OpenBLAS: amax:samax utest failure

System configuration:

Compile host is ODROID-C2, but I’m running the compile inside of a docker image that was created from a NI RoboRIO disk image (ARMv7, Cortex A9). I’m also using setarch linux32.
Compilers are gcc 6.3.0, gfortran 6.3.0
OpenBLAS 0.3.4 (but the error occurs on 0.2.20 also)

Compile was via:

make TARGET=CORTEXA9 PREFIX=/usr/local

Here’s the output:

./openblas_utest 
TEST 1/23 amax:samax [FAIL]
  ERR: test_amax.c:44  expected 3.300e+00, got 4.204e-45 (diff 3.300e+00, tol 1.000e-04)
...
RESULTS: 23 tests (22 ok, 1 failed, 0 skipped) ran in 1860 ms

What steps should I take next to diagnose this issue? Thanks!

About this issue

Original URL
State: closed
Created 6 years ago
Comments: 68 (21 by maintainers)

Commits related to this issue

rebase? (#1) * With the Intel compiler on Linux, prefer ifort for the final link step icc has known problems with mixed-language builds that ifort can handle just fine. Fixes #1956 * Rename op... — committed to TiborGY/OpenBLAS by TiborGY 5 years ago

Most upvoted comments

I’ve gotten it to compile this year (with gcc 7.3.0 and OpenBLAS 0.3.7). Thanks!

virtuald on Dec 20, 2019

Few things to note.

Regarding amax.

Using iamax_vfp.S for amax kernel is wrong. iamax_vfp.S only has the implementation to find the index of the max value. So KERNEL.ARMV6 needs to be corrected. This looks to be long standing undetected issue in OpenBLAS.
For the same reason, #2142 is not correct. Needs to be reverted. This will break isamax .
The current implementation in iamax_vfp.S works for hardfp for samax because inadvertently it stores the max value in s0 where it is supposed to end up.

Regarding CHERK

Looks to be a compiler/environment issue. Could you try replacing -O2 by -O0 in Makefile.system for FCOMMON_OPT and COMMON_OPT
Also try setting “ulimit -s unlimited”

ashwinyes on May 29, 2019

Both the AMAX bug and the missing utest build should be fixed now on the develop branch. Unfortunately I have not yet been able to set up a (cross)compiler environment for softfp that includes gfortran, so I cannot investigate the CHERK error from the original report right now.

martin-frbg on May 28, 2019