Graph coloring

.gitignore

@@ -1,6 +1,8 @@
 out
 *.swp
-src/*.o
+*.o
+*.txt
+xhpcg
 bin/HPCG-Benchmark_3*.txt
 bin/xhpcg
 bin/hpcg20*.txt

PP_MPI_OpenMP/Makefile

@@ -0,0 +1,186 @@
+# -*- Makefile -*-
+
+#arch = Linux_Serial
+arch = PP_MPI_OMP
+setup_file = setup/Make.$(arch)
+
+include $(setup_file)
+
+
+HPCG_DEPS = src/CG.o \
+	    src/CG_ref.o \
+	    src/TestCG.o \
+	    src/ComputeResidual.o \
+	    src/ExchangeHalo.o \
+	    src/GenerateGeometry.o \
+	    src/GenerateProblem.o \
+	    src/GenerateProblem_ref.o \
+	    src/CheckProblem.o \
+	    src/MixedBaseCounter.o \
+	    src/OptimizeProblem.o \
+	    src/ReadHpcgDat.o \
+	    src/ReportResults.o \
+	    src/SetupHalo.o \
+	    src/SetupHalo_ref.o \
+	    src/TestSymmetry.o \
+	    src/TestNorms.o \
+	    src/WriteProblem.o \
+	    src/YAML_Doc.o \
+	    src/YAML_Element.o \
+	    src/ComputeDotProduct.o \
+	    src/ComputeDotProduct_ref.o \
+	    src/mytimer.o \
+	    src/ComputeOptimalShapeXYZ.o \
+	    src/ComputeSPMV.o \
+	    src/ComputeSPMV_ref.o \
+	    src/ComputeSYMGS.o \
+	    src/ComputeSYMGS_ref.o \
+	    src/ComputeWAXPBY.o \
+	    src/ComputeWAXPBY_ref.o \
+	    src/ComputeMG_ref.o \
+	    src/ComputeMG.o \
+	    src/ComputeProlongation_ref.o \
+	    src/ComputeRestriction_ref.o \
+	    src/CheckAspectRatio.o \
+	    src/OutputFile.o \
+	    src/GenerateCoarseProblem.o \
+	    src/init.o \
+	    src/finalize.o
+
+# These header files are included in many source files, so we recompile every file if one or more of these header is modified.
+PRIMARY_HEADERS = ../src/Geometry.hpp ../src/SparseMatrix.hpp ../src/Vector.hpp ../src/CGData.hpp \
+                  ../src/MGData.hpp ../src/hpcg.hpp
+
+all: bin/xhpcg
+	#sbatch ./bin/job.sh
+	export OMP_NUM_THREADS=2 && mpiexec -n 4 ./bin/xhpcg
+	mv ./*.txt ./result/HPCG
+
+bin/xhpcg: src/main.o $(HPCG_DEPS)
+	$(LINKER) $(LINKFLAGS) src/main.o $(HPCG_DEPS) $(HPCG_LIBS) -o bin/xhpcg
+
+clean:
+	rm -f src/*.o bin/xhpcg
+
+.PHONY: all clean
+
+src/main.o: ../src/main.cpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/CG.o: ../src/CG.cpp ../src/CG.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/CG_ref.o: ../src/CG_ref.cpp ../src/CG_ref.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/TestCG.o: ../src/TestCG.cpp ../src/TestCG.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/ComputeResidual.o: ../src/ComputeResidual.cpp ../src/ComputeResidual.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/ExchangeHalo.o: ../src/ExchangeHalo.cpp ../src/ExchangeHalo.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/GenerateGeometry.o: ../src/GenerateGeometry.cpp ../src/GenerateGeometry.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/GenerateProblem.o: ../src/GenerateProblem.cpp ../src/GenerateProblem.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/GenerateProblem_ref.o: ../src/GenerateProblem_ref.cpp ../src/GenerateProblem_ref.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/CheckProblem.o: ../src/CheckProblem.cpp ../src/CheckProblem.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/MixedBaseCounter.o: ../src/MixedBaseCounter.cpp ../src/MixedBaseCounter.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/OptimizeProblem.o: ../src/OptimizeProblem.cpp ../src/OptimizeProblem.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/ReadHpcgDat.o: ../src/ReadHpcgDat.cpp ../src/ReadHpcgDat.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/ReportResults.o: ../src/ReportResults.cpp ../src/ReportResults.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/SetupHalo.o: ../src/SetupHalo.cpp ../src/SetupHalo.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/SetupHalo_ref.o: ../src/SetupHalo_ref.cpp ../src/SetupHalo_ref.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/TestSymmetry.o: ../src/TestSymmetry.cpp ../src/TestSymmetry.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/TestNorms.o: ../src/TestNorms.cpp ../src/TestNorms.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/WriteProblem.o: ../src/WriteProblem.cpp ../src/WriteProblem.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/YAML_Doc.o: ../src/YAML_Doc.cpp ../src/YAML_Doc.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/YAML_Element.o: ../src/YAML_Element.cpp ../src/YAML_Element.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/ComputeDotProduct.o: ../src/ComputeDotProduct.cpp ../src/ComputeDotProduct.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/ComputeDotProduct_ref.o: ../src/ComputeDotProduct_ref.cpp ../src/ComputeDotProduct_ref.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/finalize.o: ../src/finalize.cpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/init.o: ../src/init.cpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/mytimer.o: ../src/mytimer.cpp ../src/mytimer.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/ComputeOptimalShapeXYZ.o: ../src/ComputeOptimalShapeXYZ.cpp ../src/ComputeOptimalShapeXYZ.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/ComputeSPMV.o: ../src/ComputeSPMV.cpp ../src/ComputeSPMV.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c -march=native $(CXXFLAGS) -I../src $< -o $@
+
+src/ComputeSPMV_ref.o: ../src/ComputeSPMV_ref.cpp ../src/ComputeSPMV_ref.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/ComputeSYMGS.o: ../src/ComputeSYMGS.cpp ../src/ComputeSYMGS.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/ComputeSYMGS_ref.o: ../src/ComputeSYMGS_ref.cpp ../src/ComputeSYMGS_ref.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/ComputeWAXPBY.o: ../src/ComputeWAXPBY.cpp ../src/ComputeWAXPBY.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/ComputeWAXPBY_ref.o: ../src/ComputeWAXPBY_ref.cpp ../src/ComputeWAXPBY_ref.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/ComputeMG_ref.o: ../src/ComputeMG_ref.cpp ../src/ComputeMG_ref.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/ComputeMG.o: ../src/ComputeMG.cpp ../src/ComputeMG.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/ComputeProlongation_ref.o: ../src/ComputeProlongation_ref.cpp ../src/ComputeProlongation_ref.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/ComputeRestriction_ref.o: ../src/ComputeRestriction_ref.cpp ../src/ComputeRestriction_ref.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/GenerateCoarseProblem.o: ../src/GenerateCoarseProblem.cpp ../src/GenerateCoarseProblem.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/CheckAspectRatio.o: ../src/CheckAspectRatio.cpp ../src/CheckAspectRatio.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+
+src/OutputFile.o: ../src/OutputFile.cpp ../src/OutputFile.hpp $(PRIMARY_HEADERS)
+	$(CXX) -c $(CXXFLAGS) -I../src $< -o $@
+

PP_MPI_OpenMP/bin/hpcg.dat

@@ -0,0 +1,4 @@
+HPCG benchmark input file
+Sandia National Laboratories; University of Tennessee, Knoxville
+96 96 96
+64

PP_MPI_OpenMP/bin/job.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+#SBATCH -o ./result/SBATCH/job.%j.out
+#SBATCH -J HPCG_g7_SZW
+#SBATCH --nodes=1
+#SBATCH --ntasks-per-node=64
+
+export OMP_NUM_THREADS=4
+mpiexec -n 32 /public1/home/sc81071/CAS_PP2024/sichengtaotao/hpcg/PP_MPI_OpenMP/bin/xhpcg

PP_MPI_OpenMP/hpcg.dat

@@ -0,0 +1,4 @@
+HPCG benchmark input file
+Sandia National Laboratories; University of Tennessee, Knoxville
+96 96 96
+64

PP_MPI_OpenMP/result/HPCG/HPCG-Benchmark_3.1_2024-06-29_15-10-58.txt

@@ -0,0 +1,127 @@
+HPCG-Benchmark
+version=3.1
+Release date=March 28, 2019
+Machine Summary=
+Machine Summary::Distributed Processes=8
+Machine Summary::Threads per processes=8
+Global Problem Dimensions=
+Global Problem Dimensions::Global nx=32
+Global Problem Dimensions::Global ny=32
+Global Problem Dimensions::Global nz=32
+Processor Dimensions=
+Processor Dimensions::npx=2
+Processor Dimensions::npy=2
+Processor Dimensions::npz=2
+Local Domain Dimensions=
+Local Domain Dimensions::nx=16
+Local Domain Dimensions::ny=16
+Local Domain Dimensions::Lower ipz=0
+Local Domain Dimensions::Upper ipz=1
+Local Domain Dimensions::nz=16
+########## Problem Summary  ##########=
+Setup Information=
+Setup Information::Setup Time=0.0218346
+Linear System Information=
+Linear System Information::Number of Equations=32768
+Linear System Information::Number of Nonzero Terms=830584
+Multigrid Information=
+Multigrid Information::Number of coarse grid levels=3
+Multigrid Information::Coarse Grids=
+Multigrid Information::Coarse Grids::Grid Level=1
+Multigrid Information::Coarse Grids::Number of Equations=4096
+Multigrid Information::Coarse Grids::Number of Nonzero Terms=97336
+Multigrid Information::Coarse Grids::Number of Presmoother Steps=1
+Multigrid Information::Coarse Grids::Number of Postsmoother Steps=1
+Multigrid Information::Coarse Grids::Grid Level=2
+Multigrid Information::Coarse Grids::Number of Equations=512
+Multigrid Information::Coarse Grids::Number of Nonzero Terms=10648
+Multigrid Information::Coarse Grids::Number of Presmoother Steps=1
+Multigrid Information::Coarse Grids::Number of Postsmoother Steps=1
+Multigrid Information::Coarse Grids::Grid Level=3
+Multigrid Information::Coarse Grids::Number of Equations=64
+Multigrid Information::Coarse Grids::Number of Nonzero Terms=1000
+Multigrid Information::Coarse Grids::Number of Presmoother Steps=1
+Multigrid Information::Coarse Grids::Number of Postsmoother Steps=1
+########## Memory Use Summary  ##########=
+Memory Use Information=
+Memory Use Information::Total memory used for data (Gbytes)=0.0235669
+Memory Use Information::Memory used for OptimizeProblem data (Gbytes)=0
+Memory Use Information::Bytes per equation (Total memory / Number of Equations)=719.205
+Memory Use Information::Memory used for linear system and CG (Gbytes)=0.0207158
+Memory Use Information::Coarse Grids=
+Memory Use Information::Coarse Grids::Grid Level=1
+Memory Use Information::Coarse Grids::Memory used=0.00249264
+Memory Use Information::Coarse Grids::Grid Level=2
+Memory Use Information::Coarse Grids::Memory used=0.000316812
+Memory Use Information::Coarse Grids::Grid Level=3
+Memory Use Information::Coarse Grids::Memory used=4.1684e-05
+########## V&V Testing Summary  ##########=
+Spectral Convergence Tests=
+Spectral Convergence Tests::Result=PASSED
+Spectral Convergence Tests::Unpreconditioned=
+Spectral Convergence Tests::Unpreconditioned::Maximum iteration count=11
+Spectral Convergence Tests::Unpreconditioned::Expected iteration count=12
+Spectral Convergence Tests::Preconditioned=
+Spectral Convergence Tests::Preconditioned::Maximum iteration count=2
+Spectral Convergence Tests::Preconditioned::Expected iteration count=2
+Departure from Symmetry |x'Ay-y'Ax|/(2*||x||*||A||*||y||)/epsilon=
+Departure from Symmetry |x'Ay-y'Ax|/(2*||x||*||A||*||y||)/epsilon::Result=PASSED
+Departure from Symmetry |x'Ay-y'Ax|/(2*||x||*||A||*||y||)/epsilon::Departure for SpMV=0
+Departure from Symmetry |x'Ay-y'Ax|/(2*||x||*||A||*||y||)/epsilon::Departure for MG=0
+########## Iterations Summary  ##########=
+Iteration Count Information=
+Iteration Count Information::Result=PASSED
+Iteration Count Information::Reference CG iterations per set=50
+Iteration Count Information::Optimized CG iterations per set=51
+Iteration Count Information::Total number of reference iterations=50
+Iteration Count Information::Total number of optimized iterations=51
+########## Reproducibility Summary  ##########=
+Reproducibility Information=
+Reproducibility Information::Result=PASSED
+Reproducibility Information::Scaled residual mean=7.57053e-20
+Reproducibility Information::Scaled residual variance=0
+########## Performance Summary (times in sec) ##########=
+Benchmark Time Summary=
+Benchmark Time Summary::Optimization phase=1.05e-07
+Benchmark Time Summary::DDOT=0.0313035
+Benchmark Time Summary::WAXPBY=0.00405827
+Benchmark Time Summary::SpMV=0.00620048
+Benchmark Time Summary::MG=0.0666923
+Benchmark Time Summary::Total=0.108292
+Floating Point Operations Summary=
+Floating Point Operations Summary::Raw DDOT=1.00925e+07
+Floating Point Operations Summary::Raw WAXPBY=1.00925e+07
+Floating Point Operations Summary::Raw SpMV=8.63807e+07
+Floating Point Operations Summary::Raw MG=4.78874e+08
+Floating Point Operations Summary::Total=5.8544e+08
+Floating Point Operations Summary::Total with convergence overhead=5.7396e+08
+GB/s Summary=
+GB/s Summary::Raw Read B/W=33.358
+GB/s Summary::Raw Write B/W=7.71199
+GB/s Summary::Raw Total B/W=41.0699
+GB/s Summary::Total with convergence and optimization phase overhead=39.4689
+GFLOP/s Summary=
+GFLOP/s Summary::Raw DDOT=0.322409
+GFLOP/s Summary::Raw WAXPBY=2.48691
+GFLOP/s Summary::Raw SpMV=13.9313
+GFLOP/s Summary::Raw MG=7.18035
+GFLOP/s Summary::Raw Total=5.4061
+GFLOP/s Summary::Total with convergence overhead=5.3001
+GFLOP/s Summary::Total with convergence and optimization phase overhead=5.19535
+User Optimization Overheads=
+User Optimization Overheads::Optimization phase time (sec)=1.05e-07
+User Optimization Overheads::Optimization phase time vs reference SpMV+MG time=2.68842e-05
+DDOT Timing Variations=
+DDOT Timing Variations::Min DDOT MPI_Allreduce time=0.00153632
+DDOT Timing Variations::Max DDOT MPI_Allreduce time=0.0267875
+DDOT Timing Variations::Avg DDOT MPI_Allreduce time=0.0142139
+Final Summary=
+Final Summary::HPCG result is VALID with a GFLOP/s rating of=5.19535
+Final Summary::HPCG 2.4 rating for historical reasons is=5.3001
+Final Summary::Reference version of ComputeDotProduct used=Performance results are most likely suboptimal
+Final Summary::Reference version of ComputeSPMV used=Performance results are most likely suboptimal
+Final Summary::Reference version of ComputeMG used and number of threads greater than 1=Performance results are severely suboptimal
+Final Summary::Reference version of ComputeWAXPBY used=Performance results are most likely suboptimal
+Final Summary::Results are valid but execution time (sec) is=0.108292
+Final Summary::You have selected the QuickPath option=Results are official for legacy installed systems with confirmation from the HPCG Benchmark leaders.
+Final Summary::After confirmation please upload results from the YAML file contents to=http://hpcg-benchmark.org

PP_MPI_OpenMP/result/HPCG/hpcg20240629T151058.txt

@@ -0,0 +1,11 @@
+WARNING: PERFORMING UNPRECONDITIONED ITERATIONS
+Call [0] Number of Iterations [11] Scaled Residual [1.08807e-14]
+WARNING: PERFORMING UNPRECONDITIONED ITERATIONS
+Call [1] Number of Iterations [11] Scaled Residual [1.08946e-14]
+Call [0] Number of Iterations [2] Scaled Residual [7.51788e-17]
+Call [1] Number of Iterations [2] Scaled Residual [7.51788e-17]
+Departure from symmetry (scaled) for SpMV abs(x'*A*y - y'*A*x) = 0
+Departure from symmetry (scaled) for MG abs(x'*Minv*y - y'*Minv*x) = 0
+SpMV call [0] Residual [0]
+SpMV call [1] Residual [0]
+Call [0] Scaled Residual [7.57053e-20]