Re: Change in floating point performance across kernels

2012-08-19 Thread Mans Rullgard
On 20 August 2012 00:41, Michael Hope wrote: > On 20 August 2012 11:36, Mans Rullgard wrote: >> On 19 August 2012 23:55, Michael Hope wrote: On 17 August 2012 00:37, Michael Hope wrote: > Hi there. I'm seeing a huge improvement in the SPEC floating point > benchmarks between a hac

Re: Change in floating point performance across kernels

2012-08-19 Thread Michael Hope
On 20 August 2012 11:36, Mans Rullgard wrote: > On 19 August 2012 23:55, Michael Hope wrote: >>> On 17 August 2012 00:37, Michael Hope wrote: Hi there. I'm seeing a huge improvement in the SPEC floating point benchmarks between a hacked Ubuntu Precise 3.2.14 kernel and Linus 3.5.

Re: Change in floating point performance across kernels

2012-08-19 Thread Mans Rullgard
On 19 August 2012 23:55, Michael Hope wrote: >> On 17 August 2012 00:37, Michael Hope wrote: >>> Hi there. I'm seeing a huge improvement in the SPEC floating point >>> benchmarks between a hacked Ubuntu Precise 3.2.14 kernel and Linus >>> 3.5. Does anyone know why off the top of their head? >>

Re: Change in floating point performance across kernels

2012-08-19 Thread Michael Hope
> On 17 August 2012 00:37, Michael Hope wrote: >> Hi there. I'm seeing a huge improvement in the SPEC floating point >> benchmarks between a hacked Ubuntu Precise 3.2.14 kernel and Linus >> 3.5. Does anyone know why off the top of their head? > > Hacked how? How big a change? What does perf sa

Re: Change in floating point performance across kernels

2012-08-17 Thread Mans Rullgard
On 17 August 2012 00:37, Michael Hope wrote: > Hi there. I'm seeing a huge improvement in the SPEC floating point > benchmarks between a hacked Ubuntu Precise 3.2.14 kernel and Linus > 3.5. Does anyone know why off the top of their head? Hacked how? How big a change? What does perf say? --