Re: [PATCH v3] x86, crypto: ported aes-ni implementation to x86

2010-11-17 Thread Mathias Krause
On 13.11.2010, 00:25 Mathias Krause wrote: > On 12.11.2010, 08:34 Huang Ying wrote: > On Fri, 2010-11-12 at 15:30 +0800, Mathias Krause wrote: >>> On 12.11.2010, 01:33 Huang Ying wrote: Why the improvement of ECB is so small? I can not understand it. It should be as big as CBC. >>> >>> I

Re: [PATCH v3] x86, crypto: ported aes-ni implementation to x86

2010-11-12 Thread Mathias Krause
On 12.11.2010, 08:34 Huang Ying wrote: On Fri, 2010-11-12 at 15:30 +0800, Mathias Krause wrote: >> On 12.11.2010, 01:33 Huang Ying wrote: >>> Why the improvement of ECB is so small? I can not understand it. It >>> should be as big as CBC. >> >> I don't know why the ECB variant is so slow compared

Re: [PATCH v3] x86, crypto: ported aes-ni implementation to x86

2010-11-11 Thread Mathias Krause
On 12.11.2010, 08:34 Huang Ying wrote: On Fri, 2010-11-12 at 15:30 +0800, Mathias Krause wrote: >> On 12.11.2010, 01:33 Huang Ying wrote: >>> Hi, Mathias, >>> >>> On Fri, 2010-11-12 at 06:18 +0800, Mathias Krause wrote: All test were run five times in a row using a 256 bit key and doing i/o >

Re: [PATCH v3] x86, crypto: ported aes-ni implementation to x86

2010-11-11 Thread Huang Ying
On Fri, 2010-11-12 at 15:30 +0800, Mathias Krause wrote: > On 12.11.2010, 01:33 Huang Ying wrote: > > Hi, Mathias, > > > > On Fri, 2010-11-12 at 06:18 +0800, Mathias Krause wrote: > >> All test were run five times in a row using a 256 bit key and doing i/o > >> to the block device in chunks of 1MB

Re: [PATCH v3] x86, crypto: ported aes-ni implementation to x86

2010-11-11 Thread Mathias Krause
On 12.11.2010, 01:33 Huang Ying wrote: > Hi, Mathias, > > On Fri, 2010-11-12 at 06:18 +0800, Mathias Krause wrote: >> All test were run five times in a row using a 256 bit key and doing i/o >> to the block device in chunks of 1MB. The numbers are MB/s. >> >> x86 (i586 variant): >>1. run

Re: [PATCH v3] x86, crypto: ported aes-ni implementation to x86

2010-11-11 Thread Huang Ying
Hi, Mathias, On Fri, 2010-11-12 at 06:18 +0800, Mathias Krause wrote: > All test were run five times in a row using a 256 bit key and doing i/o > to the block device in chunks of 1MB. The numbers are MB/s. > > x86 (i586 variant): > 1. run 2. run 3. run 4. run 5. runmean > ECB:

Re: [PATCH v3] x86, crypto: ported aes-ni implementation to x86

2010-11-11 Thread Mathias Krause
Hello Huang Ying, On 03.11.2010, 23:27 Huang Ying wrote: > On Wed, 2010-11-03 at 14:14 -0700, Mathias Krause wrote: >> The AES-NI instructions are also available in legacy mode so the 32-bit >> architecture may profit from those, too. >> >> To illustrate the performance gain here's a short summar

Re: [PATCH v3] x86, crypto: ported aes-ni implementation to x86

2010-11-04 Thread Huang Ying
On Thu, 2010-11-04 at 00:38 -0700, Mathias Krause wrote: > On 03.11.2010, 23:27 Huang Ying wrote: > > On Wed, 2010-11-03 at 14:14 -0700, Mathias Krause wrote: > >> The AES-NI instructions are also available in legacy mode so the 32-bit > >> architecture may profit from those, too. > >> > >> To ill

Re: [PATCH v3] x86, crypto: ported aes-ni implementation to x86

2010-11-04 Thread Mathias Krause
On 03.11.2010, 23:27 Huang Ying wrote: > On Wed, 2010-11-03 at 14:14 -0700, Mathias Krause wrote: >> The AES-NI instructions are also available in legacy mode so the 32-bit >> architecture may profit from those, too. >> >> To illustrate the performance gain here's a short summary of the tcrypt >>

Re: [PATCH v3] x86, crypto: ported aes-ni implementation to x86

2010-11-03 Thread Huang Ying
On Wed, 2010-11-03 at 14:14 -0700, Mathias Krause wrote: > The AES-NI instructions are also available in legacy mode so the 32-bit > architecture may profit from those, too. > > To illustrate the performance gain here's a short summary of the tcrypt > speed test on a Core i7 M620 running at 2.67GH

[PATCH v3] x86, crypto: ported aes-ni implementation to x86

2010-11-03 Thread Mathias Krause
The AES-NI instructions are also available in legacy mode so the 32-bit architecture may profit from those, too. To illustrate the performance gain here's a short summary of the tcrypt speed test on a Core i7 M620 running at 2.67GHz comparing both assembler implementations: x86: