From 0ebebe5b064cda97d86f9138c2bfe4dfe083320b Mon Sep 17 00:00:00 2001
From: likai00 <maohaohao@huawei.com>
Date: Tue, 14 Jul 2026 21:53:24 +0800
Subject: [PATCH] fix tfillpad

---
 lib/TileOps/tfillpad_expand_template.py | 31 +++++++++++++------------
 lib/TileOps/tfillpad_template.py        | 31 +++++++++++++------------
 2 files changed, 32 insertions(+), 30 deletions(-)

diff --git a/lib/TileOps/tfillpad_expand_template.py b/lib/TileOps/tfillpad_expand_template.py
index 9fa3f435cd..6368503484 100644
--- a/lib/TileOps/tfillpad_expand_template.py
+++ b/lib/TileOps/tfillpad_expand_template.py
@@ -74,12 +74,12 @@ def template_tfillpad_expand(src: pto.Tile, dst: pto.Tile):
     has_valid_expansion = (src_valid_cols < dst_valid_cols) or (src_valid_rows < dst_valid_rows)
 
     # PadValue handling - dtype-specific
-    if pto.constexpr(dtype == pto.f32):
-        if pto.constexpr(dst.pad_value == pto.PadValue.ZERO):
-            if has_valid_expansion:
-                fill_scalar = pto.f32(_NEG1_F32)
-            else:
-                fill_scalar = pto.f32(0.0)
+    if pto.constexpr(dtype == pto.f32):
+        if pto.constexpr(dst.pad_value == pto.PadValue.ZERO):
+            if has_valid_expansion:
+                fill_scalar = pto.f32(_NEG1_F32)
+            else:
+                fill_scalar = pto.f32(0.0)
         elif pto.constexpr(dst.pad_value != pto.PadValue.NULL):
             fill_scalar = dst.pad_value.eval()
         else:
@@ -131,15 +131,16 @@ def template_tfillpad_expand(src: pto.Tile, dst: pto.Tile):
             fill_scalar = pto.i8(0)
 
     # Phase 1: Copy aligned valid blocks
-    for row in range(0, src_valid_rows, 1):
-        remained = aligned_col
-        for col in range(0, aligned_col, lanes):
-            mask, remained = pto.make_mask(dtype, remained)
-            data = pto.vlds(src[row, col:])
-            pto.vsts(data, dst[row, col:], mask)
+    if aligned_col > 0:
+        for row in range(0, src_valid_rows, 1):
+            remained = aligned_col
+            for col in range(0, aligned_col, lanes):
+                mask, remained = pto.make_mask(dtype, remained)
+                data = pto.vlds(src[row, col:])
+                pto.vsts(data, dst[row, col:], mask)
 
     # Phase 2: Fill col padding
-    if aligned_col < dst_valid_cols:
+    if aligned_col < dst_valid_cols:
         for row in range(0, dst_valid_rows, 1):
             remained = dst_valid_cols - aligned_col
             for col in range(aligned_col, dst_valid_cols, lanes):
@@ -148,7 +149,7 @@ def template_tfillpad_expand(src: pto.Tile, dst: pto.Tile):
                 pto.vsts(vec, dst[row, col:], mask)
 
     # Phase 3: Copy tail valid lanes
-    if has_tail:
+    if has_tail:
         for row in range(0, src_valid_rows, 1):
             remained = src_valid_cols - aligned_col
             mask_copy, remained = pto.make_mask(dtype, remained)
@@ -164,4 +165,4 @@ def template_tfillpad_expand(src: pto.Tile, dst: pto.Tile):
                 vec = pto.vdup(fill_scalar, mask)
                 pto.vsts(vec, dst[row, col:], mask)
 
-    return
+    return
diff --git a/lib/TileOps/tfillpad_template.py b/lib/TileOps/tfillpad_template.py
index 3378cb1983..b78af6f821 100644
--- a/lib/TileOps/tfillpad_template.py
+++ b/lib/TileOps/tfillpad_template.py
@@ -80,12 +80,12 @@ def template_tfillpad(src: pto.Tile, dst: pto.Tile):
     has_valid_expansion = (src_valid_cols < dst_valid_cols) or (src_valid_rows < dst_valid_rows)
 
     # PadValue handling - dtype-specific (inline to avoid external call)
-    if pto.constexpr(dtype == pto.f32):
-        if pto.constexpr(dst.pad_value == pto.PadValue.ZERO):
-            if has_valid_expansion:
-                fill_scalar = pto.f32(_NEG1_F32)
-            else:
-                fill_scalar = pto.f32(0.0)
+    if pto.constexpr(dtype == pto.f32):
+        if pto.constexpr(dst.pad_value == pto.PadValue.ZERO):
+            if has_valid_expansion:
+                fill_scalar = pto.f32(_NEG1_F32)
+            else:
+                fill_scalar = pto.f32(0.0)
         elif pto.constexpr(dst.pad_value != pto.PadValue.NULL):
             fill_scalar = dst.pad_value.eval()
         else:
@@ -137,15 +137,16 @@ def template_tfillpad(src: pto.Tile, dst: pto.Tile):
             fill_scalar = pto.i8(0)
 
     # Phase 1: Copy aligned valid blocks
-    for row in range(0, src_valid_rows, 1):
-        remained = aligned_col
-        for col in range(0, aligned_col, lanes):
-            mask, remained = pto.make_mask(dtype, remained)
-            data = pto.vlds(src[row, col:])
-            pto.vsts(data, dst[row, col:], mask)
+    if aligned_col > 0:
+        for row in range(0, src_valid_rows, 1):
+            remained = aligned_col
+            for col in range(0, aligned_col, lanes):
+                mask, remained = pto.make_mask(dtype, remained)
+                data = pto.vlds(src[row, col:])
+                pto.vsts(data, dst[row, col:], mask)
 
     # Phase 2: Fill cols from aligned_col to dst_cols-1
-    if aligned_col < dst_cols:
+    if aligned_col < dst_cols:
         for row in range(0, src_valid_rows, 1):
             remained = dst_cols - aligned_col
             for col in range(aligned_col, dst_cols, lanes):
@@ -154,7 +155,7 @@ def template_tfillpad(src: pto.Tile, dst: pto.Tile):
                 pto.vsts(vec, dst[row, col:], mask)
 
     # Phase 3: Copy tail valid lanes
-    if has_tail:
+    if has_tail:
         for row in range(0, src_valid_rows, 1):
             remained = src_valid_cols - aligned_col
             mask_copy, remained = pto.make_mask(dtype, remained)
@@ -170,4 +171,4 @@ def template_tfillpad(src: pto.Tile, dst: pto.Tile):
                 vec = pto.vdup(fill_scalar, mask)
                 pto.vsts(vec, dst[row, col:], mask)
 
-    return
+    return