22020750556

Committed 14 Feb 2026 04:38PM UTC coverage: 64.828% (-1.5%) from 66.315%

Build # 22020750556

Build Type

Pull #524

github

Committed by

web-flow

Commit Message

Merge 2784aa264 into 9d01cacd5

Pull Request Pull Request #524: Native Tensor Support - Step 2: Use tensor types on memlets of tensor nodes

Run Details

245 of 570 new or added lines in 24 files covered. (42.98%)

458 existing lines in 18 files now uncovered.

23080 of 35602 relevant lines covered (64.83%)

371.57 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

68.18

/sdfg/src/data_flow/library_nodes/math/tensor/elementwise_ops/div_node.cpp

#include "sdfg/data_flow/library_nodes/math/tensor/elementwise_ops/div_node.h"

#include "sdfg/analysis/analysis.h"
#include "sdfg/builder/structured_sdfg_builder.h"
#include "sdfg/types/type.h"

#include "sdfg/analysis/scope_analysis.h"

namespace sdfg {
namespace math {
namespace tensor {

DivNode::DivNode(
    size_t element_id,
    const DebugInfo& debug_info,
    const graph::Vertex vertex,
    data_flow::DataFlowGraph& parent,
    const std::vector<symbolic::Expression>& shape
)
    : ElementWiseBinaryNode(element_id, debug_info, vertex, parent, LibraryNodeType_Div, shape) {}

bool DivNode::expand_operation(
    builder::StructuredSDFGBuilder& builder,
    analysis::AnalysisManager& analysis_manager,
    structured_control_flow::Sequence& body,
    const std::string& input_name_a,
    const std::string& input_name_b,
    const std::string& output_name,
    const types::Tensor& input_type_a,
    const types::Tensor& input_type_b,
    const types::Tensor& output_type,
    const data_flow::Subset& subset
) {
    auto& code_block = builder.add_block(body);

    bool is_int = types::is_integer(output_type.primitive_type());
    data_flow::TaskletCode opcode;
    if (is_int) {
        // Distinguish between signed and unsigned division
        bool is_signed = types::is_signed(output_type.primitive_type());
        opcode = is_signed ? data_flow::TaskletCode::int_sdiv : data_flow::TaskletCode::int_udiv;
    } else {
        opcode = data_flow::TaskletCode::fp_div;
    }
    auto& tasklet = builder.add_tasklet(code_block, opcode, "_out", {"_in1", "_in2"});

    auto& output_node = builder.add_access(code_block, output_name);
    builder.add_computational_memlet(code_block, tasklet, "_out", output_node, subset, output_type);

    if (builder.subject().exists(input_name_a)) {
        auto& input_node_a = builder.add_access(code_block, input_name_a);
        if (input_type_a.is_scalar()) {
            builder.add_computational_memlet(code_block, input_node_a, tasklet, "_in1", {}, input_type_a);
        } else {
            builder.add_computational_memlet(code_block, input_node_a, tasklet, "_in1", subset, input_type_a);
        }
    } else {
        types::Scalar const_type(input_type_a.primitive_type());
        auto& input_node_a = builder.add_constant(code_block, input_name_a, const_type);
        builder.add_computational_memlet(code_block, input_node_a, tasklet, "_in1", subset, input_type_a);
    }

    if (builder.subject().exists(input_name_b)) {
        auto& input_node_b = builder.add_access(code_block, input_name_b);
        if (input_type_b.is_scalar()) {
            builder.add_computational_memlet(code_block, input_node_b, tasklet, "_in2", {}, input_type_b);
        } else {
            builder.add_computational_memlet(code_block, input_node_b, tasklet, "_in2", subset, input_type_b);
        }
    } else {
        types::Scalar const_type(input_type_b.primitive_type());
        auto& input_node_b = builder.add_constant(code_block, input_name_b, const_type);
        builder.add_computational_memlet(code_block, input_node_b, tasklet, "_in2", subset, input_type_b);
    }

    return true;
}

std::unique_ptr<data_flow::DataFlowNode> DivNode::
    clone(size_t element_id, const graph::Vertex vertex, data_flow::DataFlowGraph& parent) const {
    return std::unique_ptr<
        data_flow::DataFlowNode>(new DivNode(element_id, this->debug_info(), vertex, parent, this->shape_));
}

} // namespace tensor
} // namespace math
} // namespace sdfg

1	#include "sdfg/data_flow/library_nodes/math/tensor/elementwise_ops/div_node.h"
2
3	#include "sdfg/analysis/analysis.h"
4	#include "sdfg/builder/structured_sdfg_builder.h"
5	#include "sdfg/types/type.h"
6
7	#include "sdfg/analysis/scope_analysis.h"
8
9	namespace sdfg {
10	namespace math {
11	namespace tensor {
12
13	DivNode::DivNode(
14	size_t element_id,
15	const DebugInfo& debug_info,
16	const graph::Vertex vertex,
17	data_flow::DataFlowGraph& parent,
18	const std::vector<symbolic::Expression>& shape
19	)
20	: ElementWiseBinaryNode(element_id, debug_info, vertex, parent, LibraryNodeType_Div, shape) {}	9✔
21
22	bool DivNode::expand_operation(
23	builder::StructuredSDFGBuilder& builder,
24	analysis::AnalysisManager& analysis_manager,
25	structured_control_flow::Sequence& body,
26	const std::string& input_name_a,
27	const std::string& input_name_b,
28	const std::string& output_name,
29	const types::Tensor& input_type_a,
30	const types::Tensor& input_type_b,
31	const types::Tensor& output_type,
32	const data_flow::Subset& subset
33	) {	6✔
34	auto& code_block = builder.add_block(body);	6✔
35
36	bool is_int = types::is_integer(output_type.primitive_type());	6✔
37	data_flow::TaskletCode opcode;	6✔
38	if (is_int) {	6✔
39	// Distinguish between signed and unsigned division
40	bool is_signed = types::is_signed(output_type.primitive_type());	2✔
41	opcode = is_signed ? data_flow::TaskletCode::int_sdiv : data_flow::TaskletCode::int_udiv;	2✔
42	} else {	4✔
43	opcode = data_flow::TaskletCode::fp_div;	4✔
44	}	4✔
45	auto& tasklet = builder.add_tasklet(code_block, opcode, "_out", {"_in1", "_in2"});	6✔
46
47	auto& output_node = builder.add_access(code_block, output_name);	6✔
48	builder.add_computational_memlet(code_block, tasklet, "_out", output_node, subset, output_type);	6✔
49
50	if (builder.subject().exists(input_name_a)) {	6✔
51	auto& input_node_a = builder.add_access(code_block, input_name_a);	6✔
52	if (input_type_a.is_scalar()) {	6✔
NEW 53	builder.add_computational_memlet(code_block, input_node_a, tasklet, "_in1", {}, input_type_a);	×
54	} else {	6✔
55	builder.add_computational_memlet(code_block, input_node_a, tasklet, "_in1", subset, input_type_a);	6✔
56	}	6✔
57	} else {	6✔
NEW 58	types::Scalar const_type(input_type_a.primitive_type());	×
NEW 59	auto& input_node_a = builder.add_constant(code_block, input_name_a, const_type);	×
NEW 60	builder.add_computational_memlet(code_block, input_node_a, tasklet, "_in1", subset, input_type_a);	×
UNCOV 61	}	×
62
63	if (builder.subject().exists(input_name_b)) {	6✔
64	auto& input_node_b = builder.add_access(code_block, input_name_b);	6✔
65	if (input_type_b.is_scalar()) {	6✔
NEW 66	builder.add_computational_memlet(code_block, input_node_b, tasklet, "_in2", {}, input_type_b);	×
67	} else {	6✔
68	builder.add_computational_memlet(code_block, input_node_b, tasklet, "_in2", subset, input_type_b);	6✔
69	}	6✔
70	} else {	6✔
NEW 71	types::Scalar const_type(input_type_b.primitive_type());	×
NEW 72	auto& input_node_b = builder.add_constant(code_block, input_name_b, const_type);	×
NEW 73	builder.add_computational_memlet(code_block, input_node_b, tasklet, "_in2", subset, input_type_b);	×
UNCOV 74	}	×
75
76	return true;	6✔
77	}	6✔
78
79	std::unique_ptr<data_flow::DataFlowNode> DivNode::
80	clone(size_t element_id, const graph::Vertex vertex, data_flow::DataFlowGraph& parent) const {	×
81	return std::unique_ptr<	×
82	data_flow::DataFlowNode>(new DivNode(element_id, this->debug_info(), vertex, parent, this->shape_));	×
83	}	×
84
85	} // namespace tensor
86	} // namespace math
87	} // namespace sdfg

daisytuner / docc / 22020750556

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous