From: Ju-Zhe Zhong <juzhe.zh...@rivai.ai>
Hi, previous I made a mistake on GIMPLE_FOLD of LEN_MASK_{LOAD,STORE}.
We should fold LEN_MASK_{LOAD,STORE} (bias+len) == vf (nunits instead of
bytesize) && mask = all trues mask
into:
MEM_REF [...].
This patch added testcase to test gimple fold of LEN_MASK_{LOAD,STORE}.
Also, I fix LEN_LOAD/LEN_STORE, to make them have the same behavior.
Ok for trunk ?
gcc/ChangeLog:
* gimple-fold.cc (gimple_fold_partial_load_store_mem_ref): Fix gimple
fold of LOAD/STORE with length.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/autovec/partial/gimple_fold-1.c: New test.
---
gcc/gimple-fold.cc | 6 ++-
.../riscv/rvv/autovec/partial/gimple_fold-1.c | 43 +++++++++++++++++++
2 files changed, 47 insertions(+), 2 deletions(-)
create mode 100644
gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/gimple_fold-1.c
diff --git a/gcc/gimple-fold.cc b/gcc/gimple-fold.cc
index 3d46b76edeb..6d167b116b9 100644
--- a/gcc/gimple-fold.cc
+++ b/gcc/gimple-fold.cc
@@ -5397,8 +5397,10 @@ gimple_fold_partial_load_store_mem_ref (gcall *call,
tree vectype, bool mask_p)
unsigned int nargs = gimple_call_num_args (call);
tree bias = gimple_call_arg (call, nargs - 1);
gcc_assert (TREE_CODE (bias) == INTEGER_CST);
- if (maybe_ne (wi::to_poly_widest (basic_len) - wi::to_widest (bias),
- GET_MODE_SIZE (TYPE_MODE (vectype))))
+ /* For LEN_LOAD/LEN_STORE/LEN_MASK_LOAD/LEN_MASK_STORE,
+ we don't fold when (bias + len) != VF. */
+ if (maybe_ne (wi::to_poly_widest (basic_len) + wi::to_widest (bias),
+ GET_MODE_NUNITS (TYPE_MODE (vectype))))
return NULL_TREE;
/* For LEN_MASK_{LOAD,STORE}, we should also check whether
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/gimple_fold-1.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/gimple_fold-1.c
new file mode 100644
index 00000000000..23407a2d3f4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/gimple_fold-1.c
@@ -0,0 +1,43 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gcv -mabi=ilp32d --param
riscv-autovec-preference=fixed-vlmax --param riscv-autovec-lmul=m8 -O3
-fdump-tree-optimized-details" } */
+
+#include <stdint-gcc.h>
+
+#define SZ 255
+
+#define DEF(TYPE) void fn_##TYPE (TYPE *__restrict a);
+
+#define RUN(TYPE)
\
+ TYPE a##TYPE[SZ];
\
+ for (int i = 0; i < SZ; i++)
\
+ {
\
+ a##TYPE[i] = 127;
\
+ }
\
+ fn_##TYPE (a##TYPE);
+
+#define RUN_ALL()
\
+ RUN (int8_t)
\
+ RUN (int16_t)
\
+ RUN (int32_t)
\
+ RUN (int64_t)
\
+ RUN (uint8_t)
\
+ RUN (uint16_t)
\
+ RUN (uint32_t)
\
+ RUN (uint64_t)
+
+DEF (int8_t)
+DEF (int16_t)
+DEF (int32_t)
+DEF (int64_t)
+DEF (uint8_t)
+DEF (uint16_t)
+DEF (uint32_t)
+DEF (uint64_t)
+
+int
+main ()
+{
+ RUN_ALL ()
+}
+
+/* { dg-final { scan-tree-dump-times "\.LEN_MASK_STORE" 6 "optimized" } } */
--
2.36.3
