SPEC® ACCEL™ ACC Result
Copyright 2014-2015 Standard Performance Evaluation Corporation
Sysinfo program /home/pathscale/ACCEL/Docs/sysinfo
$Rev: 6874 $ $Date:: 2013-11-20 #$ 0953404ef7e75a5f9bbb534c6de3f831
running on Cirrascale Wed Feb 18 01:00:54 2015
This section contains SUT (System Under Test) info as seen by
some common utilities. To remove or add to this section, see:
http://www.spec.org/accel/Docs/config.html#sysinfo
From /proc/cpuinfo
model name : Intel(R) Xeon(R) CPU E5-2637 v3 @ 3.50GHz
2 "physical id"s (chips)
16 "processors"
cores, siblings (Caution: counting these is hw and system dependent. The
following excerpts from /proc/cpuinfo might not be reliable. Use with
caution.)
cpu cores : 4
siblings : 8
physical 0: cores 0 1 4 5
physical 1: cores 0 1 4 5
cache size : 15360 KB
From /proc/meminfo
MemTotal: 32946036 kB
HugePages_Total: 0
Hugepagesize: 2048 kB
/usr/bin/lsb_release -d
CentOS release 6.6 (Final)
From /etc/*release* /etc/*version*
centos-release: CentOS release 6.6 (Final)
redhat-release: CentOS release 6.6 (Final)
system-release: CentOS release 6.6 (Final)
system-release-cpe: cpe:/o:centos:linux:6:GA
uname -a:
Linux Cirrascale 3.19.0PathScale+ #6 SMP Tue Feb 17 03:20:41 PST 2015 x86_64
x86_64 x86_64 GNU/Linux
run-level 3 Feb 18 00:45
SPEC is set to: /home/pathscale/ACCEL
Filesystem Type Size Used Avail Use% Mounted on
/dev/sda1 ext4 96G 26G 67G 28% /
Additional information from dmidecode:
Warning: Use caution when you interpret this section. The 'dmidecode' program
reads system data which is "intended to allow hardware to be accurately
determined", but the intent may not be met, as there are frequent changes to
hardware, firmware, and the "DMTF SMBIOS" standard.
BIOS GIGABYTE F15 11/28/2014
Memory:
4x Kinston 9995589-001.A00G 8 GB 1 rank 2133 MHz
12x NO DIMM NO DIMM
(End of data from sysinfo program)
3.19.0PathScale+ is built from exactly this commit with one additionally patch below
https://github.com/torvalds/linux/commit/8cc748aa76c921d8834ef00f762f31acd2c93aa8
Author: Alex Deucher <alexander.deucher@amd.com>
Date: Thu Feb 12 00:40:58 2015 -0500
drm/radeon: fix voltage setup on hawaii
Missing parameter when fetching the real voltage values
from atom. Fixes problems with dynamic clocking on
certain boards.
bug:
https://bugs.freedesktop.org/show_bug.cgi?id=87457
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index dbc94f3..fc1b3f3 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -3289,6 +3289,7 @@ int radeon_atom_get_voltage_evv(struct radeon_device *rdev,
args.in.ucVoltageType = VOLTAGE_TYPE_VDDC;
args.in.ucVoltageMode = ATOM_GET_VOLTAGE_EVV_VOLTAGE;
+ args.in.usVoltageLevel = cpu_to_le16(virtual_voltage_id);
args.in.ulSCLKFreq =
ECC disabled by default
GPU Boost mode enabled by setting the device to the following below
high performance mode: "echo high > /sys/class/drm/card0/device/power_dpm_force_performance_level"
The details for high performance mode: cat /sys/kernel/debug/dri/64/radeon_pm_info
uvd disabled
vce disabled
power level avg sclk: 86100 mclk: 125000
The Intel documentation says the CPU can boost to 3700 Mhz, but dmidecode reports Max Speed: 3600 MHz
Kit built system using no case and just mounted on a test bench
| 303.ostencil: |
basepeak = yes
|
| 304.olbm: |
basepeak = yes
|
| 314.omriq: |
basepeak = yes
|
| 352.ep: |
-O3
-acc
-device=hawaii
-fprelaxed-offload
|
| 354.cg: |
basepeak = yes
|
| 357.csp: |
basepeak = yes
|
| 370.bt: |
basepeak = yes
|
| 353.clvrleaf: |
basepeak = yes
|
| 359.miniGhost: |
basepeak = yes
|
