Ryzen Linux Users Are Still Facing Issues with Heavy Compilation Loads

Megalith · Aug 5, 2017

It was originally reported that Linux users were facing segmentation faults and, at times, crashes when running concurrent compilation loads on Ryzen CPUs, and these issues don’t appear to be fixed: Phoronix has run additional tests and found that heavy workloads remain problematic, as of Linux 4.13. These problems did not occur when tested using Intel CPUs.

We'll see now if AMD will provide public comments or if they investigate further, as they now have another reproducible test case to slam the Ryzen chips hard in just a few minutes even with SMT disabled and running at DDR4-2133. As far as whether this just affects Ryzen or also Threadripper and Epyc remains unclear. While there are many Windows reviewers out there now with Threadripper, it doesn't look like AMD will be sending any Threadripper samples to Phoronix, at least in the immediate days ahead but I have asked if at least can get SSH access to a TR system for a few hours to be able to run some Linux benchmarks. We'll see.

Shmee · Aug 5, 2017

That is a bummer, but I am guessing the are prioritizing Windows with their fixes. I am sure this will get worked out soon.

Poseur · Aug 5, 2017

I hope AMD helps to get this fixed soon.

naib · Aug 5, 2017

I have been following this on the gentoo board

AMD Zen/Ryzen thread General discussion thread leading up to its release

Segfaults during compilation on AMD Ryzen. people reporting segfaults

Gentoo & Ryzen config & stability questionair I made a google form to track any commonality.

I am one of those lucky people who do not have any issues (touch wood...) I have compiled 3 copies of mesa in parallel without any issues & mesa is a package that keeps coming up. There have been a number of stress-tests that cause people to fail and none of them fail for me...

Phononix's has linked my google docs a few times. They have an updated article 50+ Segmentation Faults Per Hour: Continuing To Stress Ryzen and this is interesting as Phoronix initially stated they never had issues but as more and more things came to light he fired up a stress test and came up with a good test example

PTS_CONCURRENT_TEST_RUNS=4 TOTAL_LOOP_TIME=60 phoronix-test-suite stress-run build-linux-kernel build-php build-apache build-imagemagick

I have just finished building php with pcntl (I am a gentoo user) and I am about to execute this command to see if it does cause me issues

--edit-- started:

Code:

[jrb:~/tmp/phoronix-test-suite] 14s $ TS_CONCURRENT_TEST_RUNS=4 TOTAL_LOOP_TIME=60 ./phoronix-test-suite stress-run build-linux-kernel build-php build-apache build-imagemagick

STRESS-RUN ENVIRONMENT VARIABLES:

PTS_CONCURRENT_TEST_RUNS: Set the PTS_CONCURRENT_TEST_RUNS environment variable to specify how many tests should be run concurrently during the stress-run process. If not specified, defaults to 2.


TOTAL_LOOP_TIME set; running tests for 60 minutes

SYSTEM INFORMATION: 

  PROCESSOR:          AMD Ryzen 5 1600 Six-Core @ 3.20GHz (12 Cores)
    Core Count:       6
    Thread Count:     12
    Extensions:       SSE 4.2 + AVX2 + AVX + RDRAND + FSGSBASE
    Cache Size:       512 KB
    Microcode:        0x8001126
    Scaling Driver:   acpi-cpufreq schedutil

  GRAPHICS:           NVIDIA GeForce GTX 970 4096MB (1151/3505MHz)
    OpenGL:           4.5.0
    Vulkan:           1.0.46
    Display Driver:   NVIDIA 384.59
    Screen:           1280x1024

  MOTHERBOARD:        MSI X370 GAMING PRO CARBON (MS-7A32) v1.0
    Memory:           16384MB

  DISK:               256GB OCZ VERTEX4 + 1000GB Samsung SSD 960 EVO 1TB
    File-System:      ext4
    Mount Options:    data=ordered noatime nodiratime rw
    Disk Scheduler:   NONE

  OPERATING SYSTEM:   Gentoo 2.4.1
    Kernel:           4.12.4-gentoo (x86_64)
    Desktop:          GNOME
    Display Server:   X Server 1.19.3
    Compiler:         GCC 7.1.0 + LLVM 4.0.1


pts/build-apache-1.5.1      : Test Started
pts/build-php-1.3.1         : Test Started
pts/build-php-1.3.1         : Average: 29.72 Seconds
pts/build-php-1.3.1         : Test Ended
pts/build-apache-1.5.1      : Average: 42.62 Seconds
pts/build-apache-1.5.1      : Test Ended
pts/build-php-1.3.1         : Test Started
pts/build-linux-kernel-1.7.0: Test Started

so far so good.

Ocellaris · Aug 5, 2017

AMD's response to this:

lollerwaffle · Aug 5, 2017

Bummer for AMD, I hope this can be patched via microcode/BIOS without performance loss. It's not too surprising that a new architecture has bugs but it's a shame when it hits workloads that people specifically buy the chip for, like massive amounts of compilation.

naib · Aug 5, 2017

Well 1hour test finished...

Code:

[jrb:~/tmp/phoronix-test-suite] 14s $ TS_CONCURRENT_TEST_RUNS=4 TOTAL_LOOP_TIME=60 ./phoronix-test-suite stress-run build-linux-kernel build-php build-apache build-imagemagick

STRESS-RUN ENVIRONMENT VARIABLES:

PTS_CONCURRENT_TEST_RUNS: Set the PTS_CONCURRENT_TEST_RUNS environment variable to specify how many tests should be run concurrently during the stress-run process. If not specified, defaults to 2.


TOTAL_LOOP_TIME set; running tests for 60 minutes

SYSTEM INFORMATION: 

  PROCESSOR:          AMD Ryzen 5 1600 Six-Core @ 3.20GHz (12 Cores)
    Core Count:       6
    Thread Count:     12
    Extensions:       SSE 4.2 + AVX2 + AVX + RDRAND + FSGSBASE
    Cache Size:       512 KB
    Microcode:        0x8001126
    Scaling Driver:   acpi-cpufreq schedutil

  GRAPHICS:           NVIDIA GeForce GTX 970 4096MB (1151/3505MHz)
    OpenGL:           4.5.0
    Vulkan:           1.0.46
    Display Driver:   NVIDIA 384.59
    Screen:           1280x1024

  MOTHERBOARD:        MSI X370 GAMING PRO CARBON (MS-7A32) v1.0
    Memory:           16384MB

  DISK:               256GB OCZ VERTEX4 + 1000GB Samsung SSD 960 EVO 1TB
    File-System:      ext4
    Mount Options:    data=ordered noatime nodiratime rw
    Disk Scheduler:   NONE

  OPERATING SYSTEM:   Gentoo 2.4.1
    Kernel:           4.12.4-gentoo (x86_64)
    Desktop:          GNOME
    Display Server:   X Server 1.19.3
    Compiler:         GCC 7.1.0 + LLVM 4.0.1


pts/build-apache-1.5.1      : Test Started
pts/build-php-1.3.1         : Test Started
pts/build-php-1.3.1         : Average: 29.72 Seconds
pts/build-php-1.3.1         : Test Ended
pts/build-apache-1.5.1      : Average: 42.62 Seconds
pts/build-apache-1.5.1      : Test Ended
pts/build-php-1.3.1         : Test Started
pts/build-linux-kernel-1.7.0: Test Started
pts/build-linux-kernel-1.7.0: Average: 126.79 Seconds
pts/build-linux-kernel-1.7.0: Test Ended
pts/build-php-1.3.1         : Average: 76.76 Seconds
pts/build-php-1.3.1         : Test Ended
pts/build-imagemagick-1.7.2 : Test Started
pts/build-apache-1.5.1      : Test Started

###### STRESS RUN INTERIM REPORT ####
AUGUST 5 16:53 BST
START TIME: August 5 16:48 BST
ELAPSED TIME: 5 Minutes, 3 Seconds
TIME REMAINING: 54 Minutes, 57 Seconds
SYSTEM IP: 192.168.0.33
HOSTNAME: fluidmotion
# OF CONCURRENT TESTS: 2

TESTS CURRENTLY ACTIVE: 
   - pts/build-imagemagick-1.7.2   [PID: 1735]
   - pts/build-apache-1.5.1        [PID: 1736]

TESTS IN RUN QUEUE: 

TIMED APACHE COMPILATION [pts/build-apache-1.5.1]
TIMED IMAGEMAGICK COMPILATION [pts/build-imagemagick-1.7.2]
TIMED LINUX KERNEL COMPILATION [pts/build-linux-kernel-1.7.0]
TIMED PHP COMPILATION [pts/build-php-1.3.1]

SYSTEM INFORMATION: 
     Processor:           AMD Ryzen 5 1600 Six-Core @ 3.20GHz (12 Cores)
     Motherboard:         MSI X370 GAMING PRO CARBON (MS-7A32) v1.0
     Memory:              16384MB
     Disk:                256GB OCZ VERTEX4 + 1000GB Samsung SSD 960 EVO 1TB
     Graphics:            NVIDIA GeForce GTX 970 4096MB (1151/3505MHz)
     Audio:               NVIDIA Generic
     OS:                  Gentoo 2.4.1
     Kernel:              4.12.4-gentoo (x86_64)
     Desktop:             GNOME
     Display Server:      X Server 1.19.3
     Display Driver:      NVIDIA 384.59
     OpenGL:              4.5.0
     Vulkan:              1.0.46
     Compiler:            GCC 7.1.0 + LLVM 4.0.1
     File-System:         ext4
     Screen Resolution:   1280x1024

     TESTS EXECUTED                   TIMES CALLED
     pts/build-apache-1.5.1:          2
     pts/build-imagemagick-1.7.2:     1
     pts/build-linux-kernel-1.7.0:    1
     pts/build-php-1.3.1:             2

SENSOR DATA: 
     SENSOR                          MIN   AVG   MAX
     CPU Usage (CPU0):               6.00          66.03         100.00        Percent
     CPU Usage (CPU1):               0.00          74.09         100.00        Percent
     CPU Usage (CPU2):               7.69          70.84         100.00        Percent
     CPU Usage (CPU3):               0.00          69.61         100.00        Percent
     CPU Usage (CPU4):               6.12          76.82         100.00        Percent
     CPU Usage (CPU5):               10.00         77.41         100.00        Percent
     CPU Usage (CPU6):               6.00          75.58         100.00        Percent
     CPU Usage (CPU7):               12.00         76.63         100.00        Percent
     CPU Usage (CPU8):               0.00          66.23         100.00        Percent
     CPU Usage (CPU9):               4.00          75.47         100.00        Percent
     CPU Usage (CPU10):              2.00          71.41         100.00        Percent
     CPU Usage (CPU11):              6.00          73.96         100.00        Percent
     CPU Usage (Summary):            9.03          67.11         100.00        Percent
     GPU Temperature:                35.00         36.06         39.00         Celsius
     GPU Usage:                      0.00          5.56          35.00         Percent
     Drive Read Speed (nvme0n1):     0.00          0.01          0.11          MB/s
     Drive Write Speed (nvme0n1):    0.00          6.19          90.82         MB/s
     Memory Usage:                   1992.00       2551.06       3535.00       Megabytes
     System Temperature:             35.00         35.11         36.00         Celsius
######
pts/build-apache-1.5.1      : Average: 64.44 Seconds
pts/build-apache-1.5.1      : Test Ended
pts/build-imagemagick-1.7.2 : Average: 70.01 Seconds
pts/build-imagemagick-1.7.2 : Test Ended
pts/build-linux-kernel-1.7.0: Test Started
pts/build-php-1.3.1         : Test Started
pts/build-php-1.3.1         : Average: 75.29 Seconds
pts/build-php-1.3.1         : Test Ended
pts/build-linux-kernel-1.7.0: Average: 130.15 Seconds
pts/build-linux-kernel-1.7.0: Test Ended
pts/build-imagemagick-1.7.2 : Test Started
pts/build-linux-kernel-1.7.0: Test Started

...
######
pts/build-linux-kernel-1.7.0: Average: 146.69 Seconds
pts/build-linux-kernel-1.7.0: Test Ended
pts/build-apache-1.5.1      : Test Started
pts/build-imagemagick-1.7.2 : Average: 84.40 Seconds
pts/build-imagemagick-1.7.2 : Test Ended
pts/build-linux-kernel-1.7.0: Test Started
pts/build-apache-1.5.1      : Average: 65.96 Seconds
pts/build-apache-1.5.1      : Test Ended
pts/build-apache-1.5.1      : Test Started
pts/build-linux-kernel-1.7.0: Average: 116.00 Seconds
pts/build-linux-kernel-1.7.0: Test Ended
pts/build-php-1.3.1         : Test Started
TEST TIME EXPIRED; NO NEW TESTS WILL EXECUTE; CURRENT TESTS WILL FINISH

###### SUMMARY REPORT ####
AUGUST 5 17:48 BST
START TIME: August 5 16:48 BST
ELAPSED TIME: 1 Hour, 1 Second
WAITING FOR CURRENT TEST RUN QUEUE TO FINISH.
SYSTEM IP: 192.168.0.33
HOSTNAME: fluidmotion
# OF CONCURRENT TESTS: 2


TESTS IN RUN QUEUE: 

TIMED APACHE COMPILATION [pts/build-apache-1.5.1]
TIMED IMAGEMAGICK COMPILATION [pts/build-imagemagick-1.7.2]
TIMED LINUX KERNEL COMPILATION [pts/build-linux-kernel-1.7.0]
TIMED PHP COMPILATION [pts/build-php-1.3.1]

SYSTEM INFORMATION: 
     Processor:           AMD Ryzen 5 1600 Six-Core @ 3.20GHz (12 Cores)
     Motherboard:         MSI X370 GAMING PRO CARBON (MS-7A32) v1.0
     Memory:              16384MB
     Disk:                256GB OCZ VERTEX4 + 1000GB Samsung SSD 960 EVO 1TB
     Graphics:            NVIDIA GeForce GTX 970 4096MB (1151/3505MHz)
     Audio:               NVIDIA Generic
     OS:                  Gentoo 2.4.1
     Kernel:              4.12.4-gentoo (x86_64)
     Desktop:             GNOME
     Display Server:      X Server 1.19.3
     Display Driver:      NVIDIA 384.59
     OpenGL:              4.5.0
     Vulkan:              1.0.46
     Compiler:            GCC 7.1.0 + LLVM 4.0.1
     File-System:         ext4
     Screen Resolution:   1280x1024

     TESTS EXECUTED                   TIMES CALLED
     pts/build-apache-1.5.1:          13
     pts/build-imagemagick-1.7.2:     14
     pts/build-linux-kernel-1.7.0:    17
     pts/build-php-1.3.1:             11

SENSOR DATA: 
     SENSOR                          MIN   AVG   MAX
     CPU Usage (CPU0):               0.00          77.93         100.00        Percent
     CPU Usage (CPU1):               0.00          78.08         100.00        Percent
     CPU Usage (CPU2):               0.00          80.86         100.00        Percent
     CPU Usage (CPU3):               0.00          80.05         100.00        Percent
     CPU Usage (CPU4):               1.96          80.75         100.00        Percent
     CPU Usage (CPU5):               0.00          80.12         100.00        Percent
     CPU Usage (CPU6):               0.00          81.31         100.00        Percent
     CPU Usage (CPU7):               0.00          77.68         100.00        Percent
     CPU Usage (CPU8):               0.00          78.57         100.00        Percent
     CPU Usage (CPU9):               0.00          80.20         100.00        Percent
     CPU Usage (CPU10):              0.00          80.04         100.00        Percent
     CPU Usage (CPU11):              0.00          77.90         100.00        Percent
     CPU Usage (Summary):            0.33          76.81         100.00        Percent
     GPU Temperature:                35.00         35.92         42.00         Celsius
     GPU Usage:                      0.00          4.03          35.00         Percent
     Drive Read Speed (nvme0n1):     0.00          0.00          0.11          MB/s
     Drive Write Speed (nvme0n1):    0.00          3.77          159.76        MB/s
     Memory Usage:                   1992.00       2827.03       4218.00       Megabytes
     System Temperature:             35.00         36.40         37.00         Celsius
######

⌂169% [jrb:~/tmp/phoronix-test-suite] 1h0m2s $ pts/build-php-1.3.1         : Average: 27.53 Seconds
pts/build-php-1.3.1         : Test Ended

######
pts/build-linux-kernel-1.7.0: Average: 146.69 Seconds
pts/build-linux-kernel-1.7.0: Test Ended
pts/build-apache-1.5.1      : Test Started
pts/build-imagemagick-1.7.2 : Average: 84.40 Seconds
pts/build-imagemagick-1.7.2 : Test Ended
pts/build-linux-kernel-1.7.0: Test Started
pts/build-apache-1.5.1      : Average: 65.96 Seconds
pts/build-apache-1.5.1      : Test Ended
pts/build-apache-1.5.1      : Test Started
pts/build-linux-kernel-1.7.0: Average: 116.00 Seconds
pts/build-linux-kernel-1.7.0: Test Ended
pts/build-php-1.3.1         : Test Started
TEST TIME EXPIRED; NO NEW TESTS WILL EXECUTE; CURRENT TESTS WILL FINISH

###### SUMMARY REPORT ####
AUGUST 5 17:48 BST
START TIME: August 5 16:48 BST
ELAPSED TIME: 1 Hour, 1 Second
WAITING FOR CURRENT TEST RUN QUEUE TO FINISH.
SYSTEM IP: 192.168.0.33
HOSTNAME: fluidmotion
# OF CONCURRENT TESTS: 2


TESTS IN RUN QUEUE: 

TIMED APACHE COMPILATION [pts/build-apache-1.5.1]
TIMED IMAGEMAGICK COMPILATION [pts/build-imagemagick-1.7.2]
TIMED LINUX KERNEL COMPILATION [pts/build-linux-kernel-1.7.0]
TIMED PHP COMPILATION [pts/build-php-1.3.1]

SYSTEM INFORMATION: 
     Processor:           AMD Ryzen 5 1600 Six-Core @ 3.20GHz (12 Cores)
     Motherboard:         MSI X370 GAMING PRO CARBON (MS-7A32) v1.0
     Memory:              16384MB
     Disk:                256GB OCZ VERTEX4 + 1000GB Samsung SSD 960 EVO 1TB
     Graphics:            NVIDIA GeForce GTX 970 4096MB (1151/3505MHz)
     Audio:               NVIDIA Generic
     OS:                  Gentoo 2.4.1
     Kernel:              4.12.4-gentoo (x86_64)
     Desktop:             GNOME
     Display Server:      X Server 1.19.3
     Display Driver:      NVIDIA 384.59
     OpenGL:              4.5.0
     Vulkan:              1.0.46
     Compiler:            GCC 7.1.0 + LLVM 4.0.1
     File-System:         ext4
     Screen Resolution:   1280x1024

     TESTS EXECUTED                   TIMES CALLED
     pts/build-apache-1.5.1:          13
     pts/build-imagemagick-1.7.2:     14
     pts/build-linux-kernel-1.7.0:    17
     pts/build-php-1.3.1:             11

SENSOR DATA: 
     SENSOR                          MIN   AVG   MAX
     CPU Usage (CPU0):               0.00          77.93         100.00        Percent
     CPU Usage (CPU1):               0.00          78.08         100.00        Percent
     CPU Usage (CPU2):               0.00          80.86         100.00        Percent
     CPU Usage (CPU3):               0.00          80.05         100.00        Percent
     CPU Usage (CPU4):               1.96          80.75         100.00        Percent
     CPU Usage (CPU5):               0.00          80.12         100.00        Percent
     CPU Usage (CPU6):               0.00          81.31         100.00        Percent
     CPU Usage (CPU7):               0.00          77.68         100.00        Percent
     CPU Usage (CPU8):               0.00          78.57         100.00        Percent
     CPU Usage (CPU9):               0.00          80.20         100.00        Percent
     CPU Usage (CPU10):              0.00          80.04         100.00        Percent
     CPU Usage (CPU11):              0.00          77.90         100.00        Percent
     CPU Usage (Summary):            0.33          76.81         100.00        Percent
     GPU Temperature:                35.00         35.92         42.00         Celsius
     GPU Usage:                      0.00          4.03          35.00         Percent
     Drive Read Speed (nvme0n1):     0.00          0.00          0.11          MB/s
     Drive Write Speed (nvme0n1):    0.00          3.77          159.76        MB/s
     Memory Usage:                   1992.00       2827.03       4218.00       Megabytes
     System Temperature:             35.00         36.40         37.00         Celsius
######

⌂169% [jrb:~/tmp/phoronix-test-suite] 1h0m2s $ pts/build-php-1.3.1         : Average: 27.53 Seconds
pts/build-php-1.3.1         : Test Ended

looking at dmesg:

Code:

[Sat Aug  5 16:48:54 2017] conftest[4564]: segfault at 0 ip 00000000004005e0 sp 00007fffed3c10d0 error 4 in conftest[400000+1000]
[Sat Aug  5 16:48:55 2017] conftest[4817]: segfault at 0 ip 00007fb80c9a10c6 sp 00007ffe72b5a8a8 error 4 in libc-2.24.so[7fb80c877000+192000]
[Sat Aug  5 16:49:59 2017] conftest[4887]: segfault at 0 ip 00000000004005e0 sp 00007fffb93595d0 error 4 in conftest[400000+1000]
[Sat Aug  5 16:49:59 2017] conftest[4965]: segfault at 0 ip 00007f600bd030c6 sp 00007fffb5e32228 error 4 in libc-2.24.so[7f600bbd9000+192000]
[Sat Aug  5 16:54:20 2017] conftest[22456]: segfault at 0 ip 00000000004005e0 sp 00007ffd3cc2fca0 error 4 in conftest[400000+1000]
[Sat Aug  5 16:54:20 2017] conftest[22523]: segfault at 0 ip 00007f750fe4e0c6 sp 00007fff5ad2cdc8 error 4 in libc-2.24.so[7f750fd24000+192000]
[Sat Aug  5 17:01:09 2017] conftest[13761]: segfault at 0 ip 00000000004005e0 sp 00007ffc6d8ff650 error 4 in conftest[400000+1000]
[Sat Aug  5 17:01:09 2017] conftest[13790]: segfault at 0 ip 00007f1e2988f0c6 sp 00007fff68356e58 error 4 in libc-2.24.so[7f1e29765000+192000]
[Sat Aug  5 17:07:00 2017] conftest[622]: segfault at 0 ip 00000000004005e0 sp 00007ffe78418700 error 4 in conftest[400000+1000]
[Sat Aug  5 17:07:00 2017] conftest[703]: segfault at 0 ip 00007fc9651580c6 sp 00007ffc8dc60788 error 4 in libc-2.24.so[7fc96502e000+192000]
[Sat Aug  5 17:12:23 2017] conftest[20425]: segfault at 0 ip 00000000004005e0 sp 00007ffcc31a2620 error 4 in conftest[400000+1000]
[Sat Aug  5 17:12:23 2017] conftest[20455]: segfault at 0 ip 00007f089de110c6 sp 00007ffc6f7b9f18 error 4 in libc-2.24.so[7f089dce7000+192000]
[Sat Aug  5 17:19:04 2017] conftest[20968]: segfault at 0 ip 00000000004005e0 sp 00007ffccebcb550 error 4 in conftest[400000+1000]
[Sat Aug  5 17:19:05 2017] conftest[20997]: segfault at 0 ip 00007fdfcafee0c6 sp 00007ffcc6c47e98 error 4 in libc-2.24.so[7fdfcaec4000+192000]
[Sat Aug  5 17:24:57 2017] conftest[25230]: segfault at 0 ip 00000000004005e0 sp 00007fff50625ba0 error 4 in conftest[400000+1000]
[Sat Aug  5 17:24:57 2017] conftest[25563]: segfault at 0 ip 00007f5c915de0c6 sp 00007ffd3e63f998 error 4 in libc-2.24.so[7f5c914b4000+192000]
[Sat Aug  5 17:31:16 2017] conftest[22127]: segfault at 0 ip 00000000004005e0 sp 00007fffaa3b9e70 error 4 in conftest[400000+1000]
[Sat Aug  5 17:31:17 2017] conftest[22156]: segfault at 0 ip 00007f83af0aa0c6 sp 00007ffddc1e59b8 error 4 in libc-2.24.so[7f83aef80000+192000]
[Sat Aug  5 17:41:40 2017] conftest[30622]: segfault at 0 ip 00000000004005e0 sp 00007ffdb2dc63a0 error 4 in conftest[400000+1000]
[Sat Aug  5 17:41:40 2017] conftest[30656]: segfault at 0 ip 00007f5f646fd0c6 sp 00007fffbb9ed518 error 4 in libc-2.24.so[7f5f645d3000+192000]
[Sat Aug  5 17:48:28 2017] conftest[3111]: segfault at 0 ip 00000000004005e0 sp 00007ffe039bdd50 error 4 in conftest[400000+1000]
[Sat Aug  5 17:48:29 2017] conftest[3199]: segfault at 0 ip 00007f33f097f0c6 sp 00007fff165bb3a8 error 4 in libc-2.24.so[7f33f0855000+192000]

Only conftest segfaults & as mentioned this is expected. Autoconf and php causes this
This looks like a redherring for causing such an issue. Looking at the original article there was only conftest segfaults

I still think a number of people having these issues have poor setups: bios/ram, toolchain config etc... There maybe a bug somewhere but so far....

ole-m · Aug 5, 2017

Megalith said:
It was originally reported that Linux users were facing segmentation faults and, at times, crashes when running concurrent compilation loads on Ryzen CPUs, and these issues don’t appear to be fixed: Phoronix has run additional tests and found that heavy workloads remain problematic, as of Linux 4.13. These problems did not occur when tested using Intel CPUs.

We'll see now if AMD will provide public comments or if they investigate further, as they now have another reproducible test case to slam the Ryzen chips hard in just a few minutes even with SMT disabled and running at DDR4-2133. As far as whether this just affects Ryzen or also Threadripper and Epyc remains unclear. While there are many Windows reviewers out there now with Threadripper, it doesn't look like AMD will be sending any Threadripper samples to Phoronix, at least in the immediate days ahead but I have asked if at least can get SSH access to a TR system for a few hours to be able to run some Linux benchmarks. We'll see.

naib said:

Well 1hour test finished...

Only compilation workloads, no other workloads show any issues as of yet.

Code:

[jrb:~/tmp/phoronix-test-suite] 14s $ TS_CONCURRENT_TEST_RUNS=4 TOTAL_LOOP_TIME=60 ./phoronix-test-suite stress-run build-linux-kernel build-php build-apache build-imagemagick

STRESS-RUN ENVIRONMENT VARIABLES:

PTS_CONCURRENT_TEST_RUNS: Set the PTS_CONCURRENT_TEST_RUNS environment variable to specify how many tests should be run concurrently during the stress-run process. If not specified, defaults to 2.


TOTAL_LOOP_TIME set; running tests for 60 minutes

SYSTEM INFORMATION:

  PROCESSOR:          AMD Ryzen 5 1600 Six-Core @ 3.20GHz (12 Cores)
    Core Count:       6
    Thread Count:     12
    Extensions:       SSE 4.2 + AVX2 + AVX + RDRAND + FSGSBASE
    Cache Size:       512 KB
    Microcode:        0x8001126
    Scaling Driver:   acpi-cpufreq schedutil

  GRAPHICS:           NVIDIA GeForce GTX 970 4096MB (1151/3505MHz)
    OpenGL:           4.5.0
    Vulkan:           1.0.46
    Display Driver:   NVIDIA 384.59
    Screen:           1280x1024

  MOTHERBOARD:        MSI X370 GAMING PRO CARBON (MS-7A32) v1.0
    Memory:           16384MB

  DISK:               256GB OCZ VERTEX4 + 1000GB Samsung SSD 960 EVO 1TB
    File-System:      ext4
    Mount Options:    data=ordered noatime nodiratime rw
    Disk Scheduler:   NONE

  OPERATING SYSTEM:   Gentoo 2.4.1
    Kernel:           4.12.4-gentoo (x86_64)
    Desktop:          GNOME
    Display Server:   X Server 1.19.3
    Compiler:         GCC 7.1.0 + LLVM 4.0.1


pts/build-apache-1.5.1      : Test Started
pts/build-php-1.3.1         : Test Started
pts/build-php-1.3.1         : Average: 29.72 Seconds
pts/build-php-1.3.1         : Test Ended
pts/build-apache-1.5.1      : Average: 42.62 Seconds
pts/build-apache-1.5.1      : Test Ended
pts/build-php-1.3.1         : Test Started
pts/build-linux-kernel-1.7.0: Test Started
pts/build-linux-kernel-1.7.0: Average: 126.79 Seconds
pts/build-linux-kernel-1.7.0: Test Ended
pts/build-php-1.3.1         : Average: 76.76 Seconds
pts/build-php-1.3.1         : Test Ended
pts/build-imagemagick-1.7.2 : Test Started
pts/build-apache-1.5.1      : Test Started

###### STRESS RUN INTERIM REPORT ####
AUGUST 5 16:53 BST
START TIME: August 5 16:48 BST
ELAPSED TIME: 5 Minutes, 3 Seconds
TIME REMAINING: 54 Minutes, 57 Seconds
SYSTEM IP: 192.168.0.33
HOSTNAME: fluidmotion
# OF CONCURRENT TESTS: 2

TESTS CURRENTLY ACTIVE:
   - pts/build-imagemagick-1.7.2   [PID: 1735]
   - pts/build-apache-1.5.1        [PID: 1736]

TESTS IN RUN QUEUE:

TIMED APACHE COMPILATION [pts/build-apache-1.5.1]
TIMED IMAGEMAGICK COMPILATION [pts/build-imagemagick-1.7.2]
TIMED LINUX KERNEL COMPILATION [pts/build-linux-kernel-1.7.0]
TIMED PHP COMPILATION [pts/build-php-1.3.1]

SYSTEM INFORMATION:
     Processor:           AMD Ryzen 5 1600 Six-Core @ 3.20GHz (12 Cores)
     Motherboard:         MSI X370 GAMING PRO CARBON (MS-7A32) v1.0
     Memory:              16384MB
     Disk:                256GB OCZ VERTEX4 + 1000GB Samsung SSD 960 EVO 1TB
     Graphics:            NVIDIA GeForce GTX 970 4096MB (1151/3505MHz)
     Audio:               NVIDIA Generic
     OS:                  Gentoo 2.4.1
     Kernel:              4.12.4-gentoo (x86_64)
     Desktop:             GNOME
     Display Server:      X Server 1.19.3
     Display Driver:      NVIDIA 384.59
     OpenGL:              4.5.0
     Vulkan:              1.0.46
     Compiler:            GCC 7.1.0 + LLVM 4.0.1
     File-System:         ext4
     Screen Resolution:   1280x1024

     TESTS EXECUTED                   TIMES CALLED
     pts/build-apache-1.5.1:          2
     pts/build-imagemagick-1.7.2:     1
     pts/build-linux-kernel-1.7.0:    1
     pts/build-php-1.3.1:             2

SENSOR DATA:
     SENSOR                          MIN   AVG   MAX
     CPU Usage (CPU0):               6.00          66.03         100.00        Percent
     CPU Usage (CPU1):               0.00          74.09         100.00        Percent
     CPU Usage (CPU2):               7.69          70.84         100.00        Percent
     CPU Usage (CPU3):               0.00          69.61         100.00        Percent
     CPU Usage (CPU4):               6.12          76.82         100.00        Percent
     CPU Usage (CPU5):               10.00         77.41         100.00        Percent
     CPU Usage (CPU6):               6.00          75.58         100.00        Percent
     CPU Usage (CPU7):               12.00         76.63         100.00        Percent
     CPU Usage (CPU8):               0.00          66.23         100.00        Percent
     CPU Usage (CPU9):               4.00          75.47         100.00        Percent
     CPU Usage (CPU10):              2.00          71.41         100.00        Percent
     CPU Usage (CPU11):              6.00          73.96         100.00        Percent
     CPU Usage (Summary):            9.03          67.11         100.00        Percent
     GPU Temperature:                35.00         36.06         39.00         Celsius
     GPU Usage:                      0.00          5.56          35.00         Percent
     Drive Read Speed (nvme0n1):     0.00          0.01          0.11          MB/s
     Drive Write Speed (nvme0n1):    0.00          6.19          90.82         MB/s
     Memory Usage:                   1992.00       2551.06       3535.00       Megabytes
     System Temperature:             35.00         35.11         36.00         Celsius
######
pts/build-apache-1.5.1      : Average: 64.44 Seconds
pts/build-apache-1.5.1      : Test Ended
pts/build-imagemagick-1.7.2 : Average: 70.01 Seconds
pts/build-imagemagick-1.7.2 : Test Ended
pts/build-linux-kernel-1.7.0: Test Started
pts/build-php-1.3.1         : Test Started
pts/build-php-1.3.1         : Average: 75.29 Seconds
pts/build-php-1.3.1         : Test Ended
pts/build-linux-kernel-1.7.0: Average: 130.15 Seconds
pts/build-linux-kernel-1.7.0: Test Ended
pts/build-imagemagick-1.7.2 : Test Started
pts/build-linux-kernel-1.7.0: Test Started

...
######
pts/build-linux-kernel-1.7.0: Average: 146.69 Seconds
pts/build-linux-kernel-1.7.0: Test Ended
pts/build-apache-1.5.1      : Test Started
pts/build-imagemagick-1.7.2 : Average: 84.40 Seconds
pts/build-imagemagick-1.7.2 : Test Ended
pts/build-linux-kernel-1.7.0: Test Started
pts/build-apache-1.5.1      : Average: 65.96 Seconds
pts/build-apache-1.5.1      : Test Ended
pts/build-apache-1.5.1      : Test Started
pts/build-linux-kernel-1.7.0: Average: 116.00 Seconds
pts/build-linux-kernel-1.7.0: Test Ended
pts/build-php-1.3.1         : Test Started
TEST TIME EXPIRED; NO NEW TESTS WILL EXECUTE; CURRENT TESTS WILL FINISH

###### SUMMARY REPORT ####
AUGUST 5 17:48 BST
START TIME: August 5 16:48 BST
ELAPSED TIME: 1 Hour, 1 Second
WAITING FOR CURRENT TEST RUN QUEUE TO FINISH.
SYSTEM IP: 192.168.0.33
HOSTNAME: fluidmotion
# OF CONCURRENT TESTS: 2


TESTS IN RUN QUEUE:

TIMED APACHE COMPILATION [pts/build-apache-1.5.1]
TIMED IMAGEMAGICK COMPILATION [pts/build-imagemagick-1.7.2]
TIMED LINUX KERNEL COMPILATION [pts/build-linux-kernel-1.7.0]
TIMED PHP COMPILATION [pts/build-php-1.3.1]

SYSTEM INFORMATION:
     Processor:           AMD Ryzen 5 1600 Six-Core @ 3.20GHz (12 Cores)
     Motherboard:         MSI X370 GAMING PRO CARBON (MS-7A32) v1.0
     Memory:              16384MB
     Disk:                256GB OCZ VERTEX4 + 1000GB Samsung SSD 960 EVO 1TB
     Graphics:            NVIDIA GeForce GTX 970 4096MB (1151/3505MHz)
     Audio:               NVIDIA Generic
     OS:                  Gentoo 2.4.1
     Kernel:              4.12.4-gentoo (x86_64)
     Desktop:             GNOME
     Display Server:      X Server 1.19.3
     Display Driver:      NVIDIA 384.59
     OpenGL:              4.5.0
     Vulkan:              1.0.46
     Compiler:            GCC 7.1.0 + LLVM 4.0.1
     File-System:         ext4
     Screen Resolution:   1280x1024

     TESTS EXECUTED                   TIMES CALLED
     pts/build-apache-1.5.1:          13
     pts/build-imagemagick-1.7.2:     14
     pts/build-linux-kernel-1.7.0:    17
     pts/build-php-1.3.1:             11

SENSOR DATA:
     SENSOR                          MIN   AVG   MAX
     CPU Usage (CPU0):               0.00          77.93         100.00        Percent
     CPU Usage (CPU1):               0.00          78.08         100.00        Percent
     CPU Usage (CPU2):               0.00          80.86         100.00        Percent
     CPU Usage (CPU3):               0.00          80.05         100.00        Percent
     CPU Usage (CPU4):               1.96          80.75         100.00        Percent
     CPU Usage (CPU5):               0.00          80.12         100.00        Percent
     CPU Usage (CPU6):               0.00          81.31         100.00        Percent
     CPU Usage (CPU7):               0.00          77.68         100.00        Percent
     CPU Usage (CPU8):               0.00          78.57         100.00        Percent
     CPU Usage (CPU9):               0.00          80.20         100.00        Percent
     CPU Usage (CPU10):              0.00          80.04         100.00        Percent
     CPU Usage (CPU11):              0.00          77.90         100.00        Percent
     CPU Usage (Summary):            0.33          76.81         100.00        Percent
     GPU Temperature:                35.00         35.92         42.00         Celsius
     GPU Usage:                      0.00          4.03          35.00         Percent
     Drive Read Speed (nvme0n1):     0.00          0.00          0.11          MB/s
     Drive Write Speed (nvme0n1):    0.00          3.77          159.76        MB/s
     Memory Usage:                   1992.00       2827.03       4218.00       Megabytes
     System Temperature:             35.00         36.40         37.00         Celsius
######

⌂169% [jrb:~/tmp/phoronix-test-suite] 1h0m2s $ pts/build-php-1.3.1         : Average: 27.53 Seconds
pts/build-php-1.3.1         : Test Ended

######
pts/build-linux-kernel-1.7.0: Average: 146.69 Seconds
pts/build-linux-kernel-1.7.0: Test Ended
pts/build-apache-1.5.1      : Test Started
pts/build-imagemagick-1.7.2 : Average: 84.40 Seconds
pts/build-imagemagick-1.7.2 : Test Ended
pts/build-linux-kernel-1.7.0: Test Started
pts/build-apache-1.5.1      : Average: 65.96 Seconds
pts/build-apache-1.5.1      : Test Ended
pts/build-apache-1.5.1      : Test Started
pts/build-linux-kernel-1.7.0: Average: 116.00 Seconds
pts/build-linux-kernel-1.7.0: Test Ended
pts/build-php-1.3.1         : Test Started
TEST TIME EXPIRED; NO NEW TESTS WILL EXECUTE; CURRENT TESTS WILL FINISH

###### SUMMARY REPORT ####
AUGUST 5 17:48 BST
START TIME: August 5 16:48 BST
ELAPSED TIME: 1 Hour, 1 Second
WAITING FOR CURRENT TEST RUN QUEUE TO FINISH.
SYSTEM IP: 192.168.0.33
HOSTNAME: fluidmotion
# OF CONCURRENT TESTS: 2


TESTS IN RUN QUEUE:

TIMED APACHE COMPILATION [pts/build-apache-1.5.1]
TIMED IMAGEMAGICK COMPILATION [pts/build-imagemagick-1.7.2]
TIMED LINUX KERNEL COMPILATION [pts/build-linux-kernel-1.7.0]
TIMED PHP COMPILATION [pts/build-php-1.3.1]

SYSTEM INFORMATION:
     Processor:           AMD Ryzen 5 1600 Six-Core @ 3.20GHz (12 Cores)
     Motherboard:         MSI X370 GAMING PRO CARBON (MS-7A32) v1.0
     Memory:              16384MB
     Disk:                256GB OCZ VERTEX4 + 1000GB Samsung SSD 960 EVO 1TB
     Graphics:            NVIDIA GeForce GTX 970 4096MB (1151/3505MHz)
     Audio:               NVIDIA Generic
     OS:                  Gentoo 2.4.1
     Kernel:              4.12.4-gentoo (x86_64)
     Desktop:             GNOME
     Display Server:      X Server 1.19.3
     Display Driver:      NVIDIA 384.59
     OpenGL:              4.5.0
     Vulkan:              1.0.46
     Compiler:            GCC 7.1.0 + LLVM 4.0.1
     File-System:         ext4
     Screen Resolution:   1280x1024

     TESTS EXECUTED                   TIMES CALLED
     pts/build-apache-1.5.1:          13
     pts/build-imagemagick-1.7.2:     14
     pts/build-linux-kernel-1.7.0:    17
     pts/build-php-1.3.1:             11

SENSOR DATA:
     SENSOR                          MIN   AVG   MAX
     CPU Usage (CPU0):               0.00          77.93         100.00        Percent
     CPU Usage (CPU1):               0.00          78.08         100.00        Percent
     CPU Usage (CPU2):               0.00          80.86         100.00        Percent
     CPU Usage (CPU3):               0.00          80.05         100.00        Percent
     CPU Usage (CPU4):               1.96          80.75         100.00        Percent
     CPU Usage (CPU5):               0.00          80.12         100.00        Percent
     CPU Usage (CPU6):               0.00          81.31         100.00        Percent
     CPU Usage (CPU7):               0.00          77.68         100.00        Percent
     CPU Usage (CPU8):               0.00          78.57         100.00        Percent
     CPU Usage (CPU9):               0.00          80.20         100.00        Percent
     CPU Usage (CPU10):              0.00          80.04         100.00        Percent
     CPU Usage (CPU11):              0.00          77.90         100.00        Percent
     CPU Usage (Summary):            0.33          76.81         100.00        Percent
     GPU Temperature:                35.00         35.92         42.00         Celsius
     GPU Usage:                      0.00          4.03          35.00         Percent
     Drive Read Speed (nvme0n1):     0.00          0.00          0.11          MB/s
     Drive Write Speed (nvme0n1):    0.00          3.77          159.76        MB/s
     Memory Usage:                   1992.00       2827.03       4218.00       Megabytes
     System Temperature:             35.00         36.40         37.00         Celsius
######

⌂169% [jrb:~/tmp/phoronix-test-suite] 1h0m2s $ pts/build-php-1.3.1         : Average: 27.53 Seconds
pts/build-php-1.3.1         : Test Ended

looking at dmesg:

Code:

[Sat Aug  5 16:48:54 2017] conftest[4564]: segfault at 0 ip 00000000004005e0 sp 00007fffed3c10d0 error 4 in conftest[400000+1000]
[Sat Aug  5 16:48:55 2017] conftest[4817]: segfault at 0 ip 00007fb80c9a10c6 sp 00007ffe72b5a8a8 error 4 in libc-2.24.so[7fb80c877000+192000]
[Sat Aug  5 16:49:59 2017] conftest[4887]: segfault at 0 ip 00000000004005e0 sp 00007fffb93595d0 error 4 in conftest[400000+1000]
[Sat Aug  5 16:49:59 2017] conftest[4965]: segfault at 0 ip 00007f600bd030c6 sp 00007fffb5e32228 error 4 in libc-2.24.so[7f600bbd9000+192000]
[Sat Aug  5 16:54:20 2017] conftest[22456]: segfault at 0 ip 00000000004005e0 sp 00007ffd3cc2fca0 error 4 in conftest[400000+1000]
[Sat Aug  5 16:54:20 2017] conftest[22523]: segfault at 0 ip 00007f750fe4e0c6 sp 00007fff5ad2cdc8 error 4 in libc-2.24.so[7f750fd24000+192000]
[Sat Aug  5 17:01:09 2017] conftest[13761]: segfault at 0 ip 00000000004005e0 sp 00007ffc6d8ff650 error 4 in conftest[400000+1000]
[Sat Aug  5 17:01:09 2017] conftest[13790]: segfault at 0 ip 00007f1e2988f0c6 sp 00007fff68356e58 error 4 in libc-2.24.so[7f1e29765000+192000]
[Sat Aug  5 17:07:00 2017] conftest[622]: segfault at 0 ip 00000000004005e0 sp 00007ffe78418700 error 4 in conftest[400000+1000]
[Sat Aug  5 17:07:00 2017] conftest[703]: segfault at 0 ip 00007fc9651580c6 sp 00007ffc8dc60788 error 4 in libc-2.24.so[7fc96502e000+192000]
[Sat Aug  5 17:12:23 2017] conftest[20425]: segfault at 0 ip 00000000004005e0 sp 00007ffcc31a2620 error 4 in conftest[400000+1000]
[Sat Aug  5 17:12:23 2017] conftest[20455]: segfault at 0 ip 00007f089de110c6 sp 00007ffc6f7b9f18 error 4 in libc-2.24.so[7f089dce7000+192000]
[Sat Aug  5 17:19:04 2017] conftest[20968]: segfault at 0 ip 00000000004005e0 sp 00007ffccebcb550 error 4 in conftest[400000+1000]
[Sat Aug  5 17:19:05 2017] conftest[20997]: segfault at 0 ip 00007fdfcafee0c6 sp 00007ffcc6c47e98 error 4 in libc-2.24.so[7fdfcaec4000+192000]
[Sat Aug  5 17:24:57 2017] conftest[25230]: segfault at 0 ip 00000000004005e0 sp 00007fff50625ba0 error 4 in conftest[400000+1000]
[Sat Aug  5 17:24:57 2017] conftest[25563]: segfault at 0 ip 00007f5c915de0c6 sp 00007ffd3e63f998 error 4 in libc-2.24.so[7f5c914b4000+192000]
[Sat Aug  5 17:31:16 2017] conftest[22127]: segfault at 0 ip 00000000004005e0 sp 00007fffaa3b9e70 error 4 in conftest[400000+1000]
[Sat Aug  5 17:31:17 2017] conftest[22156]: segfault at 0 ip 00007f83af0aa0c6 sp 00007ffddc1e59b8 error 4 in libc-2.24.so[7f83aef80000+192000]
[Sat Aug  5 17:41:40 2017] conftest[30622]: segfault at 0 ip 00000000004005e0 sp 00007ffdb2dc63a0 error 4 in conftest[400000+1000]
[Sat Aug  5 17:41:40 2017] conftest[30656]: segfault at 0 ip 00007f5f646fd0c6 sp 00007fffbb9ed518 error 4 in libc-2.24.so[7f5f645d3000+192000]
[Sat Aug  5 17:48:28 2017] conftest[3111]: segfault at 0 ip 00000000004005e0 sp 00007ffe039bdd50 error 4 in conftest[400000+1000]
[Sat Aug  5 17:48:29 2017] conftest[3199]: segfault at 0 ip 00007f33f097f0c6 sp 00007fff165bb3a8 error 4 in libc-2.24.so[7f33f0855000+192000]

Only conftest segfaults & as mentioned this is expected. Autoconf and php causes this
This looks like a redherring for causing such an issue. Looking at the original article there was only conftest segfaults

I still think a number of people having these issues have poor setups: bios/ram, toolchain config etc... There maybe a bug somewhere but so far....

Happens regardless of setups it seems, ECC, No ecc, OC, No OC, Overvolting, No overvolt, fresh OS, old OS, Ubuntu,fedora +++
it's a curios issue cause its so limited to one specific load which isn't really specific

I'm sure a microcode will fix it, Intel have had a few over the years too which always get sorted in a microcode without negative impact.
The worst is that they do an Intel so far and saying absolutely nothing about it

funks · Aug 5, 2017

ole-m said:
Happens regardless of setups it seems, ECC, No ecc, OC, No OC, Overvolting, No overvolt, fresh OS, old OS, Ubuntu,fedora +++
it's a curios issue cause its so limited to one specific load which isn't really specific

I'm sure a microcode will fix it, Intel have had a few over the years too which always get sorted in a microcode without negative impact.
The worst is that they do an Intel so far and saying absolutely nothing about it

On my tests (building GCC 7.1) running on a build loop - I get Internal Compiler Errors, or one of make's utils failing and etc on both my ryzen boxes which never happens on my Intel box. Given that these tools have been around for a really long time and developers on general come to rely on them working reliably, not really sure how this got past AMD.

BIOS settings are bone stock with ram at 2133 MT/s. Seems pretty stable under Windows though (then again, I don't run this type of work on Windows)

Jim Kim · Aug 5, 2017

Ruh Roh
Linux never forgets http://www.tomshardware.co.uk/intel-admits-problems-with-pentium-iii-1,review-230-3.html

msroadkill612 · Aug 6, 2017

https://hothardware.com/news/freebsd-programmers-report-ryzen-smt-bug-that-hangs-or-resets-machines

Cooe
" As an AMD employee who's been following & been involved with the community on this issue for months now, you KNOW that isn't actually true. The segfaults from the php build test that were seen on EPYC are exactly what you say they are. Red herrings from the way Michael wrote his build-php test (using conftest), BUT that DOESN'T change that fact many Ryzen AM4 chips will segfault during almost any kind of heavy code compilation in Linux (or WSL in Windows; native compilation in Windows w/ Visual Studio doesn't seem to be effected for some reason), for reasons totally unrelated to conftest. While the fact that it hasn't appeared in EPYC is GREAT news! (because that would mean the B2 Zeppelin stepping has fixed the paper in hardware; oh and a constantly segfaulting chip would be DOA for the data center), trying to pretend the entire problem has gone away/ never existed is a really bad look. (And I say these things as a massive AMD fan, my current rig is an R7 1700 @ 4.0GHz & R9 Fury X; there is not an ounce of anti-AMD bias in my body)."

msroadkill612 · Aug 6, 2017

If not having much luck finding why it doesnt work on some ryzens, then maybe they should be focussing on those where it does? Whats different about those rigs?

naib · Aug 6, 2017

msroadkill612 said:
If not having much luck finding why it doesnt work on some ryzens, then maybe they should be focussing on those where it does? Whats different about those rigs?

I have been trying that over on the gentoo forums and Phoronix since around march this year. Those with a working system generally are happy and carry on. Those with a non-functioning system will make noise & rightly so. Likewise the problem with Phoronix is the owner is a clickbait whore (and the recent articles are proof of that) and likewise the residence are trolls. This is why I prefer dealing with gentoo users on the gentoo forums. Gentoo is more likely to higlight an actual issue due to custom CFLAG builds such that theior custom install will ONLY work on their setup, while an ubuntu install can be unplugged from an intel and plugged into an amd and just boot (compiled for the lowest common denominator, like windows)

I started a tracker to try to find a common area of issues and unfortunately it was filled with non-working systems. For it to be useful it needed a number of working. I strongly suspect there are aspects of RAM timings at play here, especially as every BIOS so far have had "incorrect" RAM timings& equally Ryzen has been seen to be sensitive to RAM

I am not saying that there isn't an issue, just right now people are frustrated and they are not piecing together the issue.

DPI · Aug 6, 2017

This is why I stick to Intel. No weird compatibility bullshit cropping up.

BloodyIron · Aug 6, 2017

How exactly was this not caught in fab QC?

Ocellaris · Aug 6, 2017

BloodyIron said:
How exactly was this not caught in fab QC?

Probably was (if it's real). It likely wasn't problem enough to hold up release since it appears to be affecting a small number of overall users. All major CPUs, GPUs, and SOCs have bugs, most of which are minor and never seen by a user.

Monkey God · Aug 6, 2017

From Phoronix:

Update [5 August]: As a result of feedback, currently working on some updated results. As some have pointed out, the conftest segmentation faults aren't specific to Ryzen, so updating the tests to avoid confusion. Though one area being explored now as well is the Clang segmentation faults shown in the original article, not originating from conftest as well as Clang being able to yield the system hanging hard where the system is unresponsive and SSH is not working. Plus also incorporating more Ryzen-Kill tests as outlined in the aforelinked article. As many readers have pointed out, BSD developers have also discovered a Ryzen bug. More details soon.

Basically some people duplicating his work got the same issue with an Intel CPU. Turns out this particular issue is PHP related.

https://community.amd.com/thread/215773?start=645&tstart=0

While Ryzen may have some issues, this particular case isn't one of them.

Ocellaris · Aug 6, 2017

https://svnweb.freebsd.org/base?view=revision&revision=321899

Based on that, looks like they have a software workaround to avoid accessing the segfault area if memory. Though it isn't clear if this is the same issue. The workaround will get patched into OS kernels that need it, fairly common for Linux.

naib · Aug 6, 2017

Ocellaris said:
https://svnweb.freebsd.org/base?view=revision&revision=321899

Based on that, looks like they have a software workaround to avoid accessing the segfault area if memory. Though it isn't clear if this is the same issue. The workaround will get patched into OS kernels that need it, fairly common for Linux.

Thats BSD, not Linux...

this should help linux reproduce the issue IF it is ryzen-based and not BSD based. if a similar testcase causes the same affect then it can be narrowed down to see exactly what is causing the issue

naib · Aug 6, 2017

Monkey God said:
From Phoronix:

Basically some people duplicating his work got the same issue with an Intel CPU. Turns out this particular issue is PHP related.

https://community.amd.com/thread/215773?start=645&tstart=0

While Ryzen may have some issues, this particular case isn't one of them.

I already said that in this thread...

LBJM · Aug 6, 2017

I'd like to thank all the AMD fanbois for buying this version of Ryzen and living with all the bugs, so later Ryzen chips won't have this problem! The problem here is AMD does not offer enough developer support to fix issues in a timely manner.

They had issues in the Athlon XP/MP and opteron days that if they weren't fixed by the community you had to buy the next gen hardware to get a fix. People say all the nasty things about Intel, but at least they work on current gen problems and supply quick bios updates. The Kaby Lake HT problem already has a bios update.

Monkey God · Aug 6, 2017

naib said:
I already said that in this thread...

Neat. My post was concise and to the point.

Lord of Shadows · Aug 6, 2017

Supposedly this is FUD as people were able to get the same php / conftest segfaults on intel chips

JustReason · Aug 6, 2017

LBJM said:
I'd like to thank all the AMD fanbois for buying this version of Ryzen and living with all the bugs, so later Ryzen chips won't have this problem! The problem here is AMD does not offer enough developer support to fix issues in a timely manner.

They had issues in the Athlon XP/MP and opteron days that if they weren't fixed by the community you had to buy the next gen hardware to get a fix. People say all the nasty things about Intel, but at least they work on current gen problems and supply quick bios updates. The Kaby Lake HT problem already has a bios update.

BS BS and a whole lot of BS. Intel had an issue with HT for more than a year that just recently got a bios fix this year. A year is far greater than 4-5mths AMD has had thus far. Falls from high horses really hurt, thus probably best not to mount one.

LBJM · Aug 6, 2017

JustReason said:
BS BS and a whole lot of BS. Intel had an issue with HT for more than a year that just recently got a bios fix this year. A year is far greater than 4-5mths AMD has had thus far. Falls from high horses really hurt, thus probably best not to mount one.

TRY five years not 4-5 months. Take the blinders off.
Zen aka Ryzen has been under development for years since 2012 (http://techreport.com/review/28228/amd-zen-chips-headed-to-desktops-servers-in-2016) and even though they are a year late upon release you ignore the fact that AMD once again failed at QC. They hasve to resort to making rev B chips because Ryzen is flawed (https://www.techpowerup.com/234476/amd-readies-b2-stepping-of-the-ryzen-summit-ridge-silicon)

Deleted whining member 223597 · Aug 6, 2017

LBJM said:
TRY five years not 4-5 months. Take the blinders off.
Zen aka Ryzen has been under development for years since 2012 (http://techreport.com/review/28228/amd-zen-chips-headed-to-desktops-servers-in-2016) and even though they are a year late upon release you ignore the fact that AMD once again failed at QC. They hasve to resort to making rev B chips because Ryzen is flawed (https://www.techpowerup.com/234476/amd-readies-b2-stepping-of-the-ryzen-summit-ridge-silicon)

What's Intel's excuse then?

naib · Aug 6, 2017

Lord of Shadows said:
Supposedly this is FUD as people were able to get the same php / conftest segfaults on intel chips

its worse then that... php autoconf will aim to cause segfaults so it knows what it shouldn't do.

The owner of Phoronix is a clickbait whore and over-sensationalises headlines for clickbait. This kind of error message would only really be known by distro builders & gentoo/slackware so I am not surprised Michael didn't know that HOWEVER... 30seconds on google would have shown it & equally he should have changed the headline once it was clear his testcase wasn't agrivating Ryzen.

AGESA 1.0.0.6 & using > GCC-6.x is showing improved stability across the board but there are still apparent stress tests that are aggravating it BUT it isn't universal. So far it is Ryzen7 people complaining so I wonder if the QA to meet initial demands may have let through some chips that maybe were not good enough for RYzen7 and should have had the dodgy cores disabled to create a bunch of Ryzen5.

The BSD issue is unique however, they appear to be honing in on something & it appears memory related.

LBJM · Aug 6, 2017

-Strelok- said:
What's Intel's excuse then?

The better question is: Where did you learn to do math?
The earliest hardocp review of kaby lake is from December 2016, that's only 9 months https://www.hardocp.com/article/2016/12/05/intel_core_i77700k_cpu_synthetic_benchmark_sneak_peek/

LBJM · Aug 6, 2017

naib said:
its worse then that... php autoconf will aim to cause segfaults so it knows what it shouldn't do.

The owner of Phoronix is a clickbait whore and over-sensationalises headlines for clickbait.

I agree with this 100% and that is why I stopped going to that web site. The guy probably couldn't ever setup lm sensors.

JustReason · Aug 6, 2017

LBJM said:
The better question is: Where did you learn to do math?
The earliest hardocp review of kaby lake is from December 2016, that's only 9 months https://www.hardocp.com/article/2016/12/05/intel_core_i77700k_cpu_synthetic_benchmark_sneak_peek/

Seriously? We could ask the same of you. 9 mths is far greater than 5.

JustReason · Aug 6, 2017

LBJM said:
The better question is: Where did you learn to do math?
The earliest hardocp review of kaby lake is from December 2016, that's only 9 months https://www.hardocp.com/article/2016/12/05/intel_core_i77700k_cpu_synthetic_benchmark_sneak_peek/

Actually decided to go look for the info to put this in perspective.

https://lists.debian.org/debian-devel/2017/06/msg00308.html

On 2017-05-29, Mark Shinwell, a core OCaml toolchain developer,
contacted the Debian developer responsible for the intel-microcode
package with key information about a Intel processor issue that could be
easily triggered by the OCaml compiler.

The issue was being investigated by the OCaml community since
2017-01-06, with reports of malfunctions going at least as far back as
Q2 2016. It was narrowed down to Skylake with hyper-threading, which is
a strong indicative of a processor defect. Intel was contacted about
it, but did not provide further feedback as far as we know.

Deleted whining member 223597 · Aug 6, 2017

LBJM said:
The better question is: Where did you learn to do math?
The earliest hardocp review of kaby lake is from December 2016, that's only 9 months https://www.hardocp.com/article/2016/12/05/intel_core_i77700k_cpu_synthetic_benchmark_sneak_peek/

So Intel just decided to come up with kabylake in a few weeks/months? LOL.

ole-m · Aug 7, 2017

funks said:
On my tests (building GCC 7.1) running on a build loop - I get Internal Compiler Errors, or one of make's utils failing and etc on both my ryzen boxes which never happens on my Intel box. Given that these tools have been around for a really long time and developers on general come to rely on them working reliably, not really sure how this got past AMD.

BIOS settings are bone stock with ram at 2133 MT/s. Seems pretty stable under Windows though (then again, I don't run this type of work on Windows)

seems stable ?

I can pretty much confirm anything I throw on mine except gcc\clang in linux is 100% stable.
I even started comparing result of variable workload with high memory usage and things that fit inside cache's to stress test, compared against my xeon and I can only report no error of end result occur in an suite of applications\programs.
Thus it must be extremely specific.

I have nothing else to add to this issue and it's out of my technical expertise from now on.

Ryzen Linux Users Are Still Facing Issues with Heavy Compilation Loads

24-bit/48kHz

[H]ard|Gawd

Limp Gawd

[H]ard|Gawd

Fully [H]

Gawd

[H]ard|Gawd

Limp Gawd

Limp Gawd

2[H]4U

n00b

n00b

[H]ard|Gawd

[H]F Junkie

2[H]4U

Fully [H]

Mangina Full of Sand

Fully [H]

[H]ard|Gawd

[H]ard|Gawd

Limp Gawd

Mangina Full of Sand

2[H]4U

razor1 is my Lover

Limp Gawd

Deleted whining member 223597

Guest

[H]ard|Gawd

Limp Gawd

Limp Gawd

razor1 is my Lover

razor1 is my Lover

Deleted whining member 223597

Guest

Limp Gawd