Merge Fix complex solver benchmark

This PR fixes the residual logging in the complex solver benchmark. In addition, tests for the `complex<double>` benchmarks are enabled for all benchmarks. Related PR: #1692
ginkgo-project · Nov 6, 2024 · dc8cfeb · dc8cfeb
2 parents 7b04094 + 8209132
commit dc8cfeb
Show file tree

Hide file tree

Showing 30 changed files with 473 additions and 11 deletions.
diff --git a/benchmark/test/CMakeLists.txt b/benchmark/test/CMakeLists.txt
@@ -9,7 +9,7 @@ function(add_benchmark_test test_name)
                       COMMAND ${Python3_EXECUTABLE} ${CMAKE_CURRENT_BINARY_DIR}/${test_name}.py $<TARGET_FILE:${test_name}> --generate
                       COMMENT "Regenerating reference output for ${test_name}"
                       WORKING_DIRECTORY "$<TARGET_FILE_DIR:ginkgo>")
-    add_dependencies(${regenerate_target} ${test_name})
+    add_dependencies(${regenerate_target} ${test_name} ${test_name}_dcomplex)
     add_dependencies(benchmark_test_regenerate ${regenerate_target})
 endfunction()
 add_custom_target(benchmark_test_regenerate)

diff --git a/benchmark/test/blas.py b/benchmark/test/blas.py
@@ -30,3 +30,11 @@
     expected_stdout="blas.profile.stdout",
     expected_stderr="blas.profile.stderr",
 )
+
+# complex
+test_framework.compare_output(
+    ["-input", '[{"n": 100}]'],
+    expected_stdout="blas_dcomplex.simple.stdout",
+    expected_stderr="blas_dcomplex.simple.stderr",
+    use_complex=True
+)
diff --git a/benchmark/test/conversion.py b/benchmark/test/conversion.py
@@ -67,3 +67,11 @@
     expected_stdout="conversion.profile.stdout",
     expected_stderr="conversion.profile.stderr",
 )
+
+# complex
+test_framework.compare_output(
+    ["-input", '[{"size": 100, "stencil": "7pt"}]', "-formats", "coo,csr"],
+    expected_stdout="conversion_dcomplex.simple.stdout",
+    expected_stderr="conversion_dcomplex.simple.stderr",
+    use_complex=True
+)
diff --git a/benchmark/test/multi_vector_distributed.py b/benchmark/test/multi_vector_distributed.py
@@ -34,3 +34,12 @@
     expected_stderr="multi_vector_distributed.profile.stderr",
     num_procs=3,
 )
+
+# complex
+test_framework.compare_output_distributed(
+    ["-input", '[{"n": 100}]'],
+    expected_stdout="multi_vector_distributed_dcomplex.simple.stdout",
+    expected_stderr="multi_vector_distributed_dcomplex.simple.stderr",
+    num_procs=3,
+    use_complex=True
+)
diff --git a/benchmark/test/preconditioner.py b/benchmark/test/preconditioner.py
@@ -66,3 +66,11 @@
     expected_stderr="preconditioner.reordered.stderr",
     stdin='[{"size": 100, "stencil": "7pt"}]',
 )
+
+# complex
+test_framework.compare_output(
+    ["-input", '[{"size": 100, "stencil": "7pt"}]'],
+    expected_stdout="preconditioner_dcomplex.simple.stdout",
+    expected_stderr="preconditioner_dcomplex.simple.stderr",
+    use_complex=True
+)
diff --git a/benchmark/test/reference/blas_dcomplex.simple.stderr b/benchmark/test/reference/blas_dcomplex.simple.stderr
@@ -0,0 +1,8 @@
+Running on ReferenceExecutor
+Running with 2 warm iterations and 10 running iterations
+The random seed for right hand sides is 42
+The operations are copy,axpy,scal
+Running test case n = 100 
+	Running blas: copy
+	Running blas: axpy
+	Running blas: scal
diff --git a/benchmark/test/reference/blas_dcomplex.simple.stdout b/benchmark/test/reference/blas_dcomplex.simple.stdout
@@ -0,0 +1,28 @@
+[
+    {
+        "n": 100,
+        "blas": {
+            "copy": {
+                "time": 1.0,
+                "flops": 1.0,
+                "bandwidth": 1.0,
+                "repetitions": 10,
+                "completed": true
+            },
+            "axpy": {
+                "time": 1.0,
+                "flops": 1.0,
+                "bandwidth": 1.0,
+                "repetitions": 10,
+                "completed": true
+            },
+            "scal": {
+                "time": 1.0,
+                "flops": 1.0,
+                "bandwidth": 1.0,
+                "repetitions": 10,
+                "completed": true
+            }
+        }
+    }
+]
diff --git a/benchmark/test/reference/conversion_dcomplex.simple.stderr b/benchmark/test/reference/conversion_dcomplex.simple.stderr
@@ -0,0 +1,10 @@
+Running on ReferenceExecutor
+Running with 2 warm iterations and 10 running iterations
+The random seed for right hand sides is 42
+The formats are coo,csr
+Running test case stencil(100, 7pt)
+Matrix is of size (125, 125), 725
+	Running conversion: coo-read
+	Running conversion: coo-csr
+	Running conversion: csr-read
+	Running conversion: csr-coo
diff --git a/benchmark/test/reference/conversion_dcomplex.simple.stdout b/benchmark/test/reference/conversion_dcomplex.simple.stdout
@@ -0,0 +1,31 @@
+[
+    {
+        "size": 100,
+        "stencil": "7pt",
+        "conversion": {
+            "coo-read": {
+                "time": 1.0,
+                "repetitions": 10,
+                "completed": true
+            },
+            "coo-csr": {
+                "time": 1.0,
+                "repetitions": 10,
+                "completed": true
+            },
+            "csr-read": {
+                "time": 1.0,
+                "repetitions": 10,
+                "completed": true
+            },
+            "csr-coo": {
+                "time": 1.0,
+                "repetitions": 10,
+                "completed": true
+            }
+        },
+        "rows": 125,
+        "cols": 125,
+        "nonzeros": 725
+    }
+]
diff --git a/benchmark/test/reference/distributed_solver_dcomplex.simple.stderr b/benchmark/test/reference/distributed_solver_dcomplex.simple.stderr
@@ -0,0 +1,8 @@
+Running on ReferenceExecutor
+Running with 2 warm iterations and 1 running iterations
+The random seed for right hand sides is 42
+Running cg with 1000 iterations and residual goal of 1.000000e-06
+The number of right hand sides is 1
+Running test case stencil(100, 7pt, stencil)
+Matrix is of size (125, 125)
+	Running solver: cg
diff --git a/benchmark/test/reference/distributed_solver_dcomplex.simple.stdout b/benchmark/test/reference/distributed_solver_dcomplex.simple.stdout
@@ -0,0 +1,59 @@
+[
+    {
+        "size": 100,
+        "stencil": "7pt",
+        "comm_pattern": "stencil",
+        "optimal": {
+            "spmv": "csr-csr"
+        },
+        "solver": {
+            "cg": {
+                "recurrent_residuals": [],
+                "true_residuals": [],
+                "implicit_residuals": [],
+                "iteration_timestamps": [],
+                "rhs_norm": 1.0,
+                "generate": {
+                    "components": {
+                        "generate(<typename>)": 1.0,
+                        "free": 1.0,
+                        "overhead": 1.0
+                    },
+                    "time": 1.0
+                },
+                "apply": {
+                    "components": {
+                        "apply(<typename>)": 1.0,
+                        "iteration": 1.0,
+                        "allocate": 1.0,
+                        "dense::fill": 1.0,
+                        "cg::initialize": 1.0,
+                        "advanced_apply(<typename>)": 1.0,
+                        "dense::row_gather": 1.0,
+                        "csr::advanced_spmv": 1.0,
+                        "dense::compute_squared_norm2": 1.0,
+                        "dense::compute_sqrt": 1.0,
+                        "copy(<typename>)": 1.0,
+                        "dense::copy": 1.0,
+                        "dense::compute_conj_dot_dispatch": 1.0,
+                        "check(<typename>)": 1.0,
+                        "residual_norm::residual_norm": 1.0,
+                        "cg::step_1": 1.0,
+                        "csr::spmv": 1.0,
+                        "cg::step_2": 1.0,
+                        "free": 1.0,
+                        "overhead": 1.0
+                    },
+                    "iterations": 7,
+                    "time": 1.0
+                },
+                "preconditioner": {},
+                "residual_norm": 1.0,
+                "repetitions": 1,
+                "completed": true
+            }
+        },
+        "rows": 125,
+        "cols": 125
+    }
+]
diff --git a/benchmark/test/reference/multi_vector_distributed_dcomplex.simple.stderr b/benchmark/test/reference/multi_vector_distributed_dcomplex.simple.stderr
@@ -0,0 +1,8 @@
+Running on ReferenceExecutor
+Running with 2 warm iterations and 10 running iterations
+The random seed for right hand sides is 42
+The operations are copy,axpy,scal
+Running test case n = 100 
+	Running blas: copy
+	Running blas: axpy
+	Running blas: scal
diff --git a/benchmark/test/reference/multi_vector_distributed_dcomplex.simple.stdout b/benchmark/test/reference/multi_vector_distributed_dcomplex.simple.stdout
@@ -0,0 +1,28 @@
+[
+    {
+        "n": 100,
+        "blas": {
+            "copy": {
+                "time": 1.0,
+                "flops": 1.0,
+                "bandwidth": 1.0,
+                "repetitions": 10,
+                "completed": true
+            },
+            "axpy": {
+                "time": 1.0,
+                "flops": 1.0,
+                "bandwidth": 1.0,
+                "repetitions": 10,
+                "completed": true
+            },
+            "scal": {
+                "time": 1.0,
+                "flops": 1.0,
+                "bandwidth": 1.0,
+                "repetitions": 10,
+                "completed": true
+            }
+        }
+    }
+]
diff --git a/benchmark/test/reference/preconditioner_dcomplex.simple.stderr b/benchmark/test/reference/preconditioner_dcomplex.simple.stderr
@@ -0,0 +1,7 @@
+Running on ReferenceExecutor
+Running with 2 warm iterations and 10 running iterations
+The random seed for right hand sides is 42
+Running with preconditioners: none
+Running test case stencil(100, 7pt)
+Matrix is of size (125, 125), 725
+	Running preconditioner: none
diff --git a/benchmark/test/reference/preconditioner_dcomplex.simple.stdout b/benchmark/test/reference/preconditioner_dcomplex.simple.stdout
@@ -0,0 +1,32 @@
+[
+    {
+        "size": 100,
+        "stencil": "7pt",
+        "preconditioner": {
+            "none": {
+                "generate": {
+                    "components": {
+                        "generate(<typename>)": 1.0,
+                        "overhead": 1.0
+                    },
+                    "time": 1.0,
+                    "repetitions": 10
+                },
+                "apply": {
+                    "components": {
+                        "apply(<typename>)": 1.0,
+                        "copy(<typename>)": 1.0,
+                        "dense::copy": 1.0,
+                        "overhead": 1.0
+                    },
+                    "time": 1.0,
+                    "repetitions": 10
+                },
+                "completed": true
+            }
+        },
+        "rows": 125,
+        "cols": 125,
+        "nonzeros": 725
+    }
+]
diff --git a/benchmark/test/reference/solver_dcomplex.simple.stderr b/benchmark/test/reference/solver_dcomplex.simple.stderr
@@ -0,0 +1,8 @@
+Running on ReferenceExecutor
+Running with 2 warm iterations and 1 running iterations
+The random seed for right hand sides is 42
+Running cg with 1000 iterations and residual goal of 1.000000e-06
+The number of right hand sides is 1
+Running test case stencil(100, 7pt)
+Matrix is of size (125, 125)
+	Running solver: cg
diff --git a/benchmark/test/reference/solver_dcomplex.simple.stdout b/benchmark/test/reference/solver_dcomplex.simple.stdout
@@ -0,0 +1,56 @@
+[
+    {
+        "size": 100,
+        "stencil": "7pt",
+        "optimal": {
+            "spmv": "csr"
+        },
+        "solver": {
+            "cg": {
+                "recurrent_residuals": [],
+                "true_residuals": [],
+                "implicit_residuals": [],
+                "iteration_timestamps": [],
+                "rhs_norm": 1.0,
+                "generate": {
+                    "components": {
+                        "generate(<typename>)": 1.0,
+                        "free": 1.0,
+                        "overhead": 1.0
+                    },
+                    "time": 1.0
+                },
+                "apply": {
+                    "components": {
+                        "apply(<typename>)": 1.0,
+                        "iteration": 1.0,
+                        "allocate": 1.0,
+                        "dense::fill": 1.0,
+                        "cg::initialize": 1.0,
+                        "advanced_apply(<typename>)": 1.0,
+                        "csr::advanced_spmv": 1.0,
+                        "dense::compute_norm2_dispatch": 1.0,
+                        "copy(<typename>)": 1.0,
+                        "dense::copy": 1.0,
+                        "dense::compute_conj_dot_dispatch": 1.0,
+                        "check(<typename>)": 1.0,
+                        "residual_norm::residual_norm": 1.0,
+                        "cg::step_1": 1.0,
+                        "csr::spmv": 1.0,
+                        "cg::step_2": 1.0,
+                        "free": 1.0,
+                        "overhead": 1.0
+                    },
+                    "iterations": 7,
+                    "time": 1.0
+                },
+                "preconditioner": {},
+                "residual_norm": 1.0,
+                "repetitions": 1,
+                "completed": true
+            }
+        },
+        "rows": 125,
+        "cols": 125
+    }
+]
diff --git a/benchmark/test/reference/sparse_blas_dcomplex.simple.stderr b/benchmark/test/reference/sparse_blas_dcomplex.simple.stderr
@@ -0,0 +1,7 @@
+Running on ReferenceExecutor
+Running with 2 warm iterations and 10 running iterations
+The random seed for right hand sides is 42
+The operations are transpose
+Running test case stencil(100, 7pt)
+Matrix is of size (125, 125), 725
+	Running sparse_blas: transpose
diff --git a/benchmark/test/reference/sparse_blas_dcomplex.simple.stdout b/benchmark/test/reference/sparse_blas_dcomplex.simple.stdout
@@ -0,0 +1,25 @@
+[
+    {
+        "size": 100,
+        "stencil": "7pt",
+        "sparse_blas": {
+            "transpose": {
+                "time": 1.0,
+                "flops": 1.0,
+                "bandwidth": 1.0,
+                "repetitions": 10,
+                "components": {
+                    "allocate": 1.0,
+                    "components::fill_array": 1.0,
+                    "csr::transpose": 1.0,
+                    "free": 1.0,
+                    "overhead": 1.0
+                },
+                "completed": true
+            }
+        },
+        "rows": 125,
+        "cols": 125,
+        "nonzeros": 725
+    }
+]
diff --git a/benchmark/test/reference/spmv_dcomplex.simple.stderr b/benchmark/test/reference/spmv_dcomplex.simple.stderr
@@ -0,0 +1,8 @@
+Running on ReferenceExecutor
+Running with 2 warm iterations and 10 running iterations
+The random seed for right hand sides is 42
+The formats are coo
+The number of right hand sides is 1
+Running test case stencil(100, 7pt)
+Matrix is of size (125, 125), 725
+	Running spmv: coo