Fri, 29 Apr 2016 17:24:16 +0200 8154943: AArch64: redundant address computation instructions with vectorization
roland [Fri, 29 Apr 2016 17:24:16 +0200] rev 38236
8154943: AArch64: redundant address computation instructions with vectorization Summary: duplicated i2l nodes can be eliminated to optimize redundant address computations Reviewed-by: kvn, dlong
Wed, 04 May 2016 13:32:03 -0700 8155717: Aarch64: enable loop superword's unrolling analysis
roland [Wed, 04 May 2016 13:32:03 -0700] rev 38235
8155717: Aarch64: enable loop superword's unrolling analysis Reviewed-by: aph, kvn, mcberg
(0) -30000 -10000 -3000 -1000 -300 -100 -30 -10 -2 +2 +10 +30 +100 +300 +1000 +3000 +10000 tip