https://gcc.gnu.org/g:ae88da5e070659d37b3c3daa4b880531769183bf
commit r15-4133-gae88da5e070659d37b3c3daa4b880531769183bf
Author: Prathamesh Kulkarni <prathame...@nvidia.com>
Date: Tue Oct 8 12:38:31 2024 +0530
Recompute TYPE_MODE and DECL_MODE for vector_type for accelerator.
gcc/ChangeLog:
PR ipa/96265
* lto-streamer-in.cc (lto_read_tree_1): Set TYPE_MODE and DECL_MODE
for vector_type if offloading is enabled.
(lto_input_mode_table): Remove handling of vector modes.
* tree-streamer-out.cc (pack_ts_decl_common_value_fields): Stream
out
VOIDmode for vector_type if offloading is enabled.
(pack_ts_decl_common_value_fields): Likewise.
Signed-off-by: Prathamesh Kulkarni <prathame...@nvidia.com>
Diff:
---
gcc/lto-streamer-in.cc | 38 ++++++++++++++++++++++++--------------
gcc/tree-streamer-out.cc | 6 ++++--
2 files changed, 28 insertions(+), 16 deletions(-)
diff --git a/gcc/lto-streamer-in.cc b/gcc/lto-streamer-in.cc
index 9d0ec5d589c4..15181c3f5746 100644
--- a/gcc/lto-streamer-in.cc
+++ b/gcc/lto-streamer-in.cc
@@ -1753,16 +1753,30 @@ lto_read_tree_1 (class lto_input_block *ib, class
data_in *data_in, tree expr)
with -g1, see for example PR113488. */
else if (DECL_P (expr) && DECL_ABSTRACT_ORIGIN (expr) == expr)
DECL_ABSTRACT_ORIGIN (expr) = NULL_TREE;
+ }
#ifdef ACCEL_COMPILER
- if ((VAR_P (expr)
- || TREE_CODE (expr) == PARM_DECL
- || TREE_CODE (expr) == FIELD_DECL)
- && AGGREGATE_TYPE_P (TREE_TYPE (expr))
- && DECL_MODE (expr) == VOIDmode)
- SET_DECL_MODE (expr, TYPE_MODE (TREE_TYPE (expr)));
-#endif
+ if ((VAR_P (expr)
+ || TREE_CODE (expr) == PARM_DECL
+ || TREE_CODE (expr) == FIELD_DECL)
+ && DECL_MODE (expr) == VOIDmode)
+ {
+ tree type = TREE_TYPE (expr);
+ if (AGGREGATE_TYPE_P (type))
+ SET_DECL_MODE (expr, TYPE_MODE (type));
+ else if (VECTOR_TYPE_P (type))
+ SET_DECL_MODE (expr, TYPE_MODE_RAW (type));
}
+
+ if (VECTOR_TYPE_P (expr) && TYPE_MODE (expr) == VOIDmode)
+ {
+ poly_uint64 nunits = TYPE_VECTOR_SUBPARTS (expr);
+ tree innertype = TREE_TYPE (expr);
+ machine_mode vmode
+ = mode_for_vector (SCALAR_TYPE_MODE (innertype), nunits).else_blk ();
+ SET_TYPE_MODE (expr, vmode);
+ }
+#endif
}
/* Read the physical representation of a tree node with tag TAG from
@@ -2106,13 +2120,9 @@ lto_input_mode_table (struct lto_file_decl_data
*file_data)
case MODE_VECTOR_UFRACT:
case MODE_VECTOR_ACCUM:
case MODE_VECTOR_UACCUM:
- /* For unsupported vector modes just use BLKmode,
- if the scalar mode is supported. */
- if (table[(int) inner] != VOIDmode)
- {
- table[m] = BLKmode;
- break;
- }
+ /* Vector modes are recomputed on accel side and shouldn't have
+ been streamed-out from host. */
+ gcc_unreachable ();
/* FALLTHRU */
default:
/* This is only used for offloading-target compilations and
diff --git a/gcc/tree-streamer-out.cc b/gcc/tree-streamer-out.cc
index 7de4447a1b53..81f5aeb30a6d 100644
--- a/gcc/tree-streamer-out.cc
+++ b/gcc/tree-streamer-out.cc
@@ -194,7 +194,8 @@ pack_ts_decl_common_value_fields (struct bitpack_d *bp,
tree expr)
&& (VAR_P (expr)
|| TREE_CODE (expr) == PARM_DECL
|| TREE_CODE (expr) == FIELD_DECL)
- && AGGREGATE_TYPE_P (TREE_TYPE (expr)))
+ && (AGGREGATE_TYPE_P (TREE_TYPE (expr))
+ || VECTOR_TYPE_P (TREE_TYPE (expr))))
bp_pack_machine_mode (bp, VOIDmode);
else
bp_pack_machine_mode (bp, DECL_MODE (expr));
@@ -332,7 +333,8 @@ pack_ts_type_common_value_fields (struct bitpack_d *bp,
tree expr)
whose size is 256-bits, which is not representable on accelerator.
Instead stream out VOIDmode, and while streaming-in, recompute
appropriate TYPE_MODE for accelerator. */
- if (lto_stream_offload_p && AGGREGATE_TYPE_P (expr))
+ if (lto_stream_offload_p
+ && (AGGREGATE_TYPE_P (expr) || VECTOR_TYPE_P (expr)))
bp_pack_machine_mode (bp, VOIDmode);
/* for VECTOR_TYPE, TYPE_MODE reevaluates the mode using target_flags
not necessary valid in a global context.
