tt-perf-report 1.1.4__tar.gz → 1.1.6__tar.gz

{tt_perf_report-1.1.4/src/tt_perf_report.egg-info → tt_perf_report-1.1.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tt-perf-report
-Version: 1.1.4
+Version: 1.1.6
 Summary: This tool analyzes performance traces from TT-Metal operations, providing insights into throughput, bottlenecks, and optimization opportunities.
 License:                                  Apache License
                                    Version 2.0, January 2004

{tt_perf_report-1.1.4 → tt_perf_report-1.1.6}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "tt-perf-report"
-version = "1.1.4"
+version = "1.1.6"
 description = "This tool analyzes performance traces from TT-Metal operations, providing insights into throughput, bottlenecks, and optimization opportunities."
 license = {file = "LICENSE"}
 readme = "README.md"

{tt_perf_report-1.1.4 → tt_perf_report-1.1.6}/src/tt_perf_report/perf_report.py

@@ -866,11 +866,14 @@ def generate_matmul_advice(op_data):
 
 
 def generate_stacked_report(rows, visible_headers, stack_by_input0_layout:bool = False):
+    # Ensure we filter out signpost rows before processing because they aren't useful in the stacked report
+    filtered_rows = [row for row in rows if row["OP TYPE"].raw_value != "signpost"]
+    
     if stack_by_input0_layout:
         visible_headers.append("Input 0 Memory")
 
     # Create a pandas DataFrame from rows and headers
-    data = {header: [row[header].raw_value for row in rows] for header in visible_headers}
+    data = {header: [row[header].raw_value for row in filtered_rows] for header in visible_headers}
     df = pd.DataFrame(data)
 
     if (stack_by_input0_layout):
@@ -882,7 +885,7 @@ def generate_stacked_report(rows, visible_headers, stack_by_input0_layout:bool =
     # Group by the joined OP Code and aggregate the data
     stacked_df = df.groupby("OP Code Joined").agg(
         Device_Time_Sum_us=("Device Time", "sum"),
-        Ops_Count=("Device Time", "count"),
+        Ops_Count=("Device Time", "size"),
         Flops_min=("FLOPs %", "min"),
         Flops_max=("FLOPs %", "max"),
         Flops_mean=("FLOPs %", "mean"),
@@ -891,7 +894,12 @@ def generate_stacked_report(rows, visible_headers, stack_by_input0_layout:bool =
 
     # Calculate the percentage of device time
     total_device_time = stacked_df["Device_Time_Sum_us"].sum()
-    stacked_df["%"] = (stacked_df["Device_Time_Sum_us"] / total_device_time) * 100
+
+    if total_device_time != 0:
+        stacked_df["%"] = (stacked_df["Device_Time_Sum_us"] / total_device_time) * 100
+    else:
+        stacked_df["%"] = 0
+        
     # Reorder columns to move Device_Time_Percentage to be the 3rd column
     cols = stacked_df.columns.tolist()
     cols.insert(0, cols.pop(cols.index("%")))

{tt_perf_report-1.1.4 → tt_perf_report-1.1.6/src/tt_perf_report.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tt-perf-report
-Version: 1.1.4
+Version: 1.1.6
 Summary: This tool analyzes performance traces from TT-Metal operations, providing insights into throughput, bottlenecks, and optimization opportunities.
 License:                                  Apache License
                                    Version 2.0, January 2004