From 5e609dab7856bef0834895db6b64ee4bc430e0d4 Mon Sep 17 00:00:00 2001
From: Oleksandr Pavlyk <21087696+oleksandr-pavlyk@users.noreply.github.com>
Date: Sun, 28 Jun 2026 18:42:07 -0500
Subject: [PATCH] Respect custom bulk readers in materiality checks

Move Float32BinarySource material-payload detection into the source object.
Default file-backed sources still use resolved file size so missing or empty
sidecars remain unavailable, but positive-count sources with custom readers are
treated as material and proceed through the lazy read path.

Add regression coverage for virtual bulk sources whose custom reader provides
data without a local sidecar file.
---
 python/scripts/nvbench_compare.py   | 25 ++++++++++++++---------
 python/test/test_nvbench_compare.py | 31 +++++++++++++++++++++++++++++
 2 files changed, 47 insertions(+), 9 deletions(-)

diff --git a/python/scripts/nvbench_compare.py b/python/scripts/nvbench_compare.py
index 5afa28a..d02f5a3 100644
--- a/python/scripts/nvbench_compare.py
+++ b/python/scripts/nvbench_compare.py
@@ -425,6 +425,19 @@ class Float32BinarySource:
             self.count, self.filename, self.json_dir, self.description, self.reader
         )
 
+    def has_material_payload(self) -> bool:
+        if self.count <= 0:
+            return False
+
+        if self.reader is not read_float32_file:
+            return True
+
+        filename = resolve_binary_filename(self.json_dir, self.filename)
+        try:
+            return os.path.getsize(filename) > 0
+        except OSError:
+            return False
+
 
 @dataclass(frozen=True)
 class GpuTimingData:
@@ -1568,15 +1581,9 @@ def has_material_bulk_source(source):
     if source is None:
         return False
 
-    if isinstance(source, Float32BinarySource):
-        if source.count <= 0:
-            return False
-
-        filename = resolve_binary_filename(source.json_dir, source.filename)
-        try:
-            return os.path.getsize(filename) > 0
-        except OSError:
-            return False
+    has_material_payload = getattr(source, "has_material_payload", None)
+    if callable(has_material_payload):
+        return has_material_payload()
 
     values = getattr(source, "values", None)
     return values is not None and len(values) > 0
diff --git a/python/test/test_nvbench_compare.py b/python/test/test_nvbench_compare.py
index 92221fa..b2a6eac 100644
--- a/python/test/test_nvbench_compare.py
+++ b/python/test/test_nvbench_compare.py
@@ -1220,6 +1220,37 @@ def test_compare_gpu_timings_classifies_common_cases(tmp_path, nvbench_compare):
     assert missing_bulk_files.status == nvbench_compare.ComparisonStatus.FAST
     assert missing_bulk_files.reason.code == "clear_gap_confirmed_by_summary_cycles"
 
+    def virtual_reader(_):
+        return np.asarray([1.0, 1.1, 1.2, 1.3], dtype="<f4")
+
+    virtual_source = nvbench_compare.Float32BinarySource(
+        count=4,
+        filename="virtual.bin",
+        json_dir=str(tmp_path),
+        description="virtual sample",
+        reader=virtual_reader,
+    )
+    virtual_bulk_files = nvbench_compare.compare_gpu_timings(
+        replace(
+            ref_interval_timing,
+            sample_source=virtual_source,
+            frequency_source=virtual_source,
+        ),
+        make_gpu_timing_data(
+            nvbench_compare,
+            minimum=0.8,
+            first_quartile=0.85,
+            median=0.9,
+            third_quartile=0.95,
+            mean=0.9,
+            stdev_relative=0.05,
+            sample_values=[0.8, 0.85, 0.9, 0.95],
+            frequency_values=[100.0] * 4,
+        ),
+    )
+    assert virtual_bulk_files is not None
+    assert virtual_bulk_files.reason.code == "bulk_cycle_gap_not_confirmed"
+
     unusable_bulk_cycles = nvbench_compare.compare_gpu_timings(
         make_gpu_timing_data(
             nvbench_compare,