Created attachment 114017 [details]
Xorg info

System Environment: 
Regression: Yes     
Platform:  BDW BSW
Kernel:  V3.19
Libdrm:(master)libdrm-2.4.59-31-gf799a527db2851b2890146a9ce777f73fea30176
Mesa:  (10.5)c32d83528189be988275c9ccbd3bbb2e48ee4362
Xserver: (server-1.16-branch)xorg-server-1.16.4
Xf86_video_intel:(master)2.99.917-165-gf6ba71ac194a19c80aa64f4769f76a47ebb7bd16
Cairo:  (master)70cc8f250b5669e757b4f044571ba0f71e3dea9e
Libva:  (master)f9741725839ea144e9a6a1827f74503ee39946c3
Libva_intel_driver: (master)e8fde1cdaafb93c2b54d6092a728d099ad7cdd11

Bug detailed description:
--------------------------------------------------
SynMark2_v6_0_0_OglDrvCtx performance reduce by 12% with gnome-session on BDW and BSW. The problem also exists on latest Master branch.
It's Mesa regression. By bisected, show that ee5fb8d1 is the first bad commit.
Its parents commit (7ff457b9) is good.

commit ee5fb8d1ba7f50ed94e1a34fa0f6e15a0588145e  
Author:     Kristian Høgsberg <krh@bitplanet.net>
AuthorDate: Mon Oct 20 23:29:41 2014 -0700
Commit:     Kristian Høgsberg <krh@bitplanet.net>
CommitDate: Wed Dec 10 12:29:27 2014 -0800

    i965: Generate vs code using scalar backend for BDW+

    With everything in place, we can now use the scalar backend compiler for
    vertex shaders on BDW+.  We make scalar vertex shaders the default on
    BDW+ but add a new vec4vs debug option to force the vec4 backend.

    No piglit regressions.

    Performance impact is minimal, I see a ~1.5 improvement on the T-Rex
    GLBenchmark case, but in general it's in the noise.  Some of our
    internal synthetic, vs bounded benchmarks show great improvement, 20%-40%
    in some cases, but real-world cases are mostly unaffected.

    Signed-off-by: Kristian Høgsberg <krh@bitplanet.net>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org> 

Please see Xrog.0.log.

Reproduce steps:
----------------------------
1, xinit& 
2, gnome-session&
3, ./synmark2 OglDrvCtx