[Patch,optimization]: Optimized changes in the estimate register pressure cost.
Mon Sep 28 01:30:00 GMT 2015
On September 26, 2015 9:10:13 AM GMT+02:00, "Bin.Cheng" <firstname.lastname@example.org> wrote:
>On Sat, Sep 26, 2015 at 12:51 PM, Ajit Kumar Agarwal
>> SPEC CPU 2000 benchmarks are run and there is following impact on the
>> and code size.
>> ratio with the optimization vs ratio without optimization for INT
>> (3807.632 vs 3804.661)
>> ratio with the optimization vs ratio without optimization for FP
>> ( 4668.743 vs 4778.741)
Do I read this correctly to introduce a 2,4% regression for FP?
>> Code size reduction with respect to FP SPEC CPU 2000 benchmarks
>> Number of instruction with optimization = 1094117
>> Number of instruction without optimization = 1094659
>> Reduction in number of instruction with the optimization = 542
More information about the Gcc-patches