commit f8425340e429c361e73326d610077305e1b6838d
author Evandro Menezes <e.menezes@samsung.com> Tue May 29 15:58:50 2018 +0000
committer Evandro Menezes <e.menezes@samsung.com> Tue May 29 15:58:50 2018 +0000
tree d26bcf96bd24563fd90b5d341a4b06abee76e540
parent 69301c9eb9c895ff851be4be6a2e4cfe7ff4e0b4

[AArch64] Fix PR32384: bump up the number of stores per memset and memcpy

As suggested in https://bugs.llvm.org/show_bug.cgi?id=32384#c1, this change
makes the inlining of `memset()` and `memcpy()` more aggressive when
compiling for speed.  The tuning remains the same when optimizing for size.

Patch by: Sebastian Pop <s.pop@samsung.com>
          Evandro Menezes <e.menezes@samsung.com>

Differential revision: https://reviews.llvm.org/D45098

llvm-svn: 333429

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index 5bf5231..66f1b63 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -579,11 +579,17 @@
 
   setTargetDAGCombine(ISD::GlobalAddress);
 
-  MaxStoresPerMemset = MaxStoresPerMemsetOptSize = 8;
-  MaxGluedStoresPerMemcpy = 4;
+  // In case of strict alignment, avoid an excessive number of byte wide stores.
+  MaxStoresPerMemsetOptSize = 8;
+  MaxStoresPerMemset = Subtarget->requiresStrictAlign()
+                       ? MaxStoresPerMemsetOptSize : 32;
 
-  MaxStoresPerMemcpy = MaxStoresPerMemcpyOptSize = 4;
-  MaxStoresPerMemmove = MaxStoresPerMemmoveOptSize = 4;
+  MaxGluedStoresPerMemcpy = 4;
+  MaxStoresPerMemcpyOptSize = 4;
+  MaxStoresPerMemcpy = Subtarget->requiresStrictAlign()
+                       ? MaxStoresPerMemcpyOptSize : 16;
+
+  MaxStoresPerMemmoveOptSize = MaxStoresPerMemmove = 4;
 
   setStackPointerRegisterToSaveRestore(AArch64::SP);