triton-lang/triton

10.3

Adjusted Score

10.3

Raw Score

100%

Time Factor

2026-07-14

Last Push

19.7K

Stars

MLIR

Language

384.9K

Lines of Code

1.2K

Files

3.4K

Pattern Hits

2026-07-14

Scan Date

0.02

HC Hit Rate

What These Metrics Mean

Adjusted Score: Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score: The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor: The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits: Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate: High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files: Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 15HIGH 7MEDIUM 409LOW 3007

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 3438 distinct pattern matches across 24 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Hyper-Verbose Identifiers1205 hits · 1012 pts

Severity	File	Line	Snippet	Context
LOW	setup.py	550	def get_triton_version_suffix():	CODE
LOW	python/build_helpers.py	126	def _download_file_with_urllib(url: str, path: str, label: str):	CODE
LOW	python/build_helpers.py	380	def _get_thirdparty_package_cmake_vars(package: Package, helper_args: BuildHelperArgs):	CODE
LOW	python/build_helpers.py	414	def get_thirdparty_cmake_vars(packages: list[str], helper_args: BuildHelperArgs):	CODE
LOW	python/build_helpers.py	434	def write_thirdparty_cmake_vars(output: str, packages: list[str], helper_args: BuildHelperArgs):	CODE
LOW	python/build_helpers.py	482	def download_and_copy_dependencies(helper_args: BuildHelperArgs):	CODE
LOW	python/test/conftest.py	45	def fresh_knobs_including_libraries():	CODE
LOW	python/test/unit/test_utils.py	18	def test_validate_block_shape_rejects_zero():	CODE
LOW	python/test/unit/test_utils.py	27	def test_validate_block_shape_accepts_powers_of_two():	CODE
LOW	python/test/unit/test_debug.py	24	def _run_device_assert_barrier(device):	CODE
LOW	python/test/unit/test_debug.py	38	def _run_expect_zero_device_assert(device):	CODE
LOW	python/test/unit/test_debug.py	54	def test_expect_zero_device_assert(device):	CODE
LOW	python/test/unit/test_debug.py	76	def test_device_assert_barrier(device):	CODE
LOW	python/test/unit/test_debug.py	151	def test_sanitize_int_add_overflow(x, y, x_dtype, y_dtype, debug, should_overflow, device):	CODE
LOW	python/test/unit/test_debug.py	167	def test_sanitize_int_mul_overflow(x, y, x_dtype, y_dtype, debug, should_overflow, device):	CODE
LOW	python/test/unit/test_debug.py	182	def test_sanitize_int_sub_overflow(x, y, x_dtype, y_dtype, debug, should_overflow, device):	CODE
LOW	python/test/unit/test_perf_warning.py	12	def enable_diagnostics_context(value):	CODE
LOW	python/test/unit/test_perf_warning.py	98	def test_remark_vectorization(capfd, fresh_triton_cache):	CODE
LOW	python/test/unit/test_perf_warning.py	162	def test_remark_swp_op_before_operands(capfd, fresh_triton_cache):	CODE
LOW	python/test/unit/tools/test_aot.py	321	def compile_aot_kernel_no_specialization(dir, kernel_path, dtype, BM, BN, BK, target=None):	STRING
LOW	python/test/unit/tools/test_aot.py	366	def generate_matmul_test_data(dir, M, N, K):	STRING
LOW	python/test/unit/tools/test_aot.py	392	def test_compile_link_matmul_no_specialization():	STRING
LOW	python/test/unit/tools/test_aot.py	459	def test_launcher_has_no_available_kernel():	STRING
LOW	python/test/unit/tools/test_aot.py	497	def test_compile_link_autotune_matmul():	STRING
LOW	python/test/unit/tools/test_linear_layout.py	36	def test_operator_mul_identity():	CODE
LOW	python/test/unit/tools/test_linear_layout.py	42	def test_operator_mul_disjoint_dims():	CODE
LOW⚡	python/test/unit/tools/test_linear_layout.py	75	def test_get_matrix_view_identity():	CODE
LOW⚡	python/test/unit/tools/test_linear_layout.py	83	def test_get_matrix_view_strided():	CODE
LOW⚡	python/test/unit/tools/test_linear_layout.py	92	def test_get_matrix_view_from_bases():	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	45	def test_slice_kernel_basic_module_slicing(tmp_path):	CODE
LOW⚡	python/test/unit/tools/test_slice_kernel.py	733	def test_slice_kernel_treats_assign_targets_as_locals(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	121	def test_slice_kernel_does_not_treat_site_packages_as_stdlib(tmp_path, monkeypatch):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	167	def test_slice_kernel_does_not_treat_base_python_site_packages_as_stdlib_in_venv(tmp_path, monkeypatch):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	215	def test_slice_kernel_supports_injected_decorator_matchers(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	311	def test_slice_kernel_translate_to_gluon_keeps_tensor_method_rewrites(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	357	def test_slice_kernel_translate_to_gluon_inlines_descriptor_adapter(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	404	def test_slice_kernel_binds_local_imports(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	434	def test_slice_kernel_function_import(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	469	def test_slice_kernel_function_import_module_value(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	500	def test_slice_kernel_function_relative_import(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	542	def test_slice_kernel_module_level_imported_value_alias(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	575	def test_slice_kernel_function_from_import_value(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	606	def test_slice_kernel_function_absolute_import(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	652	def test_slice_kernel_function_module_relative_import(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	694	def test_slice_kernel_function_module_relative_import_leaf(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	758	def test_slice_kernel_treats_annassign_targets_as_locals(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	782	def test_slice_kernel_treats_assign_and_annassign_targets_as_locals(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	820	def test_slice_kernel_translate_to_gluon_avoids_double_descriptor_wrap(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	852	def test_translate_to_gluon_explicit_expand_dims_rewrites_layout(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	886	def test_translate_to_gluon_member_fn_expand_dims_rewrites_layout(tmp_path):	STRING
LOW	python/test/unit/tools/test_slice_kernel.py	920	def test_slice_kernel_public_imports():	STRING
LOW	python/test/unit/tools/test_irsource.py	10	def test_mlir_attribute_parsing(tmp_path: pathlib.Path) -> None:	CODE
LOW	python/test/unit/tools/test_disasm.py	25	def test_extract_handles_large_instruction_offsets(monkeypatch):	CODE
LOW	python/test/unit/tools/test_triton_to_gluon.py	100	def test_triton_to_gluon_dot_minimal(tmp_path):	CODE
LOW	python/test/unit/tools/test_triton_to_gluon.py	222	def test_triton_to_gluon_dot_scaled(	CODE
LOW	python/test/unit/tools/test_triton_to_gluon.py	272	def dot_transposed_operand_tile_kernel(	CODE
LOW	python/test/unit/tools/test_triton_to_gluon.py	308	def test_triton_to_gluon_dot_transposed_operands(lhs_transposed, rhs_transposed, tmp_path):	CODE
LOW	python/test/unit/tools/test_triton_to_gluon.py	435	def _skip_unless_descriptor_target():	CODE
LOW	python/test/unit/tools/test_triton_to_gluon.py	442	def test_triton_to_gluon_descriptor_roundtrip(tmp_path):	CODE
LOW	python/test/unit/tools/test_triton_to_gluon.py	466	def test_triton_to_gluon_descriptor_load_roundtrip(tmp_path):	CODE
1145 more matches not shown…

Decorative Section Separators368 hits · 966 pts

Severity	File	Line	Snippet	Context
MEDIUM	python/test/unit/cuda/test_libdevice_cuda.py	13	# -----------------------	COMMENT
MEDIUM	python/test/unit/cuda/test_libdevice_cuda.py	15	# -----------------------	COMMENT
MEDIUM	python/test/unit/language/test_standard.py	8	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_standard.py	10	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_standard.py	23	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_standard.py	25	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_standard.py	62	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_standard.py	64	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	370	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	372	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	516	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	580	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	582	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	607	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	609	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	639	# ----------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	641	# ----------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	688	# ------------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	690	# ------------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	705	# ----------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	707	# ----------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	816	# ----------------------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	818	# ----------------------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	832	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	834	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	926	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	928	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	959	# ----------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	961	# ----------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	1030	# -------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	1032	# -------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	1091	# ----------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	1093	# ----------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	1138	# ----------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	1140	# ----------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	1172	# ----------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	1174	# ----------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	1199	# ----------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	1201	# ----------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	1382	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	1384	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	2019	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	2021	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	2465	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	2467	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	3079	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	3081	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	3129	# ------------------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	3131	# ------------------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	3326	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	3328	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	3443	# ---------------	COMMENT
MEDIUM	python/test/unit/language/test_core.py	3445	# ---------------	COMMENT
MEDIUM⚡	python/test/unit/language/test_core.py	4829	# ---------------	STRING
MEDIUM⚡	python/test/unit/language/test_core.py	4831	# ---------------	STRING
MEDIUM⚡	python/test/unit/language/test_core.py	5006	# --------------------	STRING
MEDIUM⚡	python/test/unit/language/test_core.py	5008	# --------------------	STRING
MEDIUM⚡	python/test/unit/language/test_core.py	5278	# -------------	STRING
MEDIUM⚡	python/test/unit/language/test_core.py	5280	# -------------	STRING
MEDIUM	python/test/unit/language/test_core.py	4525	# ---------------	STRING
308 more matches not shown…

Over-Commented Block867 hits · 832 pts

Severity	File	Line	Snippet	Context
LOW	unittest/Dialect/TritonGPU/SwizzleTest.cpp	1	#include "triton/Dialect/Triton/IR/Dialect.h"	COMMENT
LOW	unittest/Dialect/TritonGPU/SwizzleTest.cpp	241	int maskedLaneIdx;	COMMENT
LOW	unittest/Dialect/TritonGPU/SwizzleTest.cpp	261	} else {	COMMENT
LOW	…test/Dialect/TritonGPU/LinearLayoutConversionsTest.cpp	3581	{{0, 1}, {0, 2}, {0, 4}, {16, 0}, {32, 0}, {64, 0}, {128, 0}}},	COMMENT
LOW	…test/Dialect/TritonGPU/LinearLayoutConversionsTest.cpp	3601	// created after TMA load or used for conceptual access patterns, not for	COMMENT
LOW	bin/triton-llvm-opt.cpp	1	/// Trimmed down clone of llvm opt to be able to test triton custom llvm ir	COMMENT
LOW	bin/triton-tensor-layout.cpp	1	#include "RegisterTritonDialects.h"	COMMENT
LOW	bin/triton-tensor-layout.cpp	21	//	COMMENT
LOW	bin/RegisterTritonDialects.h	1	#pragma once	COMMENT
LOW	bin/RegisterTritonDialects.h	21	#include "TritonAMDGPUTransforms/Passes.h"	COMMENT
LOW	python/test/unit/cuda/test_tma_store_gemm.py	1	# Copyright (c) 2023 NVIDIA Corporation & Affiliates. All rights reserved.	COMMENT
LOW	python/test/unit/language/test_line_info.py	301	# CHECK: %offsets_1 = arith.addi %offsets_0, %offsets : tensor<16xi32> loc(#loc16)	COMMENT
LOW	python/test/unit/language/test_line_info.py	521	# CHECK: #loc = loc("{{.*}}":@DEF_LINE@:5)	COMMENT
LOW	python/test/unit/language/test_line_info.py	541	# CHECK: } loc(#loc)	COMMENT
LOW	python/test/gluon/test_frontend.py	221	@gluon.jit	COMMENT
LOW	python/test/gluon/test_frontend.py	521	# CHECK-NEXT: [[OUTS:%.]]:3 = ttg.warp_specialize([[A]], [[B]], [[C]], [[A]], [[B]], [[C]]) {{.}}requestedRegis	COMMENT
LOW	python/test/gluon/test_frontend.py	581	# CHECK-DAG: [[BLOCKED_NW4:#.*]] = #ttg.blocked<{sizePerThread = [1], threadsPerWarp = [32], warpsPerCTA = [4], orde	COMMENT
LOW	python/triton/knobs.py	561	#	COMMENT
LOW	python/triton/experimental/gsan/src/GSan.h	1	#pragma once	COMMENT
LOW	…on/experimental/gluon/language/amd/gfx1250/_layouts.py	181	# WMMA CTA layout: Below, M runs vertically (rows) and N	COMMENT
LOW	…on/experimental/gluon/language/amd/gfx1250/_layouts.py	201	# For example, if the block 64x128, the block would look like this:	COMMENT
LOW	python/triton/tools/disasm.py	1	# MIT License	COMMENT
LOW	…triton/tools/triton_to_gluon_translator/ordered_set.py	1	"""	COMMENT
LOW	python/examples/gluon/02-conv-dgrad.py	61	#	COMMENT
LOW	python/examples/gluon/02-conv-fprop.py	61		COMMENT
LOW	python/examples/gluon/02-conv-fprop.py	481	output = torch.empty((N, out_h, out_w, Co), device=input_tensor.device, dtype=TORCH_GEMM_DTYPE)	COMMENT
LOW	python/examples/gluon/02-conv-wgrad.py	61	# grad_W[Co, RSCi] = grad_out[M, Co]^T @ im2col(input)[M, RSCi]	COMMENT
LOW	python/triton_kernels/tests/test_reduce.py	201	# bench_reduce(B=16384, M=4, N=8192, dim=1, dtype=torch.float16, mask_mode="broadcast_n")	COMMENT
LOW	python/triton_kernels/triton_kernels/matmul.py	61	out_handles: torch.Tensor	COMMENT
LOW	…_kernels/tensor_details/layout_details/hopper_value.py	141	# 3: threads[0]	COMMENT
LOW	…riton_kernels/tensor_details/layout_details/strided.py	1	from dataclasses import dataclass	COMMENT
LOW	…n_kernels/tensor_details/layout_details/torch_utils.py	1	import torch	COMMENT
LOW	…n_kernels/tensor_details/layout_details/torch_utils.py	21	# if not is_fp4:	COMMENT
LOW	python/tutorials/02-fused-softmax.py	61		COMMENT
LOW	python/tutorials/02-fused-softmax.py	181		COMMENT
LOW	python/tutorials/08-grouped-gemm.py	1	"""	COMMENT
LOW	python/tutorials/04-low-memory-dropout.py	21	# The dropout operator was first introduced in [SRIVASTAVA2014]_ as a way to improve the performance	COMMENT
LOW	python/tutorials/04-low-memory-dropout.py	81	output = dropout(x, x_keep=x_keep, p=p)	COMMENT
LOW	python/tutorials/04-low-memory-dropout.py	161		COMMENT
LOW	python/tutorials/03-matrix-multiplication.py	21	# -----------	COMMENT
LOW	python/tutorials/03-matrix-multiplication.py	41	# for k in range(0, K, BLOCK_SIZE_K):	COMMENT
LOW	python/tutorials/03-matrix-multiplication.py	61	# For a row-major 2D tensor :code:`X`, the memory location of :code:`X[i, j]` is given	COMMENT
LOW	python/tutorials/03-matrix-multiplication.py	81	# offs_k = tl.arange(0, BLOCK_SIZE_K)	COMMENT
LOW	python/tutorials/03-matrix-multiplication.py	101	#	COMMENT
LOW	python/tutorials/03-matrix-multiplication.py	121	# # Number of programs ids along the N axis	COMMENT
LOW	python/tutorials/03-matrix-multiplication.py	281	# We will advance this pointer as we move in the K direction	COMMENT
LOW	python/tutorials/05-layer-norm.py	21	# It takes a vector :math:`x` as input and produces a vector :math:`y` of the same shape as output.	COMMENT
LOW	python/tutorials/05-layer-norm.py	101	#	COMMENT
LOW	python/tutorials/10-block-scaled-matmul.py	21	python 10-block-scaled-matmul.py --format mxfp8 --K_range 8192 16384 --K_step 2048 --bench	COMMENT
LOW	python/tutorials/10-block-scaled-matmul.py	41	# where scale_a and scale_b are the blocked scale factors for the A and B matrices.	COMMENT
LOW	python/tutorials/10-block-scaled-matmul.py	61	# In order to conform with Triton's language semantics for dot_scaled, the scale factors	COMMENT
LOW	python/tutorials/10-block-scaled-matmul.py	81	#	COMMENT
LOW	python/tutorials/10-block-scaled-matmul.py	101	#	COMMENT
LOW	python/tutorials/gluon/05-wgmma.py	41	# Let's illustrate WGMMA with a trivial kernel launched with grid size (1, ).	COMMENT
LOW	python/tutorials/gluon/05-wgmma.py	61	#	COMMENT
LOW	python/tutorials/gluon/05-wgmma.py	81	#	COMMENT
LOW	python/tutorials/gluon/05-wgmma.py	101	#	COMMENT
LOW	python/tutorials/gluon/05-wgmma.py	181	# and all this does is immediately wait for 0 outstanding operations. In	COMMENT
LOW	python/tutorials/gluon/05-wgmma.py	261	# False 32 8.48	COMMENT
LOW	python/tutorials/gluon/05-wgmma.py	421	# We should try to pick the largest `n` for the WGMMA layout. Based on the	COMMENT
807 more matches not shown…

Unused Imports507 hits · 394 pts

Severity	File	Line	Context
LOW	python/test/unit/runtime/test_build.py	1	CODE
LOW	python/test/unit/language/test_annotations.py	1	CODE
LOW	python/test/gsan/test_allocator.py	1	CODE
LOW	python/test/gsan/test_gsan_failures.py	1	CODE
LOW	python/test/gsan/test_symmetric_memory.py	1	CODE
LOW	python/test/gsan/test_gsan.py	1	CODE
LOW	python/triton/knobs.py	1	CODE
LOW	python/triton/__init__.py	8	CODE
LOW	python/triton/__init__.py	8	CODE
LOW	python/triton/__init__.py	8	CODE
LOW	python/triton/__init__.py	8	CODE
LOW	python/triton/__init__.py	8	CODE
LOW	python/triton/__init__.py	8	CODE
LOW	python/triton/__init__.py	8	CODE
LOW	python/triton/__init__.py	8	CODE
LOW	python/triton/__init__.py	8	CODE
LOW	python/triton/__init__.py	8	CODE
LOW	python/triton/__init__.py	20	CODE
LOW	python/triton/__init__.py	21	CODE
LOW	python/triton/__init__.py	21	CODE
LOW	python/triton/__init__.py	22	CODE
LOW	python/triton/__init__.py	22	CODE
LOW	python/triton/__init__.py	23	CODE
LOW	python/triton/__init__.py	24	CODE
LOW	python/triton/__init__.py	27	CODE
LOW	python/triton/__init__.py	28	CODE
LOW	python/triton/_utils.py	1	CODE
LOW	python/triton/experimental/gsan/__init__.py	1	CODE
LOW	python/triton/experimental/gsan/__init__.py	1	CODE
LOW	python/triton/experimental/gsan/__init__.py	1	CODE
LOW	python/triton/experimental/gsan/__init__.py	1	CODE
LOW	python/triton/experimental/gsan/__init__.py	1	CODE
LOW	python/triton/experimental/gsan/__init__.py	2	CODE
LOW	python/triton/experimental/gsan/_testing_utils.py	1	CODE
LOW	python/triton/experimental/gsan/_allocator.py	1	CODE
LOW	python/triton/experimental/gsan/symmetric_memory.py	1	CODE
LOW	python/triton/experimental/gsan/_testing.py	1	CODE
LOW	python/triton/experimental/gsan/_stream_sync.py	1	CODE
LOW	python/triton/experimental/gsan/_utils.py	1	CODE
LOW	python/triton/experimental/gluon/__init__.py	1	CODE
LOW	python/triton/experimental/gluon/__init__.py	1	CODE
LOW	python/triton/experimental/gluon/__init__.py	1	CODE
LOW	python/triton/experimental/gluon/__init__.py	2	CODE
LOW	python/triton/experimental/gluon/__init__.py	2	CODE
LOW	python/triton/experimental/gluon/__init__.py	3	CODE
LOW	python/triton/experimental/gluon/__init__.py	4	CODE
LOW	python/triton/experimental/gluon/_runtime.py	1	CODE
LOW	python/triton/experimental/gluon/_runtime.py	4	CODE
LOW	python/triton/experimental/gluon/language/__init__.py	1	CODE
LOW	python/triton/experimental/gluon/language/__init__.py	1	CODE
LOW	python/triton/experimental/gluon/language/__init__.py	1	CODE
LOW	python/triton/experimental/gluon/language/__init__.py	1	CODE
LOW	python/triton/experimental/gluon/language/__init__.py	1	CODE
LOW	python/triton/experimental/gluon/language/__init__.py	1	CODE
LOW	python/triton/experimental/gluon/language/__init__.py	1	CODE
LOW	python/triton/experimental/gluon/language/__init__.py	1	CODE
LOW	python/triton/experimental/gluon/language/__init__.py	1	CODE
LOW	python/triton/experimental/gluon/language/__init__.py	1	CODE
LOW	python/triton/experimental/gluon/language/__init__.py	1	CODE
LOW	python/triton/experimental/gluon/language/__init__.py	1	CODE
447 more matches not shown…

Hallucination Indicators15 hits · 145 pts

Severity	File	Line	Snippet	Context
CRITICAL	python/test/unit/language/test_core.py	4225	if not is_interpreter() and triton.runtime.driver.active.utils.get_device_properties(	CODE
CRITICAL	python/test/unit/language/test_matmul.py	129	shared_mem_avail = triton.runtime.driver.active.utils.get_device_properties(0)["max_shared_mem"]	CODE
CRITICAL	python/test/gluon/test_frontend.py	786	%0 = tt.call @triton.experimental.gluon.language.nvidia.ampere.mbarrier.allocate_mbarrier__cNone_cTrue() : () -> !tt	CODE
CRITICAL	python/test/gluon/test_frontend.py	791	tt.func private @triton.experimental.gluon.language.nvidia.ampere.mbarrier.allocate_mbarrier__cNone_cTrue() -> !ttg.me	CODE
CRITICAL	python/test/gluon/test_frontend.py	3551	%13 = tt.call @triton.experimental.gluon.language._standard.zeros__Tc1T_cfp16_cAL() : () -> tensor<1xf16, #gluon.aut	CODE
CRITICAL	python/test/gluon/test_frontend.py	3579	tt.func private @triton.experimental.gluon.language._standard.zeros__Tc1T_cfp16_cAL() -> tensor<1xf16, #gluon.auto_enc	CODE
CRITICAL	python/test/gluon/test_frontend.py	3610	%1 = tt.call @triton.experimental.gluon.language._standard.zeros__Tc1T_cbf16_cAL() : () -> tensor<1xbf16, #gluon.aut	CODE
CRITICAL	python/test/gluon/test_frontend.py	3628	tt.func private @triton.experimental.gluon.language._standard.zeros__Tc1T_cbf16_cAL() -> tensor<1xbf16, #gluon.auto_en	CODE
CRITICAL	python/triton/language/core.py	3531	triton.runtime.driver.active.utils.set_printf_fifo_size(size_bytes)	STRING
CRITICAL	third_party/proton/proton/hooks/instrumentation.py	157	max_shared_mem = triton.runtime.driver.active.utils.get_device_properties(device)["max_shared_mem"]	CODE
CRITICAL	third_party/proton/proton/hooks/instrumentation.py	182	arch = triton.runtime.driver.active.utils.get_device_properties(device)["arch"].split(":")[0]	CODE
CRITICAL	third_party/amd/backend/driver.py	242	return triton.runtime.driver.active.utils.build_signature_metadata(kernel_signature)	CODE
CRITICAL	third_party/nvidia/backend/driver.py	182	return triton.runtime.driver.active.utils.build_signature_metadata(kernel_signature)	CODE
CRITICAL	third_party/nvidia/backend/driver.py	238	cu_tensor_map = triton.runtime.driver.active.utils.fill_tma_descriptor_im2col(	CODE
CRITICAL	third_party/nvidia/backend/driver.py	253	cu_tensor_map = triton.runtime.driver.active.utils.fill_tma_descriptor_tiled(	CODE

Deep Nesting153 hits · 128 pts

Severity	File	Line	Context
LOW	setup.py	129	CODE
LOW	python/build_helpers.py	313	CODE
LOW	python/test/unit/tools/test_triton_to_gluon.py	520	CODE
LOW	python/test/unit/cuda/test_libdevice_cuda.py	60	CODE
LOW	python/test/unit/runtime/test_specialize.py	41	CODE
LOW	python/test/unit/language/test_conversions.py	15	CODE
LOW	python/test/unit/language/test_conversions.py	277	CODE
LOW	python/test/unit/language/test_core.py	383	CODE
LOW	python/test/unit/language/test_core.py	2765	CODE
LOW	python/test/unit/language/test_core.py	2943	CODE
LOW	python/test/unit/language/test_core.py	3448	CODE
LOW	python/test/unit/language/test_core.py	3628	CODE
LOW	python/test/unit/language/test_core.py	4440	CODE
LOW	python/test/unit/language/test_core.py	4665	CODE
LOW	python/test/unit/language/test_core.py	4836	CODE
LOW	python/test/unit/language/test_core.py	5288	CODE
LOW	python/test/unit/language/test_core.py	5761	CODE
LOW	python/test/unit/language/test_core.py	2769	CODE
LOW	python/test/unit/language/test_core.py	5291	CODE
LOW	python/test/unit/language/test_core.py	5764	CODE
LOW	python/test/unit/language/test_pipeliner.py	215	CODE
LOW	python/test/unit/language/test_subprocess.py	37	CODE
LOW	python/test/unit/language/test_matmul.py	526	CODE
LOW	python/test/unit/language/test_matmul.py	665	CODE
LOW	python/test/unit/language/test_matmul.py	721	CODE
LOW	python/test/unit/language/test_line_info.py	164	CODE
LOW	python/test/unit/language/test_line_info.py	212	CODE
LOW	python/test/unit/language/test_annotations.py	62	CODE
LOW	python/test/unit/language/print_helper.py	107	CODE
LOW	python/test/unit/language/test_tensor_descriptor.py	1555	CODE
LOW	python/test/unit/language/test_tensor_descriptor.py	1564	CODE
LOW	python/test/gsan/test_gsan_failures.py	107	CODE
LOW	python/test/gsan/test_symmetric_memory.py	474	CODE
LOW	python/test/gsan/test_gsan.py	600	CODE
LOW	python/test/gluon/test_lowerings.py	15	CODE
LOW	python/test/gluon/test_lowerings.py	845	CODE
LOW	python/test/gluon/test_frontend.py	4305	CODE
LOW	python/test/gluon/test_frontend.py	4308	CODE
LOW	python/test/gluon/test_core.py	1193	CODE
LOW	python/test/gluon/test_core.py	2325	CODE
LOW	python/test/gluon/test_core.py	3202	CODE
LOW	python/test/gluon/test_core.py	3460	CODE
LOW	python/test/gluon/test_core.py	3572	CODE
LOW	python/test/gluon/test_core.py	1273	CODE
LOW	python/test/gluon/test_core.py	2332	CODE
LOW	python/test/gluon/test_consan.py	1048	CODE
LOW	python/test/gluon/test_consan.py	2964	CODE
LOW	python/test/gluon/test_consan.py	1076	CODE
LOW	python/test/gluon/test_consan.py	2975	CODE
LOW	python/test/gluon/test_fpsan.py	540	CODE
LOW	python/test/gluon/test_fpsan.py	900	CODE
LOW	python/test/gluon/test_fpsan.py	954	CODE
LOW	python/test/gluon/test_fpsan.py	1168	CODE
LOW	python/test/regression/test_functional_regressions.py	137	CODE
LOW	python/test/regression/test_functional_regressions.py	140	CODE
LOW	python/triton/knobs.py	297	CODE
LOW	python/triton/testing.py	45	CODE
LOW	python/triton/testing.py	119	CODE
LOW	python/triton/testing.py	189	CODE
LOW	python/triton/testing.py	340	CODE
93 more matches not shown…

Structural Annotation Overuse43 hits · 85 pts

Severity	File	Line	Snippet	Context
LOW⚡	README.md	261	# Step 1: Run the kernel once to dump kernel's IRs and ptx/amdgcn in $TRITON_DUMP_DIR	COMMENT
LOW⚡	README.md	262	# Step 2: Copy $TRITON_DUMP_DIR/<kernel_hash> to $TRITON_OVERRIDE_DIR	COMMENT
LOW⚡	README.md	263	# Step 3: Delete the stages that you do not want to override and modify the stage you do want to override	COMMENT
LOW⚡	README.md	264	# Step 4: Run the kernel again to see the overridden result	COMMENT
LOW⚡	python/tutorials/gluon/13-conv-im2col.py	149	# Step 1: Extract patches for each output position	COMMENT
LOW⚡	python/tutorials/gluon/13-conv-im2col.py	156	# Step 2: Stack patches into im2col matrix A (M=4, K=4)	COMMENT
LOW⚡	python/tutorials/gluon/13-conv-im2col.py	167	# Step 3: Reshape filter into weight matrix W (Co=1, K=4)	COMMENT
LOW⚡	python/tutorials/gluon/13-conv-im2col.py	171	# Step 4: Output = A @ W^T	COMMENT
LOW	…ude/triton/Conversion/TritonGPUToLLVM/TargetInfoBase.h	92	// NOTE: This function is used for backend debug. DO NOT DELETE.	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/TargetInfo.cpp	478	// Step 1: Right shift for 8 lanes.	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/TargetInfo.cpp	481	// Step 2: Right shift for 4 lanes.	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/TargetInfo.cpp	484	// Step 3: Right shift for 2 lanes.	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/TargetInfo.cpp	487	// Step 4: Right shift for 1 lane.	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/TargetInfo.cpp	490	// Step 5: Broadcast lane 15 of each row to all the lanes of its next row.	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/TargetInfo.cpp	493	// Step 6: Broadcast lane 31 to lane 32-63.	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/TargetInfo.cpp	498	// Step 7: Read the reduction result from lane 63 and broadcast with	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1035	// Step 1: extract EM bits for elements 0,2,4,6 and 1,3,5,7 respectively.	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1042	// Step 2: convert fp4 to fp8 using LUT	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1052	// Step 3: extract sign bits	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1056	// Step 4: assemble 4 packed fp8 values w/ sign	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1060	// Step 5: convert fp8 to fp32	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1142	// Step 1: extract EM bits for elements 0,2,4,6 and 1,3,5,7 respectively.	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1150	// Step 2: extract S bit for elements 0,2,4,6 and 1,3,5,7	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1158	// Step 3: Upcast elements 0,2,4,6 to 4 16-bit elements	COMMENT
LOW	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1187	// Step 4: Upcast elements 1,3,5,7 to 4 16-bit elements	COMMENT
LOW	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1217	// Step 5: Reorder 16-bit elements to be 0,1,2,3,4,5,6,7	COMMENT
LOW	…_party/amd/lib/TritonAMDGPUToLLVM/DotOpToLLVM/MFMA.cpp	500	// Step 1: construct each kBase-element vector by	COMMENT
LOW	…_party/amd/lib/TritonAMDGPUToLLVM/DotOpToLLVM/MFMA.cpp	512	// Step 2: process rawElems based on element type	COMMENT
LOW	…_party/amd/lib/TritonAMDGPUToLLVM/DotOpToLLVM/MFMA.cpp	532	// Step 3: Insert the processed vals into the ValueTable	COMMENT
LOW	…/lib/Transforms/WarpSpecialization/WSCodePartition.cpp	1229	// Step 1: collect all communications between producers and consumers.	COMMENT
LOW⚡	…/lib/Transforms/WarpSpecialization/WSCodePartition.cpp	1240	// Step 2: group channels	COMMENT
LOW⚡	…/lib/Transforms/WarpSpecialization/WSCodePartition.cpp	1249	// Step 3: reorder producer ops and the backward slices of the producer ops.	COMMENT
LOW⚡	…/lib/Transforms/WarpSpecialization/WSCodePartition.cpp	1252	// Step 4: find top-level ops that contain a channel, also create new ForOps	COMMENT
LOW⚡	…/lib/Transforms/WarpSpecialization/WSCodePartition.cpp	1272	// Step 5: Create buffers. An array of buffers for each channel.	COMMENT
LOW⚡	…/lib/Transforms/WarpSpecialization/WSCodePartition.cpp	1280	// Step 6: Lower the loads. Also add local copy ops for non-load	COMMENT
LOW⚡	…/lib/Transforms/WarpSpecialization/WSCodePartition.cpp	1290	// Step 7: Create tokens. A set of tokens for each group of channels for	COMMENT
LOW	…/lib/Transforms/WarpSpecialization/WSCodePartition.cpp	1301	// Step 8: add async communication ops (ProducerAcquire etc). Also lower	COMMENT
LOW⚡	…/hopper/lib/Transforms/WarpSpecialization/WSBuffer.cpp	304	// Step 1: Append accumCnts as forOp arguments.	COMMENT
LOW⚡	…/hopper/lib/Transforms/WarpSpecialization/WSBuffer.cpp	308	// Step 2: Add accumCnts to yieldOp.	COMMENT
LOW⚡	…/hopper/lib/Transforms/WarpSpecialization/WSBuffer.cpp	317	// Step 3: Create loop arguments for the new ForOp.	COMMENT
LOW⚡	…/hopper/lib/Transforms/WarpSpecialization/WSBuffer.cpp	326	// Step 4: Create newForOp and take the region of the original forOp.	COMMENT
LOW⚡	…/hopper/lib/Transforms/WarpSpecialization/WSBuffer.cpp	332	// Step 5: Replace forOp with newForOp.	COMMENT
LOW	lib/Dialect/TritonGPU/IR/LinearLayoutConversions.cpp	1151	// Step 3: Along the "register" dim, remove any all-zero bases.	COMMENT

Verbosity Indicators41 hits · 79 pts

Severity	File	Line	Snippet	Context
LOW	python/triton/runtime/jit.py	202	# The purpose of this function is to visit everything in `arguments`	COMMENT
LOW⚡	python/tutorials/gluon/13-conv-im2col.py	149	# Step 1: Extract patches for each output position	COMMENT
LOW⚡	python/tutorials/gluon/13-conv-im2col.py	156	# Step 2: Stack patches into im2col matrix A (M=4, K=4)	COMMENT
LOW⚡	python/tutorials/gluon/13-conv-im2col.py	167	# Step 3: Reshape filter into weight matrix W (Co=1, K=4)	COMMENT
LOW⚡	python/tutorials/gluon/13-conv-im2col.py	171	# Step 4: Output = A @ W^T	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/TargetInfo.cpp	478	// Step 1: Right shift for 8 lanes.	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/TargetInfo.cpp	481	// Step 2: Right shift for 4 lanes.	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/TargetInfo.cpp	484	// Step 3: Right shift for 2 lanes.	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/TargetInfo.cpp	487	// Step 4: Right shift for 1 lane.	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/TargetInfo.cpp	490	// Step 5: Broadcast lane 15 of each row to all the lanes of its next row.	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/TargetInfo.cpp	493	// Step 6: Broadcast lane 31 to lane 32-63.	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/TargetInfo.cpp	498	// Step 7: Read the reduction result from lane 63 and broadcast with	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1035	// Step 1: extract EM bits for elements 0,2,4,6 and 1,3,5,7 respectively.	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1042	// Step 2: convert fp4 to fp8 using LUT	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1052	// Step 3: extract sign bits	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1056	// Step 4: assemble 4 packed fp8 values w/ sign	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1060	// Step 5: convert fp8 to fp32	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1142	// Step 1: extract EM bits for elements 0,2,4,6 and 1,3,5,7 respectively.	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1150	// Step 2: extract S bit for elements 0,2,4,6 and 1,3,5,7	COMMENT
LOW⚡	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1158	// Step 3: Upcast elements 0,2,4,6 to 4 16-bit elements	COMMENT
LOW	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1187	// Step 4: Upcast elements 1,3,5,7 to 4 16-bit elements	COMMENT
LOW	third_party/amd/lib/TritonAMDGPUToLLVM/Utility.cpp	1217	// Step 5: Reorder 16-bit elements to be 0,1,2,3,4,5,6,7	COMMENT
LOW	…_party/amd/lib/TritonAMDGPUToLLVM/DotOpToLLVM/MFMA.cpp	500	// Step 1: construct each kBase-element vector by	COMMENT
LOW	…_party/amd/lib/TritonAMDGPUToLLVM/DotOpToLLVM/MFMA.cpp	512	// Step 2: process rawElems based on element type	COMMENT
LOW	…_party/amd/lib/TritonAMDGPUToLLVM/DotOpToLLVM/MFMA.cpp	532	// Step 3: Insert the processed vals into the ValueTable	COMMENT
LOW	…/lib/Transforms/WarpSpecialization/WSCodePartition.cpp	1229	// Step 1: collect all communications between producers and consumers.	COMMENT
LOW⚡	…/lib/Transforms/WarpSpecialization/WSCodePartition.cpp	1240	// Step 2: group channels	COMMENT
LOW⚡	…/lib/Transforms/WarpSpecialization/WSCodePartition.cpp	1249	// Step 3: reorder producer ops and the backward slices of the producer ops.	COMMENT
LOW⚡	…/lib/Transforms/WarpSpecialization/WSCodePartition.cpp	1252	// Step 4: find top-level ops that contain a channel, also create new ForOps	COMMENT
LOW⚡	…/lib/Transforms/WarpSpecialization/WSCodePartition.cpp	1272	// Step 5: Create buffers. An array of buffers for each channel.	COMMENT
LOW⚡	…/lib/Transforms/WarpSpecialization/WSCodePartition.cpp	1280	// Step 6: Lower the loads. Also add local copy ops for non-load	COMMENT
LOW⚡	…/lib/Transforms/WarpSpecialization/WSCodePartition.cpp	1290	// Step 7: Create tokens. A set of tokens for each group of channels for	COMMENT
LOW	…/lib/Transforms/WarpSpecialization/WSCodePartition.cpp	1301	// Step 8: add async communication ops (ProducerAcquire etc). Also lower	COMMENT
LOW⚡	…/hopper/lib/Transforms/WarpSpecialization/WSBuffer.cpp	304	// Step 1: Append accumCnts as forOp arguments.	COMMENT
LOW⚡	…/hopper/lib/Transforms/WarpSpecialization/WSBuffer.cpp	308	// Step 2: Add accumCnts to yieldOp.	COMMENT
LOW⚡	…/hopper/lib/Transforms/WarpSpecialization/WSBuffer.cpp	317	// Step 3: Create loop arguments for the new ForOp.	COMMENT
LOW⚡	…/hopper/lib/Transforms/WarpSpecialization/WSBuffer.cpp	326	// Step 4: Create newForOp and take the region of the original forOp.	COMMENT
LOW⚡	…/hopper/lib/Transforms/WarpSpecialization/WSBuffer.cpp	332	// Step 5: Replace forOp with newForOp.	COMMENT
LOW	third_party/nvidia/lib/NVGPUToLLVM/NVGPUToLLVMPass.cpp	606	// TODO: pred will have a long liverange, we need to check if this is a	COMMENT
LOW	lib/Dialect/TritonGPU/IR/LinearLayoutConversions.cpp	1151	// Step 3: Along the "register" dim, remove any all-zero bases.	COMMENT
LOW	…t/TritonInstrument/Transforms/ConcurrencySanitizer.cpp	887	// Op is writing to the buffer, we need to check if anything else	COMMENT

Modern Structural Boilerplate66 hits · 62 pts

Severity	File	Line	Snippet	Context
LOW	python/triton/__init__.py	33	__all__ = [	CODE
LOW	python/triton/experimental/gsan/__init__.py	4	__all__ = [	CODE
LOW	python/triton/experimental/gluon/__init__.py	6	__all__ = ["aggregate", "amd", "constexpr_function", "GluonJITFunction", "jit", "must_use_result", "nvidia"]	CODE
LOW	python/triton/experimental/gluon/_runtime.py	10	__all__ = ["GluonJITFunction", "constexpr_function", "jit"]	CODE
LOW	python/triton/experimental/gluon/language/_core.py	53	__all__ = [	CODE
LOW	python/triton/experimental/gluon/language/_core.py	301	def _set_name(self, builder: ir.builder, name: str) -> None:	STRING
LOW	python/triton/experimental/gluon/language/amd/slice.py	8	__all__ = ["slice"]	CODE
LOW	…hon/triton/experimental/gluon/language/amd/__init__.py	9	__all__ = [	CODE
LOW	…hon/triton/experimental/gluon/language/amd/_layouts.py	9	__all__ = [	CODE
LOW	…on/experimental/gluon/language/amd/cdna4/async_copy.py	6	__all__ = [	CODE
LOW	…iton/experimental/gluon/language/amd/cdna4/__init__.py	16	__all__ = [	CODE
LOW	…iton/experimental/gluon/language/amd/cdna3/__init__.py	13	__all__ = [	CODE
LOW	…iton/experimental/gluon/language/amd/rdna4/__init__.py	4	__all__ = ["wmma"]	CODE
LOW	…iton/experimental/gluon/language/amd/rdna3/__init__.py	4	__all__ = ["wmma"]	CODE
LOW	…/experimental/gluon/language/amd/gfx1250/async_copy.py	6	__all__ = ["global_to_shared", "shared_to_global", "commit_group", "wait_group", "mbarrier_arrive"]	CODE
LOW	…on/experimental/gluon/language/amd/gfx1250/__init__.py	14	__all__ = [	CODE
LOW	…/triton/experimental/gluon/language/amd/gfx1250/tdm.py	14	__all__ = [	CODE
LOW	…/triton/experimental/gluon/language/amd/gfx1250/tdm.py	66	def _set_name(self, builder: ir.builder, name: str) -> None:	CODE
LOW	…ton/experimental/gluon/language/amd/gfx1250/cluster.py	3	__all__ = ["arrive", "wait"]	CODE
LOW	…on/experimental/gluon/language/amd/gfx1250/_layouts.py	9	__all__ = [	CODE
LOW	…on/experimental/gluon/language/amd/gfx1250/mbarrier.py	5	__all__ = ["MBarrierLayout", "init", "wait", "arrive"]	CODE
LOW	…/triton/experimental/gluon/language/nvidia/__init__.py	4	__all__ = ["blackwell", "hopper"]	CODE
LOW	…/experimental/gluon/language/nvidia/hopper/__init__.py	11	__all__ = [	CODE
LOW	…/experimental/gluon/language/nvidia/hopper/__init__.py	90	def _set_name(self, builder: ir.builder, name: str) -> None:	CODE
LOW	…n/experimental/gluon/language/nvidia/hopper/cluster.py	5	__all__ = ["arrive", "wait", "barrier"]	CODE
LOW	…riton/experimental/gluon/language/nvidia/hopper/tma.py	12	__all__ = [	CODE
LOW	…riton/experimental/gluon/language/nvidia/hopper/tma.py	121	def _set_name(self, builder: ir.builder, name: str) -> None:	CODE
LOW	…/experimental/gluon/language/nvidia/hopper/mbarrier.py	4	__all__ = [	CODE
LOW	…experimental/gluon/language/nvidia/blackwell/float2.py	5	__all__ = [	CODE
LOW	…perimental/gluon/language/nvidia/blackwell/__init__.py	21	__all__ = [	CODE
LOW	…perimental/gluon/language/nvidia/blackwell/__init__.py	227	def _set_name(self, builder: ir.builder, name: str) -> None:	CODE
LOW	…on/experimental/gluon/language/nvidia/blackwell/tma.py	22	__all__ = [	CODE
LOW	…on/experimental/gluon/language/nvidia/blackwell/clc.py	18	__all__ = [	CODE
LOW	…on/experimental/gluon/language/nvidia/blackwell/clc.py	86	def _set_name(self, builder: ir.builder, name: str) -> None:	CODE
LOW	…xperimental/gluon/language/nvidia/ampere/async_copy.py	5	__all__ = [	CODE
LOW	…/experimental/gluon/language/nvidia/ampere/__init__.py	9	__all__ = ["async_copy", "mbarrier", "mma_v2"]	CODE
LOW	…/experimental/gluon/language/nvidia/ampere/mbarrier.py	8	__all__ = ["allocate_mbarrier", "arrive", "init", "invalidate", "MBarrierLayout", "wait"]	CODE
LOW	…n/triton/experimental/gluon/language/extra/__init__.py	3	__all__ = ["libdevice"]	CODE
LOW	python/triton/experimental/gluon/amd/__init__.py	3	__all__ = ["gfx1250"]	CODE
LOW	python/triton/experimental/gluon/amd/gfx1250.py	7	__all__ = ["TensorDescriptor"]	CODE
LOW	python/triton/experimental/gluon/nvidia/blackwell.py	3	__all__ = ["TensorDescriptor"]	CODE
LOW	python/triton/experimental/gluon/nvidia/__init__.py	4	__all__ = ["hopper", "blackwell"]	CODE
LOW	python/triton/experimental/gluon/nvidia/hopper.py	7	__all__ = ["TensorDescriptor", "TensorDescriptorIm2Col"]	CODE
LOW	…riton/tools/triton_to_gluon_translator/slice_kernel.py	31	logger = logging.getLogger(__name__)	CODE
LOW	python/triton/runtime/__init__.py	7	__all__ = [	CODE
LOW	python/triton/runtime/interpreter.py	907	def set_attr(self, obj: object, name: str, value: object) -> None:	CODE
LOW	python/triton/runtime/_allocation.py	29	def set_allocator(allocator: Allocator) -> None:	CODE
LOW	python/triton/runtime/_allocation.py	59	def set_profile_allocator(allocator: Optional[Allocator]) -> None:	CODE
LOW	python/triton/runtime/driver.py	42	def set_active(self, driver: DriverBase) -> None:	CODE
LOW	python/triton/language/__init__.py	144	__all__ = [	CODE
LOW	python/triton/language/core.py	162	def _set_name(self, builder: ir.builder, name: str) -> None:	CODE
LOW	python/triton/language/core.py	239	def _set_name(self, builder: ir.builder, name: str) -> None:	CODE
LOW	python/triton/language/core.py	903	def _set_name(self, builder: ir.builder, name: str) -> None:	CODE
LOW	python/triton/language/core.py	1351	def _set_name(self, builder: ir.builder, name: str) -> None:	CODE
LOW	python/triton/language/core.py	1418	def _set_name(self, builder: ir.builder, name: str) -> None:	CODE
LOW	python/triton/language/core.py	1544	def _set_name(self, builder: ir.builder, name: str) -> None:	CODE
LOW	python/triton/language/core.py	1722	def _set_name(self, builder: ir.builder, name: str) -> None:	CODE
LOW	python/triton/language/target_info.py	4	__all__ = ["current_target"]	CODE
LOW	python/triton/compiler/__init__.py	4	__all__ = [	CODE
LOW⚡	python/triton/compiler/code_generator.py	444	def set_value(self, name: str, value: Union[base_value, constexpr]) -> None:	CODE
6 more matches not shown…

Excessive Try-Catch Wrapping45 hits · 51 pts

Severity	File	Line	Snippet	Context
LOW	setup.py	528	except Exception:	CODE
LOW	setup.py	536	except Exception:	CODE
MEDIUM	setup.py	524	def get_git_commit_hash(length=8):	CODE
MEDIUM	setup.py	532	def get_git_branch():	CODE
LOW	python/test/unit/runtime/test_cache.py	883	except Exception as e:	STRING
LOW⚡	python/test/unit/language/test_core.py	5268	except Exception as e:	STRING
LOW	python/test/unit/language/test_decorator.py	27	except Exception as e:	CODE
LOW	python/test/backend/test_mir_stage.py	11	except Exception:	CODE
MEDIUM	python/test/backend/test_mir_stage.py	8	def is_hip():	CODE
LOW	python/triton/_internal_testing.py	262	except Exception as e:	CODE
LOW	python/triton/experimental/gsan/symmetric_memory.py	165	except Exception:	CODE
LOW	python/triton/experimental/gsan/symmetric_memory.py	267	except Exception:	CODE
LOW	python/triton/experimental/gsan/symmetric_memory.py	454	except Exception:	CODE
MEDIUM	python/triton/experimental/gsan/symmetric_memory.py	264	def __del__(self) -> None:	CODE
LOW	python/triton/experimental/gsan/_utils.py	113	except Exception:	CODE
LOW	python/triton/runtime/cache.py	81	except Exception:	CODE
LOW	python/triton/runtime/cache.py	225	except Exception:	CODE
LOW	python/triton/runtime/_async_compile.py	22	except Exception:	CODE
LOW	python/triton/runtime/interpreter.py	1425	except Exception as e:	CODE
LOW	python/triton/runtime/interpreter.py	1466	except Exception:	CODE
LOW	python/triton/runtime/interpreter.py	1559	except Exception as e:	CODE
LOW	python/triton/runtime/autotuner.py	159	except Exception as e:	CODE
LOW	python/triton/compiler/compiler.py	308	except Exception as e:	CODE
LOW	python/triton/compiler/code_generator.py	1382	except Exception as e:	CODE
LOW	python/triton/compiler/code_generator.py	1433	except Exception as e:	CODE
LOW	python/triton/compiler/code_generator.py	1598	except Exception as e:	CODE
LOW	python/triton/compiler/code_generator.py	1633	except Exception as e:	CODE
LOW	python/examples/gluon/02-conv-dgrad.py	980	except Exception:	CODE
MEDIUM	python/examples/gluon/02-conv-dgrad.py	937	def _benchmark_dgrad_config(	CODE
LOW	python/examples/gluon/02-conv-wgrad.py	735	except Exception:	CODE
MEDIUM	python/examples/gluon/02-conv-wgrad.py	692	def _benchmark_wgrad_config(	CODE
LOW	third_party/proton/test/test_instrumentation.py	938	except Exception as e:	CODE
MEDIUM	third_party/proton/test/test_instrumentation.py	935	def run_kernel():	CODE
LOW	third_party/proton/test/test_api.py	98	except Exception as e:	CODE
LOW	third_party/proton/test/test_api.py	120	except Exception as e:	CODE
LOW	third_party/proton/test/test_api.py	133	except Exception as e:	CODE
LOW	third_party/proton/test/test_api.py	287	except Exception as e:	CODE
LOW	third_party/proton/test/test_api.py	404	except Exception as e:	CODE
LOW	third_party/proton/test/test_api.py	414	except Exception as e:	CODE
LOW	…ton/test/reproducers/cupti_graph_replay_heap_growth.py	275	except Exception:	CODE
LOW	third_party/proton/proton/proton.py	46	except Exception as e:	STRING
MEDIUM	third_party/proton/proton/proton.py	47	print("An error occurred while executing the script:")	STRING
LOW⚡	third_party/amd/python/test/test_gluon_gfx1250.py	2020	except Exception as e:	CODE
LOW	third_party/amd/backend/driver.py	45	except Exception:	CODE
LOW	third_party/nvidia/backend/driver.py	58	except Exception:	CODE

Self-Referential Comments17 hits · 49 pts

Severity	File	Line	Snippet	Context
MEDIUM	python/build_helpers.py	356	# Create a stable symlink that doesn't include revision	COMMENT
MEDIUM	python/test/gluon/test_core.py	3028	# Create a test matrix with known values	COMMENT
MEDIUM	python/test/gluon/test_core.py	3860	# Create a test matrix [N, M]	COMMENT
MEDIUM	python/test/gluon/test_core.py	4021	# Create a test tensor [N, M, P]	COMMENT
MEDIUM	python/triton/experimental/gluon/language/_semantic.py	618	# Create the warp specialize op.	COMMENT
MEDIUM	python/triton/experimental/gluon/language/_layouts.py	617	# Create a idendity mapping based on shape_per_cta + order	COMMENT
MEDIUM	python/triton/runtime/jit.py	404	# Create the function argument list and the dict entries for the return statement	COMMENT
MEDIUM	python/triton/runtime/jit.py	1144	# Create a bound function to support constexpr_function methods	STRING
MEDIUM	python/triton/language/core.py	1674	# Define the wrapped Triton value type.	COMMENT
MEDIUM	…rnels/tensor_details/layout_details/blackwell_scale.py	181	# The following code is equivalent to the above, but faster for GPU tensors.	COMMENT
MEDIUM	python/tutorials/02-fused-softmax.py	173	# Create a number of persistent programs.	COMMENT
MEDIUM	python/tutorials/01-vector-add.py	46	# Create a mask to guard memory operations against out-of-bounds accesses.	COMMENT
MEDIUM	docs/conf.py	6	# This file is execfile()d with the current directory set to its	COMMENT
MEDIUM	third_party/proton/proton/hooks/instrumentation.py	39	# Create the buffer	COMMENT
MEDIUM	third_party/proton/proton/hooks/instrumentation.py	111	# Create the appropriate mode instance	COMMENT
MEDIUM	third_party/amd/python/test/test_gluon_gfx1250.py	2238	# Create a flattened view into the nD reference to unify the indexing logic over all dimensions	COMMENT
MEDIUM	…ird_party/amd/python/examples/gluon/mxfp_fa_gfx1250.py	3063	# Create a pytest id	COMMENT

AI Slop Vocabulary15 hits · 40 pts

Severity	File	Line	Snippet	Context
MEDIUM	…riton/tools/triton_to_gluon_translator/slice_kernel.py	118	# HACK: An AST rewrite would be more robust, but this works for now.	COMMENT
MEDIUM	python/triton/runtime/cache.py	115	# use temp dir to be robust against program interruptions	COMMENT
LOW	python/triton/runtime/interpreter.py	1463	# e.g., dynamically generated functions, we cannot rewrite it so just return the original function	COMMENT
MEDIUM	python/triton_kernels/bench/bench_dense_matmul.py	3	# This is not meant to be a comprehensive benchmark of triton_kernels.	COMMENT
MEDIUM	python/triton_kernels/bench/bench_dense_matmul.py	135	# even for the fp16 benchmark path. Match that when reproducing the OpenAI harness.	COMMENT
MEDIUM	python/tutorials/09-persistent-matmul.py	411	# Enable warp specialization to leverage async warp scheduling in the GPU.	COMMENT
MEDIUM	python/tutorials/10-block-scaled-matmul.py	390	# With 256 elements we better utilize the L2 and don't require the TMA	COMMENT
MEDIUM	python/tutorials/gluon/11-tcgen05-mma-scaled.py	654	# elements. With 256 bytes along the inner dimension, we better utilize the	COMMENT
MEDIUM	python/tutorials/gluon/08-warp-specialization.py	369	# specialization is especially powerful when used to build intricate schedules	COMMENT
MEDIUM	python/tutorials/gluon/02-layouts.py	868	# Linear layouts are extremely poweful, and can be used in conjunction with	COMMENT
MEDIUM	python/tutorials/gluon/07-persistence.py	841	# work in conjunction with the GPU, getting the best of both worlds. This is	COMMENT
LOW	third_party/amd/python/test/test_gluon_gfx1250.py	2802	# In practice, since we know that phase is initialized to 0, we can just set count = NUM_WARPS * WARP_SIZE and call	COMMENT
LOW	third_party/amd/python/test/test_gluon_gfx1250.py	2863	# In practice, since we know that phase is initialized to 0, we can just set count = NUM_WARPS and call directly ttg	COMMENT
MEDIUM	…party/amd/lib/TritonAMDGPUTransforms/ScheduleLoops.cpp	210	/// which is not coalesced. To better utilize global memory bandwidth,	COMMENT
MEDIUM	…party/amd/lib/TritonAMDGPUToLLVM/LoadStoreOpToLLVM.cpp	2261	// In the case of unpaired f16 elements utilize dpp instructions to	COMMENT

AI Structural Patterns39 hits · 36 pts

Severity	File	Line	Context
LOW	python/test/unit/language/test_core.py	221	CODE
LOW	python/triton/testing.py	22	CODE
LOW	python/triton/experimental/gluon/_runtime.py	75	CODE
LOW	python/triton/tools/ragged_tma.py	76	CODE
LOW	…/tools/triton_to_gluon_translator/blackwell_helpers.py	93	CODE
LOW	…/tools/triton_to_gluon_translator/blackwell_helpers.py	205	CODE
LOW	…/tools/triton_to_gluon_translator/blackwell_helpers.py	304	CODE
LOW	…triton/tools/triton_to_gluon_translator/amd_helpers.py	302	CODE
LOW	…ton/tools/triton_to_gluon_translator/nvidia_helpers.py	53	CODE
LOW	…ton/tools/triton_to_gluon_translator/nvidia_helpers.py	133	CODE
LOW	…/triton/tools/triton_to_gluon_translator/translator.py	256	CODE
LOW	python/triton/runtime/jit.py	953	CODE
LOW	python/triton/runtime/autotuner.py	408	CODE
LOW	python/triton/runtime/autotuner.py	21	CODE
LOW	python/triton/language/standard.py	389	CODE
LOW	python/triton/language/core.py	2497	CODE
LOW	python/triton/language/core.py	1911	CODE
LOW	python/triton/language/core.py	3802	CODE
LOW	python/triton/compiler/code_generator.py	288	CODE
LOW	python/examples/gluon/04-2cta-block-scale-matmul.py	797	CODE
LOW	python/triton_kernels/triton_kernels/matmul.py	243	CODE
LOW	python/triton_kernels/triton_kernels/matmul.py	823	CODE
LOW	python/triton_kernels/triton_kernels/reduce.py	664	CODE
LOW	python/triton_kernels/triton_kernels/reduce.py	1143	CODE
LOW	python/triton_kernels/triton_kernels/reduce.py	1181	CODE
LOW	python/triton_kernels/triton_kernels/testing.py	238	CODE
LOW	python/triton_kernels/triton_kernels/swiglu.py	100	CODE
LOW	python/triton_kernels/triton_kernels/swiglu.py	82	CODE
LOW	…n_kernels/tensor_details/layout_details/cdna4_scale.py	77	CODE
LOW	…_kernels/tensor_details/layout_details/hopper_value.py	224	CODE
LOW	…_kernels/tensor_details/layout_details/hopper_value.py	187	CODE
LOW	…rnels/tensor_details/layout_details/blackwell_scale.py	213	CODE
LOW	…_kernels/tensor_details/layout_details/hopper_scale.py	112	CODE
LOW	…ton_kernels/triton_kernels/matmul_details/_p_matmul.py	62	CODE
LOW	…riton_kernels/triton_kernels/matmul_details/_matmul.py	43	CODE
LOW	python/tutorials/02-fused-softmax.py	59	CODE
LOW	python/tutorials/gluon/14-multicta.py	1066	CODE
LOW	third_party/amd/python/examples/gluon/moe_gfx1250.py	1202	CODE
LOW	…ird_party/amd/python/examples/gluon/mxfp_fa_gfx1250.py	2918	CODE

Overly Generic Function Names19 hits · 20 pts

Severity	File	Line	Snippet	Context
LOW⚡	python/test/unit/tools/test_slice_kernel.py	723	def helper() -> None:	CODE
LOW⚡	python/test/unit/tools/test_slice_kernel.py	739	def helper() -> int:	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	130	def helper() -> int:	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	157	def helper() -> int:	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	178	def helper() -> int:	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	205	def helper() -> int:	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	440	def helper() -> None:	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	455	def helper() -> None:	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	475	def helper():	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	490	def helper():	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	513	def helper() -> None:	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	532	def helper() -> None:	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	581	def helper():	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	596	def helper():	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	623	def helper() -> None:	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	642	def helper() -> None:	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	665	def helper() -> None:	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	684	def helper() -> None:	CODE
LOW	python/test/unit/tools/test_slice_kernel.py	707	def helper() -> None:	CODE

Cross-File Repetition3 hits · 15 pts

Severity	File	Snippet	Context
HIGH	…iton/experimental/gluon/language/amd/rdna4/__init__.py	computes matrix-multiplication of a * b + acc using amd wmma instruction. args: a (tensor): the operand a to be multipli	STRING
HIGH	…iton/experimental/gluon/language/amd/rdna3/__init__.py	computes matrix-multiplication of a * b + acc using amd wmma instruction. args: a (tensor): the operand a to be multipli	STRING
HIGH	…on/experimental/gluon/language/amd/gfx1250/__init__.py	computes matrix-multiplication of a * b + acc using amd wmma instruction. args: a (tensor): the operand a to be multipli	STRING

Redundant / Tautological Comments10 hits · 13 pts

Severity	File	Line	Snippet	Context
LOW	python/build_helpers.py	96	# Set timeout to 300 seconds to prevent the request from hanging forever.	COMMENT
LOW	python/triton/compiler/code_generator.py	143	# Check if the given syntax node has an "early" return	COMMENT
LOW	utils/generate-test-checks.py	177	# Check if an existing variable exists for this name.	STRING
LOW	utils/generate-test-checks.py	320	# Check if this is an attribute definition and process it	STRING
LOW	third_party/proton/proton/hooks/hook.py	93	# Check if any other sessions rely on this hook	COMMENT
LOW	third_party/amd/python/test/address_sanitizer_helper.py	23	#Set access to go out of bounds for ASAN test	COMMENT
LOW	third_party/amd/backend/driver.py	330	# Check if cooperative groups are supported on the device.	COMMENT
LOW	.github/workflows/integration-tests-nvidia.yml	41	# Check if files exist before proceeding	COMMENT
LOW	.github/workflows/integration-tests-amd.yml	65	# Check if files exist before proceeding	COMMENT
LOW	.github/workflows/build-macos.yml	37	# Check if files exist before proceeding	COMMENT

Cross-Language Confusion2 hits · 10 pts

Severity	File	Line	Snippet	Context
HIGH	python/test/unit/tools/test_aot.py	147	while (fscanf(file, "%hd,", &buffer[index]) != EOF && index < size) {	CODE
HIGH	python/triton/experimental/gsan/symmetric_memory.py	406	stack.push(listener)	CODE

Slop Phrases4 hits · 8 pts

Severity	File	Line	Snippet	Context
LOW	python/test/unit/language/test_core.py	6671	# reuse the temp variable and make sure to check that it isn't creating incorrect IR.	STRING
LOW	python/tutorials/01-vector-add.py	74	# - Don't forget to pass meta-parameters as keywords arguments.	COMMENT
MEDIUM	python/tutorials/gluon/14-multicta.py	357	# It's worth noting that the pattern changes a bit once the TMA has to wait on the tcgen05_mma	COMMENT
MEDIUM	python/tutorials/gluon/02-layouts.py	839	# require reordering registers within a thread (which is free), you can use	COMMENT

AI Response Leakage1 hit · 8 pts

Severity	File	Line	Snippet	Context
HIGH	python/tutorials/11-programmatic-dependent-launch.py	26	# In this example	COMMENT

Fake / Example Data11 hits · 6 pts

Severity	File	Line	Snippet	Context
LOW⚡	python/test/unit/language/test_line_info.py	585	run_filecheck("placeholder", h.asm["ttir"], check_template)	STRING
LOW	python/test/unit/language/test_line_info.py	344	run_filecheck("placeholder", h.asm["ttir"], check_template)	STRING
LOW	python/test/unit/language/test_line_info.py	364	run_filecheck("placeholder", h.asm["ttir"], check_template)	STRING
LOW	python/test/unit/language/test_line_info.py	383	run_filecheck("placeholder", h.asm["ttir"], check_template)	STRING
LOW	python/test/unit/language/test_line_info.py	396	run_filecheck("placeholder", h.asm["ttir"], check_template)	STRING
LOW	python/test/unit/language/test_line_info.py	416	run_filecheck("placeholder", h.asm["ttir"], check_template)	STRING
LOW	python/test/unit/language/test_line_info.py	442	run_filecheck("placeholder", h.asm["ttir"], check_template)	STRING
LOW	python/test/unit/language/test_line_info.py	466	run_filecheck("placeholder", h.asm["ttir"], check_template)	STRING
LOW	python/test/unit/language/test_line_info.py	493	run_filecheck("placeholder", h.asm["ttir"], check_template)	STRING
LOW	python/test/unit/language/test_line_info.py	606	run_filecheck("placeholder", h.asm["ttir"], check_template)	STRING
LOW	python/triton/_filecheck.py	87	run_filecheck("placeholder", mlir_module.str_nodebug(), check_template)	CODE

Docstring Block Structure1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	…/triton/experimental/gluon/language/amd/gfx1250/tdm.py	160	Update selected fields of a TDM descriptor; return a new descriptor SSA value. Each parameter is independently opti	STRING

TODO Padding3 hits · 4 pts

Severity	File	Line	Snippet	Context
LOW	third_party/amd/backend/include/hip/hip_runtime_api.h	2500	// TODO: implement IPC apis	COMMENT
LOW	lib/Analysis/Alias.cpp	67	// TODO: implement	COMMENT
LOW	lib/Analysis/Alias.cpp	73	// TODO: implement	COMMENT

Dead Code2 hits · 4 pts

Severity	File	Line	Snippet	Context
MEDIUM	python/test/unit/language/test_compile_errors.py	171		CODE
MEDIUM	python/triton_kernels/triton_kernels/tensor.py	98		CODE

Example Usage Blocks1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	bin/triton-tensor-layout.cpp	23	// Example usage:	COMMENT

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings