https://gcc.gnu.org/g:993c6de642ffeb2867edbe80ff2a72c0a2eb604e
commit r14-9418-g993c6de642ffeb2867edbe80ff2a72c0a2eb604e
Author: Pan Li <pan2...@intel.com>
Date: Sun Mar 10 11:02:35 2024 +0800
VECT: Fix ICE for vectorizable LD/ST when both len and store are enabled
This patch would like to fix one ICE in vectorizable_store when both the
loop_masks and loop_lens are enabled. The ICE looks like below when build
with "-march=rv64gcv -O3".
during GIMPLE pass: vect
test.c: In function ‘d’:
test.c:6:6: internal compiler error: in vectorizable_store, at
tree-vect-stmts.cc:8691
6 | void d() {
| ^
0x37a6f2f vectorizable_store
.../__RISC-V_BUILD__/../gcc/tree-vect-stmts.cc:8691
0x37b861c vect_analyze_stmt(vec_info*, _stmt_vec_info*, bool*,
_slp_tree*, _slp_instance*, vec<stmt_info_for_cost, va_heap, vl_ptr>*)
.../__RISC-V_BUILD__/../gcc/tree-vect-stmts.cc:13242
0x1db5dca vect_analyze_loop_operations
.../__RISC-V_BUILD__/../gcc/tree-vect-loop.cc:2208
0x1db885b vect_analyze_loop_2
.../__RISC-V_BUILD__/../gcc/tree-vect-loop.cc:3041
0x1dba029 vect_analyze_loop_1
.../__RISC-V_BUILD__/../gcc/tree-vect-loop.cc:3481
0x1dbabad vect_analyze_loop(loop*, vec_info_shared*)
.../__RISC-V_BUILD__/../gcc/tree-vect-loop.cc:3639
0x1e389d1 try_vectorize_loop_1
.../__RISC-V_BUILD__/../gcc/tree-vectorizer.cc:1066
0x1e38f3d try_vectorize_loop
.../__RISC-V_BUILD__/../gcc/tree-vectorizer.cc:1182
0x1e39230 execute
.../__RISC-V_BUILD__/../gcc/tree-vectorizer.cc:1298
There are two ways to reach vectorizer LD/ST, one is the analysis and
the other is transform. We cannot have both the lens and the masks
enabled during transform but it is valid during analysis. Given the
transform doesn't required cost_vec, we can only enable the assert
based on cost_vec is NULL or not.
Below testsuites are passed for this patch:
* The x86 bootstrap tests.
* The x86 fully regression tests.
* The aarch64 fully regression tests.
* The riscv fully regressison tests.
gcc/ChangeLog:
* tree-vect-stmts.cc (vectorizable_store): Enable the assert
during transform process.
(vectorizable_load): Ditto.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/base/pr114195-1.c: New test.
Signed-off-by: Pan Li <pan2...@intel.com>
Diff:
---
gcc/testsuite/gcc.target/riscv/rvv/base/pr114195-1.c | 15 +++++++++++++++
gcc/tree-vect-stmts.cc | 18 ++++++++++++++----
2 files changed, 29 insertions(+), 4 deletions(-)
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr114195-1.c
b/gcc/testsuite/gcc.target/riscv/rvv/base/pr114195-1.c
new file mode 100644
index 00000000000..a67b847112b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr114195-1.c
@@ -0,0 +1,15 @@
+/* Test that we do not have ice when compile */
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize" } */
+
+long a, b;
+extern short c[];
+
+void d() {
+ for (int e = 0; e < 35; e = 2) {
+ a = ({ a < 0 ? a : 0; });
+ b = ({ b < 0 ? b : 0; });
+
+ c[e] = 0;
+ }
+}
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index 14a3ffb5f02..e8617439a48 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -8697,8 +8697,13 @@ vectorizable_store (vec_info *vinfo,
? &LOOP_VINFO_LENS (loop_vinfo)
: NULL);
- /* Shouldn't go with length-based approach if fully masked. */
- gcc_assert (!loop_lens || !loop_masks);
+ /* The vect_transform_stmt and vect_analyze_stmt will go here but there
+ are some difference here. We cannot enable both the lens and masks
+ during transform but it is allowed during analysis.
+ Shouldn't go with length-based approach if fully masked. */
+ if (cost_vec == NULL)
+ /* The cost_vec is NULL during transfrom. */
+ gcc_assert ((!loop_lens || !loop_masks));
/* Targets with store-lane instructions must not require explicit
realignment. vect_supportable_dr_alignment always returns either
@@ -10577,8 +10582,13 @@ vectorizable_load (vec_info *vinfo,
? &LOOP_VINFO_LENS (loop_vinfo)
: NULL);
- /* Shouldn't go with length-based approach if fully masked. */
- gcc_assert (!loop_lens || !loop_masks);
+ /* The vect_transform_stmt and vect_analyze_stmt will go here but there
+ are some difference here. We cannot enable both the lens and masks
+ during transform but it is allowed during analysis.
+ Shouldn't go with length-based approach if fully masked. */
+ if (cost_vec == NULL)
+ /* The cost_vec is NULL during transfrom. */
+ gcc_assert ((!loop_lens || !loop_masks));
/* Targets with store-lane instructions must not require explicit
realignment. vect_supportable_dr_alignment always returns either
