Skip to content
New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

#

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

Jump to bottom

CMake Error at src/CMakeLists.txt:104 (rocm_set_soversion) #116

Closed
paolodalberto opened this issue Oct 9, 2020 · 25 comments
Closed

CMake Error at src/CMakeLists.txt:104 (rocm_set_soversion) #116

paolodalberto opened this issue Oct 9, 2020 · 25 comments

Comments

@paolodalberto
Copy link

installed rocBLAS, rocSPARSE, rocRAND
....

paolo@fastmmw:~/FastMM/Epyc/rocALUTION$ ./install.sh -idc
Creating project build directory in: ./build
[sudo] password for paolo:
Hit:1 http://repo.radeon.com/rocm/apt/debian xenial InRelease
Hit:2 http://security.ubuntu.com/ubuntu bionic-security InRelease
Hit:3 http://us.archive.ubuntu.com/ubuntu bionic InRelease
Hit:4 http://us.archive.ubuntu.com/ubuntu bionic-updates InRelease
Hit:5 http://us.archive.ubuntu.com/ubuntu bionic-backports InRelease
Reading package lists... Done
Building dependency tree
Reading state information... Done
All packages are up to date.
~/FastMM/Epyc/rocALUTION ~/FastMM/Epyc/rocALUTION
Building googletest from source; installing into /usr/local
-- Configuring done
-- Generating done
CMake Warning:
Manually-specified variables were not used by the project:

BUILD_BOOST

-- Build files have been written to: /home/paolo/FastMM/Epyc/rocALUTION/build/deps
Scanning dependencies of target install
Built target install
~/FastMM/Epyc/rocALUTION
~/FastMM/Epyc/rocALUTION ~/FastMM/Epyc/rocALUTION
-- The CXX compiler identification is GNU 7.5.0
-- Check for working CXX compiler: /usr/bin/c++
-- Check for working CXX compiler: /usr/bin/c++ -- works
-- Detecting CXX compiler ABI info
-- Detecting CXX compiler ABI info - done
-- Detecting CXX compile features
-- Detecting CXX compile features - done
-- Found Git: /usr/bin/git (found version "2.17.1")
-- Found OpenMP_CXX: -fopenmp (found version "4.5")
-- Found OpenMP: TRUE (found version "4.5")
-- Found MPI_CXX: /usr/lib/x86_64-linux-gnu/openmpi/lib/libmpi_cxx.so (found version "3.1")
-- Found MPI: TRUE (found version "3.1")
-- Found HIP: /opt/rocm-3.8.0/hip (found version "3.8.20371-d1886b0b")
-- Looking for C++ include pthread.h
-- Looking for C++ include pthread.h - found
-- Looking for pthread_create
-- Looking for pthread_create - not found
-- Looking for pthread_create in pthreads
-- Looking for pthread_create in pthreads - not found
-- Looking for pthread_create in pthread
-- Looking for pthread_create in pthread - found
-- Found Threads: TRUE
CMake Error at src/CMakeLists.txt:104 (rocm_set_soversion):
Unknown CMake command "rocm_set_soversion".

-- Configuring incomplete, errors occurred!
See also "/home/paolo/FastMM/Epyc/rocALUTION/build/release/CMakeFiles/CMakeOutput.log".
See also "/home/paolo/FastMM/Epyc/rocALUTION/build/release/CMakeFiles/CMakeError.log".
@paolodalberto
Copy link
Author

Any help is welcome thank you

@paolodalberto
Copy link
Author

one step forward:

export ROCM_DIR=/opt/rocm/share/rocm/cmake/
./install.sh -icd

1 warning generated when compiling for host.
1 warning generated when compiling for gfx906.
1 warning generated when compiling for host.
In file included from /home/paolo/FastMM/Epyc/rocALUTION/src/base/hip/hip_matrix_csr.cpp:35:
In file included from /home/paolo/FastMM/Epyc/rocALUTION/src/base/hip/hip_vector.hpp:32:
In file included from /opt/rocm-3.8.0/include/hip/hip_runtime.h:53:
/opt/rocm-3.8.0/include/hip/hip_common.h:30:9: warning: 'HIP_PLATFORM_HCC' macro redefined [-Wmacro-redefined]
#define HIP_PLATFORM_HCC
^
:7:9: note: previous definition is here
#define HIP_PLATFORM_HCC 1
^
1 warning generated when compiling for gfx908.
In file included from /home/paolo/FastMM/Epyc/rocALUTION/src/base/hip/hip_matrix_csr.cpp:35:
In file included from /home/paolo/FastMM/Epyc/rocALUTION/src/base/hip/hip_vector.hpp:32:
In file included from /opt/rocm-3.8.0/include/hip/hip_runtime.h:53:
/opt/rocm-3.8.0/include/hip/hip_common.h:30:9: warning: 'HIP_PLATFORM_HCC' macro redefined [-Wmacro-redefined]
#define HIP_PLATFORM_HCC
^
:7:9: note: previous definition is here
#define HIP_PLATFORM_HCC 1
^
1 warning generated when compiling for host.
CMakeFiles/Makefile2:87: recipe for target 'src/CMakeFiles/rocalution_hip.dir/all' failed
make[1]: *** [src/CMakeFiles/rocalution_hip.dir/all] Error 2
Makefile:151: recipe for target 'all' failed
make: *** [all] Error 2

@paolodalberto
Copy link
Author

one step forward

[ 9%] Building HIPCC object src/CMakeFiles/rocalution_hip.dir/base/hip/rocalution_hip_generated_hip_matrix_bcsr.cpp.o
In file included from /home/paolo/FastMM/Epyc/rocALUTION/src/base/hip/hip_vector.cpp:45:
/home/paolo/FastMM/Epyc/rocALUTION/src/base/hip/hip_rand_normal.hpp:28:10: fatal error: 'rocrand/rocrand.hpp' file not found
#include <rocrand/rocrand.hpp>
^~~~~~~~~~~~~~~~~~~~~
1 error generated when compiling for host.
CMake Error at rocalution_hip_generated_hip_vector.cpp.o.cmake:138 (message):
Error generating
/home/paolo/FastMM/Epyc/rocALUTION/build/src/CMakeFiles/rocalution_hip.dir/base/hip/./rocalution_hip_generated_hip_vector.cpp.o

@paolodalberto
Copy link
Author

rocRAND install only the C includes

Install the project...
-- Install configuration: "Release"
-- Installing: /opt/rocm/rocrand/lib/librocrand.so.1.1
-- Up-to-date: /opt/rocm/rocrand/lib/librocrand.so.1
-- Up-to-date: /opt/rocm/rocrand/lib/librocrand.so
-- Set runtime path of "/opt/rocm/rocrand/lib/librocrand.so.1.1" to "/opt/rocm/lib"
-- Up-to-date: /opt/rocm/rocrand/include
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_discrete.h
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_common.h
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_normal.h
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_xorwow_precomputed.h
-- Up-to-date: /opt/rocm/rocrand/include/rocrand.hpp
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_log_normal.h
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_discrete_types.h
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_sobol32.h
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_mrg32k3a_precomputed.h
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_mrg32k3a.h
-- Up-to-date: /opt/rocm/rocrand/include/rocrand.h
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_philox4x32_10.h
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_uniform.h
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_xorwow.h
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_mtgp32_11213.h
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_kernel.h
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_sobol_precomputed.h
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_poisson.h
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_mtgp32.h
-- Up-to-date: /opt/rocm/rocrand/include
-- Up-to-date: /opt/rocm/rocrand/include/rocrand_version.h
-- Up-to-date: /opt/rocm/rocrand/lib/cmake/rocrand/rocrand-targets.cmake
-- Installing: /opt/rocm/rocrand/lib/cmake/rocrand/rocrand-targets-release.cmake
-- Installing: /opt/rocm/rocrand/lib/cmake/rocrand/rocrand-config.cmake
-- Up-to-date: /opt/rocm/rocrand/lib/cmake/rocrand/rocrand-config-version.cmake
-- Installing: /opt/rocm/hiprand/lib/libhiprand.so.1.1
-- Up-to-date: /opt/rocm/hiprand/lib/libhiprand.so.1
-- Up-to-date: /opt/rocm/hiprand/lib/libhiprand.so
-- Set runtime path of "/opt/rocm/hiprand/lib/libhiprand.so.1.1" to "/opt/rocm/rocrand/lib:/opt/rocm/lib"
-- Up-to-date: /opt/rocm/hiprand/include
-- Up-to-date: /opt/rocm/hiprand/include/hiprand_mtgp32_host.h
-- Up-to-date: /opt/rocm/hiprand/include/hiprand_kernel_nvcc.h
-- Up-to-date: /opt/rocm/hiprand/include/hiprand_kernel.h
-- Up-to-date: /opt/rocm/hiprand/include/hiprand.hpp
-- Up-to-date: /opt/rocm/hiprand/include/hiprand_kernel_hcc.h
-- Up-to-date: /opt/rocm/hiprand/include/hiprand.h
-- Up-to-date: /opt/rocm/hiprand/include/hiprand_nvcc.h
-- Up-to-date: /opt/rocm/hiprand/include/hiprand_hcc.h
-- Up-to-date: /opt/rocm/hiprand/include
-- Up-to-date: /opt/rocm/hiprand/include/hiprand_version.h
-- Up-to-date: /opt/rocm/hiprand/lib/cmake/hiprand/hiprand-targets.cmake
-- Installing: /opt/rocm/hiprand/lib/cmake/hiprand/hiprand-targets-release.cmake
-- Installing: /opt/rocm/hiprand/lib/cmake/hiprand/hiprand-config.cmake
-- Up-to-date: /opt/rocm/hiprand/lib/cmake/hiprand/hiprand-config-version.cmake
-- Installing: /opt/rocm/rocrand/src/fortran/rocrand_m.f90
-- Installing: /opt/rocm/rocrand/src/fortran/hip_m.f90
-- Installing: /opt/rocm/hiprand/src/fortran/hiprand_m.f90
-- Installing: /opt/rocm/hiprand/src/fortran/hip_m.f90

@paolodalberto
Copy link
Author

manually changed the

#include "hip_rand.hpp"
#include <hip/hip_runtime.h>
#include <rocrand.hpp>

compilation successful

however
paolo@fastmmw:~/FastMM/Epyc/rocALUTION/build$ ./clients/staging/cg ~/FastMM/Epyc/SparseFastMM/python/MTX/pdb1HYS.mtx /src/external/hip-on-vdi/rocclr/hip_code_object.cpp:92: guarantee(false && "hipErrorNoBinaryForGpu: Coudn't find binary for current devices!")
Aborted (core dumped)

@paolodalberto
Copy link
Author

paolodalberto commented Oct 10, 2020 •
edited
Loading

The goal is to run solvers on GPUs

@xuhuisheng
Copy link

Which gpu are you used?
e.g. navi10 isnot supported offically. Please refer here ROCm/tensorflow-upstream#1106

@paolodalberto
Copy link
Author

ellesmere (ProDuo) I do not have a navi
I will play with Fiji and Vega 20

@paolodalberto
Copy link
Author

rocSPARSE works

@paolodalberto
Copy link
Author

paolodalberto commented Oct 10, 2020 •
edited
Loading

it will be helpful to see what binararies are missing ....

@paolodalberto
Copy link
Author

let me build rocBLAS from scratch

@paolodalberto
Copy link
Author

Agent 2

Name: gfx803
Uuid: GPU-XX
Marketing Name: Ellesmere [Radeon Pro WX 7100]
Vendor Name: AMD
Feature: KERNEL_DISPATCH
Profile: BASE_PROFILE
Float Round Mode: NEAR
Max Queue Number: 128(0x80)
Queue Min Size: 4096(0x1000)
Queue Max Size: 131072(0x20000)
Queue Type: MULTI
Node: 1
Device Type: GPU
Cache Info:
L1: 16(0x10) KB
Chip ID: 26564(0x67c4)
Cacheline Size: 64(0x40)
Max Clock Freq. (MHz): 1243
BDFID: 17152
Internal Node ID: 1
Compute Unit: 36
SIMDs per CU: 4
Shader Engines: 4
Shader Arrs. per Eng.: 1
WatchPts on Addr. Ranges:4
Features: KERNEL_DISPATCH
Fast F16 Operation: FALSE
Wavefront Size: 64(0x40)
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension:
x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Max Waves Per CU: 40(0x28)
Max Work-item Per CU: 2560(0xa00)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension:
x 4294967295(0xffffffff)
y 4294967295(0xffffffff)
z 4294967295(0xffffffff)
Max fbarriers/Workgrp: 32
Pool Info:
Pool 1
Segment: GLOBAL; FLAGS: COARSE GRAINED
Size: 16777216(0x1000000) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Alignment: 4KB
Accessible by all: FALSE
Pool 2
Segment: GROUP
Size: 64(0x40) KB
Allocatable: FALSE
Alloc Granule: 0KB
Alloc Alignment: 0KB
Accessible by all: FALSE
ISA Info:
ISA 1
Name: amdgcn-amd-amdhsa--gfx803
Machine Models: HSA_MACHINE_MODEL_LARGE
Profiles: HSA_PROFILE_BASE
Default Rounding Mode: NEAR
Default Rounding Mode: NEAR
Fast f16: TRUE
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension:
x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension:
x 4294967295(0xffffffff)
y 4294967295(0xffffffff)
z 4294967295(0xffffffff)
FBarrier Max Size: 32

Agent 3

Name: gfx803
Uuid: GPU-XX
Marketing Name: Ellesmere [Radeon Pro WX 7100]
Vendor Name: AMD
Feature: KERNEL_DISPATCH
Profile: BASE_PROFILE
Float Round Mode: NEAR
Max Queue Number: 128(0x80)
Queue Min Size: 4096(0x1000)
Queue Max Size: 131072(0x20000)
Queue Type: MULTI
Node: 2
Device Type: GPU
Cache Info:
L1: 16(0x10) KB
Chip ID: 26564(0x67c4)
Cacheline Size: 64(0x40)
Max Clock Freq. (MHz): 1243
BDFID: 17408
Internal Node ID: 2
Compute Unit: 36
SIMDs per CU: 4
Shader Engines: 4
Shader Arrs. per Eng.: 1
WatchPts on Addr. Ranges:4
Features: KERNEL_DISPATCH
Fast F16 Operation: FALSE
Wavefront Size: 64(0x40)
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension:
x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Max Waves Per CU: 40(0x28)
Max Work-item Per CU: 2560(0xa00)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension:
x 4294967295(0xffffffff)
y 4294967295(0xffffffff)
z 4294967295(0xffffffff)
Max fbarriers/Workgrp: 32
Pool Info:
Pool 1
Segment: GLOBAL; FLAGS: COARSE GRAINED
Size: 16777216(0x1000000) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Alignment: 4KB
Accessible by all: FALSE
Pool 2
Segment: GROUP
Size: 64(0x40) KB
Allocatable: FALSE
Alloc Granule: 0KB
Alloc Alignment: 0KB
Accessible by all: FALSE
ISA Info:
ISA 1
Name: amdgcn-amd-amdhsa--gfx803
Machine Models: HSA_MACHINE_MODEL_LARGE
Profiles: HSA_PROFILE_BASE
Default Rounding Mode: NEAR
Default Rounding Mode: NEAR
Fast f16: TRUE
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension:
x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension:
x 4294967295(0xffffffff)
y 4294967295(0xffffffff)
z 4294967295(0xffffffff)
FBarrier Max Size: 32
*** Done ***
paolo@fastmmw:~/FastMM/Epyc/rocALUTION/build$

@paolodalberto
Copy link
Author

nope ... let see if something changes with a different GPU

@paolodalberto
Copy link
Author

using a different GPU and re-building does not make any difference

@xuhuisheng
Copy link

Mostly rocBLAS report missing Tensile_Library_803.co, please refer here:
ROCm/tensorflow-upstream#1106 (comment)

@paolodalberto
Copy link
Author

I can check but rocBLAS worked

@paolodalberto
Copy link
Author

paolodalberto commented Oct 12, 2020 •
edited
Loading 

paolo@fastmmw:~/FastMM/Epyc/rocBLAS/build/release/clients/staging$ ./rocblas-bench -f gemm
Query device success: there are 2 devices
-------------------------------------------------------------------------------
Device ID 0 : Ellesmere [Radeon Pro WX 7100]
with 17.2 GB memory, max. SCLK 1243 MHz, max. MCLK 1750 MHz, compute capability 8.3
maxGridDimX 2147483647, sharedMemPerBlock 65.5 KB, maxThreadsPerBlock 1024, warpSize 64
-------------------------------------------------------------------------------
Device ID 1 : Ellesmere [Radeon Pro WX 7100]
with 17.2 GB memory, max. SCLK 1243 MHz, max. MCLK 1750 MHz, compute capability 8.3
maxGridDimX 2147483647, sharedMemPerBlock 65.5 KB, maxThreadsPerBlock 1024, warpSize 64
-------------------------------------------------------------------------------

transA,transB,M,N,K,alpha,lda,ldb,beta,ldc,rocblas-Gflops,us
N,N,128,128,128,1.0000000,128,128,0.0000000,128,136.1787013,30.8000000

paolo@fastmmw:~/FastMM$ ls -lrt /opt/rocm-3.8.0/rocblas/lib/library/
total 435072
-rw-r--r-- 1 root root 13447896 Oct 10 15:02 Kernels.so-000-gfx908.hsaco
-rw-r--r-- 1 root root 13435608 Oct 10 15:02 Kernels.so-000-gfx906.hsaco
-rw-r--r-- 1 root root 15234136 Oct 10 15:02 Kernels.so-000-gfx900.hsaco
-rw-r--r-- 1 root root 14482368 Oct 10 15:02 Kernels.so-000-gfx803.hsaco
-rw-r--r-- 1 root root 13828720 Oct 10 15:02 Kernels.so-000-gfx1011.hsaco
-rw-r--r-- 1 root root 14992568 Oct 10 15:02 Kernels.so-000-gfx1010.hsaco
-rw-r--r-- 1 root root 127802736 Oct 10 15:02 TensileLibrary_gfx908.co
-rw-r--r-- 1 root root 3658000 Oct 10 15:02 TensileLibrary_gfx803.co
-rw-r--r-- 1 root root 35691768 Oct 10 15:02 TensileLibrary_gfx900.co
-rw-r--r-- 1 root root 102552952 Oct 10 15:02 TensileLibrary_gfx906.co
-rw-r--r-- 1 root root 90358993 Oct 10 15:02 TensileLibrary.dat

Tensile is there alright
let's if it is related to rocrand (which is flimsy)

@paolodalberto
Copy link
Author

paolodalberto commented Oct 12, 2020 •
edited
Loading

rocRAND ctest

Total Test time (real) = 8.99 sec

The following tests FAILED:
3 - test_poisson_distribution (Not Run)
4 - test_rocrand_basic (Not Run)
5 - test_rocrand_cpp_wrapper (Not Run)
6 - test_rocrand_generate (Not Run)
7 - test_rocrand_generate_log_normal (Not Run)
8 - test_rocrand_generate_normal (Not Run)
9 - test_rocrand_generate_poisson (Not Run)
10 - test_rocrand_generate_uniform (Not Run)
12 - test_rocrand_kernel_mrg32k3a (Not Run)
13 - test_rocrand_kernel_mtgp32 (Not Run)
14 - test_rocrand_kernel_philox4x32_10 (Not Run)
15 - test_rocrand_kernel_sobol32 (Not Run)
16 - test_rocrand_kernel_xorwow (Not Run)
24 - test_hiprand_cpp_wrapper (Not Run)
25 - test_hiprand_kernel (Not Run)
26 - test_rocrand_fortran_wrapper (Not Run)
27 - test_hiprand_fortran_wrapper (Not Run)
Errors while running CTest

@paolodalberto
Copy link
Author 

./rocsparse-bench  
Query device success: there are 2 devices
Device ID 0: Ellesmere [Radeon Pro WX 7100]
-------------------------------------------------------------------------
with 16384MB memory, clock rate 1243MHz @ computing capability 8.3
maxGridDimX 2147483647, sharedMemPerBlock 64KB, maxThreadsPerBlock 1024
wavefrontSize 64
-------------------------------------------------------------------------
Device ID 1: Ellesmere [Radeon Pro WX 7100]
-------------------------------------------------------------------------
with 16384MB memory, clock rate 1243MHz @ computing capability 8.3
maxGridDimX 2147483647, sharedMemPerBlock 64KB, maxThreadsPerBlock 1024
wavefrontSize 64
-------------------------------------------------------------------------
Using device ID 0 (Ellesmere [Radeon Pro WX 7100]) for rocSPARSE
-------------------------------------------------------------------------
rocSPARSE version: 1.17.8-855-0192c4b
M           nnz         alpha           GFlop/s     GB/s        usec        iter        verified    
128         32          1.00            0.01        0.06        8.10        10          no

@paolodalberto
Copy link
Author

How do you check what binary needs?

 ./clients/staging/cg ~/FastMM/Epyc/SparseFastMM/python/MTX/young4c.mtx 4
/src/external/hip-on-vdi/rocclr/hip_code_object.cpp:92: guarantee(false && "hipErrorNoBinaryForGpu: Coudn't find binary for current devices!")

@paolodalberto
Copy link
Author

paolodalberto commented Oct 13, 2020 •
edited
Loading

ViennaCL is the only one I could execute a cg so far ... should I implement cg using rocBLAS and rocSPARSE directly?

@paolodalberto
Copy link
Author

paolodalberto commented Oct 13, 2020 •
edited
Loading 

paolo@fastmmw:~/FastMM/Epyc/ViennaCL-1.7.1/build$ ./examples/tutorial/iterative-custom /home/paolo/FastMM/Epyc/SparseFastMM/python/MTX/Lin.mtx
gfx803
0x562f6477c810
/home/paolo/FastMM/Epyc/SparseFastMM/python/MTX/Lin.mtx
----- CG Method -----
Time difference = 816916[µs]
	iterations:100 Error:0.108561
----- BiCGStab Method -----
Time difference = 435005[µs]
	iterations: 100 Error:7.60943e-05
----- GMRES Method -----
Time difference = 46114[µs]
	iterations: 100 Error:0.0655528
!!!! TUTORIAL COMPLETED SUCCESSFULLY !!!!

@paolodalberto
Copy link
Author

No comments
No further help ?

@paolodalberto
Copy link
Author

resolved
AMDGPU_TARGETS=gfx803;gfx900;gfx906;gfx908

Adding gfx803 for vega 20 I will check

@paolodalberto
Copy link
Author 

paolo@fastmmw:~/FastMM/Epyc/rocALUTION/build$ ./clients/staging/cg gr_30_30.mtx 1
OMP: Info #270: omp_get_nested routine deprecated, please use omp_get_max_active_levels instead.
OMP: Info #270: omp_set_nested routine deprecated, please use omp_set_max_active_levels instead.
Number of CPU cores: 32
Host thread affinity policy - thread mapping on every core
Number of HIP devices in the system: 3
HURRA 
rocALUTION ver 1.11.0-539-9e5603a
rocALUTION platform is initialized
Accelerator backend: HIP
OpenMP threads: 32
rocBLAS ver 2.33.0.2836-fbe56c5e
rocSPARSE ver 1.17.8-855-0192c4b
Selected HIP device: 1
------------------------------------------------
Device number: 0
Device name: Vega 20
totalGlobalMem: 16368 MByte
clockRate: 1801000
compute capability: 9.6
------------------------------------------------
------------------------------------------------
Device number: 1
Device name: Ellesmere [Radeon Pro WX 7100]
totalGlobalMem: 16384 MByte
clockRate: 1243000
compute capability: 8.3
------------------------------------------------
------------------------------------------------
Device number: 2
Device name: Ellesmere [Radeon Pro WX 7100]
totalGlobalMem: 16384 MByte
clockRate: 1243000
compute capability: 8.3
------------------------------------------------
MPI is not initialized
ReadFileMTX: filename=gr_30_30.mtx; reading...
ReadFileMTX: filename=gr_30_30.mtx; done
LocalMatrix name=gr_30_30.mtx; rows=900; cols=900; nnz=7744; prec=64bit; format=CSR; host backend={CPU(OpenMP)}; accelerator backend={HIP}; current=HIP
PCG solver starts, with preconditioner:
Jacobi preconditioner
IterationControl criteria: abs tol=1e-15; rel tol=1e-06; div tol=1e+08; max iter=1000000
IterationControl initial residual = 33.2866
IterationControl RELATIVE criteria has been reached: res norm=2.03206e-05; rel val=6.10474e-07; iter=36
PCG ends
Solver execution:0.034622 sec
||e - x||_2 = 8.01194e-06
OMP: Info #270: omp_set_nested routine deprecated, please use omp_set_max_active_levels instead.

@pshirshov pshirshov mentioned this issue Jan 7, 2021
Closed
ntrost57 pushed a commit that referenced this issue Nov 17, 2022
@jsandham
fix clang formatting errors (#116)
365575e 
Co-authored-by: jsandham <james.sandham@amd.com>
# for free to join this conversation on GitHub. Already have an account? # to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@xuhuisheng @paolodalberto