diff options
author | 2017-04-27 16:50:47 +0100 | |
---|---|---|
committer | 2017-05-11 10:06:04 +0100 | |
commit | e1811ed6b57a54dc8ebd327e4bd2c4422092a3a0 (patch) | |
tree | e3ce48e66190c11a8b5342f4ec0d1046ba28d788 /compiler/optimizing/nodes.h | |
parent | 7113885fcd983b33ee1e350865d21517d6297843 (diff) |
ARM64: Share address computation across SIMD LDRs/STRs.
For array accesses the element address has the following structure:
Address = CONST_OFFSET + base_addr + index << ELEM_SHIFT
Taking into account ARM64 LDR/STR addressing modes address part
(CONST_OFFSET + index << ELEM_SHIFT) can be shared across array
access with the same data type and index.
For example, for the following loop 5 accesses can share address
computation:
void foo(int[] a, int[] b, int[] c) {
for (i...) {
a[i] = a[i] + 5;
b[i] = b[i] + c[i];
}
}
Test: test-art-host, test-art-target
Change-Id: I46af3b4e4a55004336672cdba3296b7622d815ca
Diffstat (limited to 'compiler/optimizing/nodes.h')
-rw-r--r-- | compiler/optimizing/nodes.h | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/compiler/optimizing/nodes.h b/compiler/optimizing/nodes.h index 36c7df70ce..00d298824e 100644 --- a/compiler/optimizing/nodes.h +++ b/compiler/optimizing/nodes.h @@ -1396,7 +1396,8 @@ class HLoopInformationOutwardIterator : public ValueObject { M(BitwiseNegatedRight, Instruction) \ M(DataProcWithShifterOp, Instruction) \ M(MultiplyAccumulate, Instruction) \ - M(IntermediateAddress, Instruction) + M(IntermediateAddress, Instruction) \ + M(IntermediateAddressIndex, Instruction) #endif #ifndef ART_ENABLE_CODEGEN_arm |