Composite GEMM: K-loop accumulator residency, pinned operands, sweep + deck

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/kernbench/triton_emu/tl_context.py

@@ -123,13 +123,14 @@ class TLContext:
 
     def _make_handle(
         self, addr: int, shape: tuple[int, ...], dtype: str,
-        space: str = "tcm",
+        space: str = "tcm", pinned: bool = False,
     ) -> TensorHandle:
         return TensorHandle(
             id=self._next_handle_id(),
             addr=addr, shape=shape, dtype=dtype,
             nbytes=self._nbytes(shape, dtype),
             space=space,
+            pinned=pinned,
         )
 
     def _make_compute_out(
@@ -184,15 +185,17 @@ class TLContext:
         actually lives in Phase 2 storage.
         """
         self._emit_dispatch_overhead()
-        handle = self._make_handle(addr=ptr, shape=shape, dtype=dtype, space="hbm")
+        handle = self._make_handle(
+            addr=ptr, shape=shape, dtype=dtype, space="hbm", pinned=True,
+        )
         cmd = DmaReadCmd(handle=handle, src_addr=ptr, nbytes=handle.nbytes)
         data = self._emit(cmd)
         if data is not None:
-            # Greenlet mode: attach real data to handle (preserve space)
+            # Greenlet mode: attach real data to handle (preserve space + pinned)
             return TensorHandle(
                 id=handle.id, addr=handle.addr, shape=handle.shape,
                 dtype=handle.dtype, nbytes=handle.nbytes, data=data,
-                space=handle.space,
+                space=handle.space, pinned=handle.pinned,
             )
         return handle