[amd] ** COMPLETE AMD ** revert to itscrd90 logs for tput/tmad tests

Revert "[amd] rerun 30 tmad tests on LUMI against AMD GPUs - all as expected (heft fail madgraph5#833, skip ggttggg madgraph5#933, gqttq crash madgraph5#806)"
This reverts commit 458b834.

Revert "[amd] rerun 96 tput builds and tests on LUMI worker node (small-g 72h) - all as expected"
This reverts commit 0c947d1.

epochX/cudacpp/tmad/logs_heftggbb_mad/log_heftggbb_mad_f_inl0_hrd0.txt

@@ -1,41 +1,41 @@
-Working directory (build): /users/valassia/GPU2024/madgraph4gpu/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx
+Working directory (build): /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx
 
-make USEBUILDDIR=1 BACKEND=hip
+
+make USEBUILDDIR=1 BACKEND=cuda
 
 make USEBUILDDIR=1 BACKEND=cppnone
-make[1]: Entering directory '/pfs/lustrep3/scratch/project_465001114/valassia/GPU2024/madgraph4gpu/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
-make[1]: Entering directory '/pfs/lustrep3/scratch/project_465001114/valassia/GPU2024/madgraph4gpu/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
 
 make USEBUILDDIR=1 BACKEND=cppsse4
-
 make USEBUILDDIR=1 BACKEND=cppavx2
-make[1]: Entering directory '/pfs/lustrep3/scratch/project_465001114/valassia/GPU2024/madgraph4gpu/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
-make[1]: Entering directory '/pfs/lustrep3/scratch/project_465001114/valassia/GPU2024/madgraph4gpu/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
 
 make USEBUILDDIR=1 BACKEND=cpp512y
+make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
+make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
+make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
+make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
 
 make USEBUILDDIR=1 BACKEND=cpp512z
-make[1]: Entering directory '/pfs/lustrep3/scratch/project_465001114/valassia/GPU2024/madgraph4gpu/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
-make[1]: Entering directory '/pfs/lustrep3/scratch/project_465001114/valassia/GPU2024/madgraph4gpu/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
+make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
+make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
 make[1]: Nothing to be done for 'all'.
-make[1]: Leaving directory '/pfs/lustrep3/scratch/project_465001114/valassia/GPU2024/madgraph4gpu/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
+make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
 make[1]: Nothing to be done for 'all'.
-make[1]: Leaving directory '/pfs/lustrep3/scratch/project_465001114/valassia/GPU2024/madgraph4gpu/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
+make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
 make[1]: Nothing to be done for 'all'.
-make[1]: Leaving directory '/pfs/lustrep3/scratch/project_465001114/valassia/GPU2024/madgraph4gpu/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
+make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
 make[1]: Nothing to be done for 'all'.
-make[1]: Leaving directory '/pfs/lustrep3/scratch/project_465001114/valassia/GPU2024/madgraph4gpu/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
+make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
 make[1]: Nothing to be done for 'all'.
-make[1]: Leaving directory '/pfs/lustrep3/scratch/project_465001114/valassia/GPU2024/madgraph4gpu/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
+make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
 make[1]: Nothing to be done for 'all'.
-make[1]: Leaving directory '/pfs/lustrep3/scratch/project_465001114/valassia/GPU2024/madgraph4gpu/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
+make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx'
 
 OMP_NUM_THREADS=
 
-DATE: 2024-09-18_23:40:55
+DATE: 2024-09-18_17:32:29
 
-On uan01 [CPU: AMD EPYC 7A53 64-Core Processor] [GPU: AMD INSTINCT MI200]:
-Working directory (run): /users/valassia/GPU2024/madgraph4gpu/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx
+On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
+Working directory (run): /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx
 
 *** (1) EXECUTE MADEVENT_FORTRAN (create results.dat) ***
 --------------------
@@ -49,18 +49,18 @@ CUDACPP_RUNTIME_VECSIZEUSED = 8192
 0 ! Helicity Sum/event 0=exact
 1 ! ICONFIG number (1-N) for single-diagram enhancement multi-channel (NB used even if suppress amplitude is 0!)
 --------------------
-Executing ' ./madevent_fortran < /tmp/valassia/input_heftggbb_x1_fortran > /tmp/valassia/output_heftggbb_x1_fortran'
- [OPENMPTH] omp_get_max_threads/nproc = 1/128
+Executing ' ./madevent_fortran < /tmp/avalassi/input_heftggbb_x1_fortran > /tmp/avalassi/output_heftggbb_x1_fortran'
+ [OPENMPTH] omp_get_max_threads/nproc = 1/4
  [NGOODHEL] ngoodhel/ncomb = 16/16
  [XSECTION] VECSIZE_USED = 8192
  [XSECTION] MultiChannel = TRUE
  [XSECTION] Configuration = 1
  [XSECTION] ChannelId = 1
- [XSECTION] Cross section = 2.016 [2.0160081479755330] fbridge_mode=0
+ [XSECTION] Cross section = 2.016 [2.0160081479755183] fbridge_mode=0
  [UNWEIGHT] Wrote 3371 events (found 6399 events)
- [COUNTERS] PROGRAM TOTAL          :    1.0731s
- [COUNTERS] Fortran Overhead ( 0 ) :    1.0367s
- [COUNTERS] Fortran MEs      ( 1 ) :    0.0364s for     8192 events => throughput is 2.25E+05 events/s
+ [COUNTERS] PROGRAM TOTAL          :    0.9597s
+ [COUNTERS] Fortran Overhead ( 0 ) :    0.9125s
+ [COUNTERS] Fortran MEs      ( 1 ) :    0.0473s for     8192 events => throughput is 1.73E+05 events/s
 
 *** (1) EXECUTE MADEVENT_FORTRAN x1 (create events.lhe) ***
 --------------------
@@ -74,18 +74,18 @@ CUDACPP_RUNTIME_VECSIZEUSED = 8192
 0 ! Helicity Sum/event 0=exact
 1 ! ICONFIG number (1-N) for single-diagram enhancement multi-channel (NB used even if suppress amplitude is 0!)
 --------------------
-Executing ' ./madevent_fortran < /tmp/valassia/input_heftggbb_x1_fortran > /tmp/valassia/output_heftggbb_x1_fortran'
- [OPENMPTH] omp_get_max_threads/nproc = 1/128
+Executing ' ./madevent_fortran < /tmp/avalassi/input_heftggbb_x1_fortran > /tmp/avalassi/output_heftggbb_x1_fortran'
+ [OPENMPTH] omp_get_max_threads/nproc = 1/4
  [NGOODHEL] ngoodhel/ncomb = 16/16
  [XSECTION] VECSIZE_USED = 8192
  [XSECTION] MultiChannel = TRUE
  [XSECTION] Configuration = 1
  [XSECTION] ChannelId = 1
- [XSECTION] Cross section = 2.016 [2.0160081479755330] fbridge_mode=0
+ [XSECTION] Cross section = 2.016 [2.0160081479755183] fbridge_mode=0
  [UNWEIGHT] Wrote 1652 events (found 1657 events)
- [COUNTERS] PROGRAM TOTAL          :    0.7254s
- [COUNTERS] Fortran Overhead ( 0 ) :    0.6890s
- [COUNTERS] Fortran MEs      ( 1 ) :    0.0364s for     8192 events => throughput is 2.25E+05 events/s
+ [COUNTERS] PROGRAM TOTAL          :    0.4554s
+ [COUNTERS] Fortran Overhead ( 0 ) :    0.4080s
+ [COUNTERS] Fortran MEs      ( 1 ) :    0.0474s for     8192 events => throughput is 1.73E+05 events/s
 
 *** (1) EXECUTE MADEVENT_FORTRAN x10 (create events.lhe) ***
 --------------------
@@ -99,18 +99,18 @@ CUDACPP_RUNTIME_VECSIZEUSED = 8192
 0 ! Helicity Sum/event 0=exact
 1 ! ICONFIG number (1-N) for single-diagram enhancement multi-channel (NB used even if suppress amplitude is 0!)
 --------------------
-Executing ' ./madevent_fortran < /tmp/valassia/input_heftggbb_x10_fortran > /tmp/valassia/output_heftggbb_x10_fortran'
- [OPENMPTH] omp_get_max_threads/nproc = 1/128
+Executing ' ./madevent_fortran < /tmp/avalassi/input_heftggbb_x10_fortran > /tmp/avalassi/output_heftggbb_x10_fortran'
+ [OPENMPTH] omp_get_max_threads/nproc = 1/4
  [NGOODHEL] ngoodhel/ncomb = 16/16
  [XSECTION] VECSIZE_USED = 8192
  [XSECTION] MultiChannel = TRUE
  [XSECTION] Configuration = 1
  [XSECTION] ChannelId = 1
- [XSECTION] Cross section = 2.034 [2.0336713375865552] fbridge_mode=0
+ [XSECTION] Cross section = 2.034 [2.0336713375865285] fbridge_mode=0
  [UNWEIGHT] Wrote 1707 events (found 1712 events)
- [COUNTERS] PROGRAM TOTAL          :    5.0374s
- [COUNTERS] Fortran Overhead ( 0 ) :    4.6751s
- [COUNTERS] Fortran MEs      ( 1 ) :    0.3623s for    81920 events => throughput is 2.26E+05 events/s
+ [COUNTERS] PROGRAM TOTAL          :    2.0424s
+ [COUNTERS] Fortran Overhead ( 0 ) :    1.5675s
+ [COUNTERS] Fortran MEs      ( 1 ) :    0.4749s for    81920 events => throughput is 1.72E+05 events/s
 
 *** (2-none) EXECUTE MADEVENT_CPP x1 (create events.lhe) ***
 --------------------
@@ -124,34 +124,34 @@ CUDACPP_RUNTIME_VECSIZEUSED = 8192
 0 ! Helicity Sum/event 0=exact
 1 ! ICONFIG number (1-N) for single-diagram enhancement multi-channel (NB used even if suppress amplitude is 0!)
 --------------------
-Executing ' ./build.none_f_inl0_hrd0/madevent_cpp < /tmp/valassia/input_heftggbb_x1_cudacpp > /tmp/valassia/output_heftggbb_x1_cudacpp'
+Executing ' ./build.none_f_inl0_hrd0/madevent_cpp < /tmp/avalassi/input_heftggbb_x1_cudacpp > /tmp/avalassi/output_heftggbb_x1_cudacpp'
 DEBUG: MEK processed 8192 events across 4 channels { 1 : 8192 }
- [OPENMPTH] omp_get_max_threads/nproc = 1/128
+ [OPENMPTH] omp_get_max_threads/nproc = 1/4
  [NGOODHEL] ngoodhel/ncomb = 16/16
  [XSECTION] VECSIZE_USED = 8192
  [XSECTION] MultiChannel = TRUE
  [XSECTION] Configuration = 1
  [XSECTION] ChannelId = 1
- [XSECTION] Cross section = 2.016 [2.0160406546722180] fbridge_mode=1
+ [XSECTION] Cross section = 2.016 [2.0160406825242951] fbridge_mode=1
  [UNWEIGHT] Wrote 1653 events (found 1658 events)
- [COUNTERS] PROGRAM TOTAL          :    0.7172s
- [COUNTERS] Fortran Overhead ( 0 ) :    0.6812s
- [COUNTERS] CudaCpp MEs      ( 2 ) :    0.0358s for     8192 events => throughput is 2.29E+05 events/s
- [COUNTERS] CudaCpp HEL      ( 3 ) :    0.0002s
+ [COUNTERS] PROGRAM TOTAL          :    0.4547s
+ [COUNTERS] Fortran Overhead ( 0 ) :    0.4074s
+ [COUNTERS] CudaCpp MEs      ( 2 ) :    0.0470s for     8192 events => throughput is 1.74E+05 events/s
+ [COUNTERS] CudaCpp HEL      ( 3 ) :    0.0003s
 
 *** (2-none) Compare MADEVENT_CPP x1 xsec to MADEVENT_FORTRAN xsec ***
 
-OK! xsec from fortran (2.0160081479755330) and cpp (2.0160406546722180) differ by less than 4E-4 (1.61242883456314e-05)
+OK! xsec from fortran (2.0160081479755183) and cpp (2.0160406825242951) differ by less than 4E-4 (1.6138103811513815e-05)
 
 *** (2-none) Compare MADEVENT_CPP x1 events.lhe to MADEVENT_FORTRAN events.lhe reference (including colors and helicities) ***
 ERROR! events.lhe.cpp.1 and events.lhe.ref.1 differ!
-diff /users/valassia/GPU2024/madgraph4gpu/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/events.lhe.cpp.1 /users/valassia/GPU2024/madgraph4gpu/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/events.lhe.ref.1 | head -20
+diff /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/events.lhe.cpp.1 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/events.lhe.ref.1 | head -20
 7562,7575d7561
 < 4 1 1E-03 0.1250010E+03 0.7546771E-02 0.1235066E+00
-<          21   -1    0    0  503  502  0.00000000000E+00  0.00000000000E+00  0.71320499550E+02  0.71320499550E+02  0.00000000000E+00 0.  1.
-<          21   -1    0    0  502  503 -0.00000000000E+00 -0.00000000000E+00 -0.54771239731E+02  0.54771239731E+02  0.00000000000E+00 0.  1.
-<           5    1    1    2  501    0  0.50303102232E+02  0.36190119942E+02  0.14973002962E+02  0.63925016178E+02  0.47000000000E+01 0. -1.
-<          -5    1    1    2    0  501 -0.50303102232E+02 -0.36190119942E+02  0.15762568567E+01  0.62166723103E+02  0.47000000000E+01 0. -1.
+<          21   -1    0    0  503  502  0.00000000000E+00  0.00000000000E+00  0.71320499473E+02  0.71320499473E+02  0.00000000000E+00 0.  1.
+<          21   -1    0    0  502  503 -0.00000000000E+00 -0.00000000000E+00 -0.54771239790E+02  0.54771239790E+02  0.00000000000E+00 0.  1.
+<           5    1    1    2  501    0  0.50303102232E+02  0.36190119942E+02  0.14973002893E+02  0.63925016162E+02  0.47000000000E+01 0. -1.
+<          -5    1    1    2    0  501 -0.50303102232E+02 -0.36190119942E+02  0.15762567893E+01  0.62166723101E+02  0.47000000000E+01 0. -1.
 < <mgrwt>
 < <rscale>  0 0.12500099E+03</rscale>
 < <asrwt>0</asrwt>