Show Posts

This section allows you to view all posts made by this member. Note that you can only see posts made in areas you currently have access to.


Messages - Hasturtium

Pages: [1] 2 3 ... 9
1
General CPU Discussion / Re: Byte Magazine Unix benchmarking
« on: June 09, 2024, 05:48:29 pm »
That is a pretty stark difference. What’s your storage configuration?

2
General CPU Discussion / Re: Byte Magazine Unix benchmarking
« on: June 08, 2024, 08:25:31 pm »
Apparently upgrading to dual NVMe drives in a HighPoint Rocket 1204 really helped versus SATA!

Code: [Select]
Architecture:             ppc64le
  Byte Order:             Little Endian
CPU(s):                   32
  On-line CPU(s) list:    0-31
Model name:               POWER9, altivec supported
  Model:                  2.3 (pvr 004e 1203)
  Thread(s) per core:     4
  Core(s) per socket:     8
  Socket(s):              1
  Frequency boost:        enabled
  CPU(s) scaling MHz:     58%
  CPU max MHz:            3800.0000
  CPU min MHz:            2166.0000
Caches (sum of all):     
  L1d:                    256 KiB (8 instances)
  L1i:                    256 KiB (8 instances)
  L2:                     4 MiB (8 instances)
  L3:                     80 MiB (8 instances)
NUMA:                     
  NUMA node(s):           1
  NUMA node0 CPU(s):      0-31
Vulnerabilities:         
  Gather data sampling:   Not affected
  Itlb multihit:          Not affected
  L1tf:                   Mitigation; RFI Flush, L1D private per thread
  Mds:                    Not affected
  Meltdown:               Mitigation; RFI Flush, L1D private per thread
  Mmio stale data:        Not affected
  Reg file data sampling: Not affected
  Retbleed:               Not affected
  Spec rstack overflow:   Not affected
  Spec store bypass:      Mitigation; Kernel entry/exit barrier (eieio)
  Spectre v1:             Mitigation; __user pointer sanitization, ori31 speculation barrier enabled
  Spectre v2:             Mitigation; Software count cache flush (hardware accelerated), Software li
                          nk stack flush
  Srbds:                  Not affected
  Tsx async abort:        Not affected

Code: [Select]

========================================================================
   BYTE UNIX Benchmarks (Version 5.1.3)

   System: garlic: GNU/Linux
   OS: GNU/Linux -- 6.8.11-300.fc40.ppc64le -- #1 SMP Mon May 27 14:48:15 UTC 2024
   Machine: ppc64le (unknown)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   19:21:24 up 1 day,  5:15,  1 user,  load average: 1.02, 0.93, 0.53; runlevel 2024-06-07

------------------------------------------------------------------------
Benchmark Run: Sat Jun 08 2024 19:21:24 - 19:49:33
32 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       43041836.3 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     4837.3 MWIPS (10.0 s, 7 samples)
Execl Throughput                               3534.7 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        505013.3 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          129743.4 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1617495.7 KBps  (30.0 s, 2 samples)
Pipe Throughput                              780267.9 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  45540.0 lps   (10.0 s, 7 samples)
Process Creation                               4907.1 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   4964.0 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   4012.3 lpm   (60.0 s, 2 samples)
System Call Overhead                         745210.3 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   43041836.3   3688.2
Double-Precision Whetstone                       55.0       4837.3    879.5
Execl Throughput                                 43.0       3534.7    822.0
File Copy 1024 bufsize 2000 maxblocks          3960.0     505013.3   1275.3
File Copy 256 bufsize 500 maxblocks            1655.0     129743.4    783.9
File Copy 4096 bufsize 8000 maxblocks          5800.0    1617495.7   2788.8
Pipe Throughput                               12440.0     780267.9    627.2
Pipe-based Context Switching                   4000.0      45540.0    113.9
Process Creation                                126.0       4907.1    389.5
Shell Scripts (1 concurrent)                     42.4       4964.0   1170.7
Shell Scripts (8 concurrent)                      6.0       4012.3   6687.1
System Call Overhead                          15000.0     745210.3    496.8
                                                                   ========
System Benchmarks Index Score                                         982.0

------------------------------------------------------------------------
Benchmark Run: Sat Jun 08 2024 19:49:33 - 20:17:50
32 CPUs in system; running 32 parallel copies of tests

Dhrystone 2 using register variables      458837067.6 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                   113857.0 MWIPS (9.9 s, 7 samples)
Execl Throughput                              37688.4 lps   (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks       7241790.7 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks         1936219.8 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks      12073774.9 KBps  (30.0 s, 2 samples)
Pipe Throughput                            11005546.8 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                1753793.6 lps   (10.0 s, 7 samples)
Process Creation                              68433.7 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  70747.1 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   9283.9 lpm   (60.1 s, 2 samples)
System Call Overhead                       13679550.5 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0  458837067.6  39317.7
Double-Precision Whetstone                       55.0     113857.0  20701.3
Execl Throughput                                 43.0      37688.4   8764.8
File Copy 1024 bufsize 2000 maxblocks          3960.0    7241790.7  18287.4
File Copy 256 bufsize 500 maxblocks            1655.0    1936219.8  11699.2
File Copy 4096 bufsize 8000 maxblocks          5800.0   12073774.9  20816.9
Pipe Throughput                               12440.0   11005546.8   8846.9
Pipe-based Context Switching                   4000.0    1753793.6   4384.5
Process Creation                                126.0      68433.7   5431.2
Shell Scripts (1 concurrent)                     42.4      70747.1  16685.6
Shell Scripts (8 concurrent)                      6.0       9283.9  15473.2
System Call Overhead                          15000.0   13679550.5   9119.7
                                                                   ========
System Benchmarks Index Score                                       12583.4


3
GPU Compute / Accelerators / Re: Intel Arc Support in Kernel 6.8
« on: May 21, 2024, 10:01:13 am »
Phoronix put up an article on May 12th indicating that a branch of Xe intended for merging into kernel 6.10 runs with some stability issues on an Ampere Altra. Obviously ARM's not Power, and I have a feeling there's something fidgety about the Altra's PCIe root complex that doesn't apply to our kit, so maybe we'll be in luck soon...? I may be crazy for dreaming that the 16GB Arc A770 I have sitting in a box would be a nicer option than the 8GB RX 6600 I'm currently running, but here's hoping.

4
And now, after updating and rebooting, the default Image Viewer fails to load an image, citing



This also causes SELinux to catch three errors:

1. Source process systemd-coredump attempted access sys_admin on capability (blank)
2. Source process abrt-dump-journal attempted access connectto on unix_stream_socket io.systemd.Home
3. Source process abrt-dump-journal attempted access connectto on unix_stream_socket io.systemd.Machine

Ristretto works and I'm running Xfce anyway, but what the hell.

5
Disregard - decided I must have followed a bad post-setup guide for F39 that broke something in the installer, so I went ahead and performed a clean install while maintaining my /home partition’s contents. Reporting in, it’s… working fine? Apart from Chromium, which is behaving as others have mentioned: it’s quick initially but bogs down and seems to stare into space in fits and starts before finally locking up and crashing. Sharkcz’s copr of Firefox 115.10 with the honorable ClassicHasClass’s JIT patches to the rescue.

6
Joy of joys - in setting up my clean install of Fedora 39 I did some media repo poking, opting for Red Hat’s non-free sources so I could get video acceleration properly working in YouTube and VLC. But when I try to run the Fedora 40 upgrade it kvetches that it can’t find corresponding packages and throws the brakes on things. Should I run it with —allow-erasing and prepare to redo my repo selection on the other side?

7
GPU Compute / Accelerators / Re: Intel Arc Support in Kernel 6.8
« on: April 06, 2024, 08:45:50 pm »
I realize I'm late getting back to this, but that's a bummer. I'm guessing the xe driver isn't behaving better now that kernel 6.8's actually out in the wild, then.

8
Ah, thanks for this. I ran afoul of my machine going into suspend over the weekend, and this should set things right going forward.

9
Applications and Porting / RustiCL on Fedora 39
« on: April 01, 2024, 02:15:56 pm »
Ahoy. I've been trying to goad RustiCL into working with my Radeon RX 6600 on Fedora 39. To my knowledge I've installed all necessary prereqs for RustiCL to work, and setting RUSTICL_ENABLE=radeonsi does not seem to trigger any problems. Unfortunately when I run QGIS it still insists it cannot find a working OpenCL implementation. In running clinfo, both Clover and RustiCL report back, and one of them - probably Clover - barfs out the following message:

Code: [Select]
=== CL_PROGRAM_BUILD_LOG ===
fatal error: cannot open file '/usr/lib64/clc/gfx1032-amdgcn-mesa-mesa3d.bc': No such file or directory

I've determined that the compute kernel it's hunting for is not present, and looking for it online has been fruitless. I am not willing to create a symlink to point to something else, that sounds like an invitation to instability at best. The complete output from running RUSTICL_ENABLE=radeonsi > output.txt is here. It would be really nice if I could use my RX 6600 for something new. Anybody else gotten RustiCL working yet?

10
User Zone / Re: Rough edges and how I work around them (or not)
« on: March 05, 2024, 01:11:07 pm »
It seems like video encoding on Power9 has been a rough edge on the platform since the beginning... I know the VP9 encoder was getting some decent ppc64le optimizations several years back; did those ever get merged into trunk? Short of using a hardware-assisted encoder I don't even know what my options are that don't require encoding to 480p.

11
Firmware / Re: Firmware 2.10 for Talos-II and Blackbird available
« on: February 20, 2024, 11:11:06 am »
What are you referring to?

Good question. My personal life's been hectic lately; maybe I dreamed something.

12
Firmware / Re: Firmware 2.10 for Talos-II and Blackbird available
« on: February 18, 2024, 11:27:37 am »
What are the video hardware compatibility issues this fixes, out of curiosity?

13
GPU Compute / Accelerators / Re: Intel Arc Support in Kernel 6.8
« on: February 09, 2024, 05:50:57 pm »
I'm cautiously optimistic, I've been literally looking for an excuse to pick up an arc gpu as it'd be perfect for my blackbird. One question, why is the Huc microcontroller not likely to be supported and what limitations would there be on video encoders without it?

To my recollection that microcontroller won’t be supported from Battlemage/future IGPs, and the driver maintainers consider implementing support outside the x86-only i915 driver to be too pernicious to be worth bothering with. IIRC the microcontroller’s responsible for configuration of parameters to be passed to the video encoder, so outside of some default setting it won’t be configurable. Once kernel support for the Xe driver is verified working I’ll throw my little Arc A380 in and take it for a test drive.

14
GPU Compute / Accelerators / Intel Arc Support in Kernel 6.8
« on: January 24, 2024, 09:01:53 am »
It looks like Intel's Xe driver is being mainlined in kernel 6.8. To this point Arc support's been officially limited to the i915 driver, which has had hard x86 dependencies. However the driver is confirmed to compile and work on aarch64, so we may be in luck. While the driver is chiefly intended for the to-be-released Battlemage hardware it does support the current Alchemist line; the only thing we'll likely miss out on is support for the HuC microcontroller. Without that support the video encoder is rather less capable... but given a choice between AMD and Intel's open graphics software stack, I know which way I'm leaning. Let's hope for good things.

15
If you believe you've determined the cause, I don't see a reason to keep the error messages around for further investigation. Good work troubleshooting it.

Pages: [1] 2 3 ... 9