Intel Sandy Bridge Linux Graphics? It's A Challenge

[Kano]

I can not test sandy bridge, but most likely a daily build of u 11.04 might be able to use the internal gfx card already. When they would include a recent libva then xbmc or vlc (or a special mplayer which is not the default one) could use accelleration too. You definitely can forget distributions released 2010 for sb.

[baddog]

I was able to get my new h67-based sandy bridge system running on fedora 14 linux with graphics without much trouble.
Little more than:
yum --enablerepo=rawhide install kernel
yum --enablerepo=rawhide update libdrm
yum update mesa-dri-drivers mesa-libGL
yum install xorg-x11-server-devel
download xf86-video-intel-2.14:
configure
make
make install
cp the intel_drv.so from /usr/local/lib/xorg/modules/drivers to /usr/lib64/xorg/modules/drivers
change /etc/X11/xorg.conf to use the intel driver

That's not so hard is it? Don't even need to do a fresh OS install.

[baddog]

There's a fedora rpm for the 2.14 X server now, so a:
yum --enablerepo=rawhide update xorg-x11-drv-intel
should eliminate the need to compile it from source.

[psycho_driver]

There's a fedora rpm for the 2.14 X server now, so a:
yum --enablerepo=rawhide update xorg-x11-drv-intel
should eliminate the need to compile it from source.

How's the 3D performance?

[baddog]

How's the 3D performance?

As measured with what? I don't use any 3d apps under linux so I don't know offhand. I could fire up a benchmark if I was pointed in the right direction.

[psycho_driver]

As measured with what? I don't use any 3d apps under linux so I don't know offhand. I could fire up a benchmark if I was pointed in the right direction.

Hmm, you probably have glxgears on your system. It doesn't really tell a whole lot outside of very basic 3d throughput.

[baddog]

Hmm, you probably have glxgears on your system. It doesn't really tell a whole lot outside of very basic 3d throughput.

Well glxgears is horribly slow on my core i7-2600k. Looks reminiscent of glxgears on a system that is melting down with full I/O load, yet the system is idle:

% glxgears
Xlib:  extension "NV-GLX" missing on display "unix:0.0".
Running synchronized to the vertical refresh.  The framerate should be
approximately the same as the monitor refresh rate.
361 frames in 5.3 seconds = 68.130 FPS
300 frames in 5.0 seconds = 59.994 FPS
300 frames in 5.0 seconds = 59.994 FPS
300 frames in 5.0 seconds = 59.994 FPS
300 frames in 5.0 seconds = 59.994 FPS
^C

% uptime

 18:56:53 up 3 min,  3 users,  load average: 0.09, 0.23, 0.12
% acat /proc/cpuinfo

processor	: 0
vendor_id	: GenuineIntel
cpu family	: 6
model		: 42
model name	: Intel(R) Core(TM) i7-2600K CPU @ 3.40GHz
stepping	: 7
cpu MHz		: 1600.000
cache size	: 8192 KB
physical id	: 0
siblings	: 8
core id		: 0
cpu cores	: 4
apicid		: 0
initial apicid	: 0
fpu		: yes
fpu_exception	: yes
cpuid level	: 13
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm sse4_1 sse4_2 popcnt aes xsave avx lahf_lm ida arat epb xsaveopt pln pts dts tpr_shadow vnmi flexpriority ept vpid
bogomips	: 6782.18
clflush size	: 64
cache_alignment	: 64
address sizes	: 36 bits physical, 48 bits virtual
power management:

processor	: 1
...

[deanjo]

Hmm, you probably have glxgears on your system. It doesn't really tell a whole lot outside of very basic 3d throughput.

/bangs head against wall.......

GLXgears is not a benchmark. The only thing that the numbers are useful for is to tell you if you have hardware acceleration or not.

*** NOTE: Don't use glxgears as a benchmark.
OpenGL implementations are not optimized for frame rates >> 60fps,
thus these numbers are meaningless when compared between vendors.

[baddog]

/bangs head against wall.......

GLXgears is not a benchmark. The only thing that the numbers are useful for is to tell you if you have hardware acceleration or not.

Agree, it didn't seem like a valid test. Still wondering where the proper benchmark is. The phoronix test suite documentation link doesn't give a clue.

[deanjo]

Agree, it didn't seem like a valid test. Still wondering where the proper benchmark is. The phoronix test suite documentation link doesn't give a clue.

Running any one of the gaming benchmarks would be a good start with pts.