7 before after
NativeDowncallStaticNormal 6.1148 6.3694 (+4.316%)
NativeDowncallStaticNormal6 5.6845 5.9026 (+3.837%)
NativeDowncallStaticNormalRefs6 5.4054 5.6022 (+3.641%)
NativeDowncallVirtualNormal 5.4726 5.7088 (+4.316%)
NativeDowncallVirtualNormal6 5.1789 5.3685 (+3.660%)
NativeDowncallVirtualNormalRefs6 4.9140 5.0902 (+3.586%)
NativeDowncallStaticFast 16.683 18.058 (+8.239%)
NativeDowncallStaticFast6 13.951 14.896 (+6.770%)
NativeDowncallStaticFastRefs6 12.279 13.006 (+5.919%)
NativeDowncallVirtualFast 16.161 17.848 (+10.44%)
NativeDowncallVirtualFast6 14.085 15.196 (+7.892%)
NativeDowncallVirtualFastRef26 12.089 12.897 (+6.683%)
linux-armv8 before after
NativeDowncallStaticNormal 6.0663 6.4229 (+5.879%)
NativeDowncallStaticNormal6 5.7252 6.0437 (+5.563%)
NativeDowncallStaticNormalRefs6 5.3114 5.5814 (+5.082%)
NativeDowncallVirtualNormal 5.8795 6.2651 (+6.558%)
NativeDowncallVirtualNormal6 5.6232 5.9494 (+5.801%)
NativeDowncallVirtualNormalRefs6 5.1862 5.4429 (+4.948%)
NativeDowncallStaticFast 17.638 19.183 (+8.760%)
NativeDowncallStaticFast6 14.903 16.161 (+8.438%)
NativeDowncallStaticFastRefs6 12.475 13.235 (+6.094%)
NativeDowncallVirtualFast 15.826 17.848 (+12.78%)
NativeDowncallVirtualFast6 14.064 15.504 (+10.24%)
NativeDowncallVirtualFastRef26 11.628 12.475 (+7.285%)
Test: m test-art-host-gtest
Test: testrunner.py --host --optimizing
Test: run-gtests.sh
Test: testrunner.py --target --optimizing
Bug: 172332525
Change-Id: I5ecfa7a661f08ab63dd2a75d666e1c1b9121935f
diff --git a/compiler/utils/x86/jni_macro_assembler_x86.h b/compiler/utils/x86/jni_macro_assembler_x86.h
index 448a7f4..1f9355a 100644
--- a/compiler/utils/x86/jni_macro_assembler_x86.h
+++ b/compiler/utils/x86/jni_macro_assembler_x86.h
@@ -54,8 +54,11 @@
void IncreaseFrameSize(size_t adjust) override;
void DecreaseFrameSize(size_t adjust) override;
+ ManagedRegister CoreRegisterWithSize(ManagedRegister src, size_t size) override;
+
// Store routines
void Store(FrameOffset offs, ManagedRegister src, size_t size) override;
+ void Store(ManagedRegister base, MemberOffset offs, ManagedRegister src, size_t size) override;
void StoreRef(FrameOffset dest, ManagedRegister src) override;
void StoreRawPtr(FrameOffset dest, ManagedRegister src) override;
@@ -69,6 +72,7 @@
// Load routines
void Load(ManagedRegister dest, FrameOffset src, size_t size) override;
+ void Load(ManagedRegister dest, ManagedRegister base, MemberOffset offs, size_t size) override;
void LoadFromThread(ManagedRegister dest, ThreadOffset32 src, size_t size) override;