From: Kyrylo Tkachov <[email protected]>
The PR120378 RISC-V tests use this source form:
(NT) ((UT) x > NT_MAX ? (-x) >> (PREC - 1) : x)
For every defined execution, it is an unsigned saturating truncation of
MAX (x, 0). The signed negation is undefined at the signed minimum under
the default overflow rules.
Loop if-conversion changes the selected negation to unsigned arithmetic.
This loses the distinction between the signed source and the explicit
unsigned-negation form from PR126981, which must not become a saturating
truncation.
Canonicalize the signed form while its overflow semantics are still
available before loop if-conversion:
(NT) MIN ((UT) MAX (x, 0), NT_MAX)
Require an unsigned comparison, a signed right shift, undefined and
unsanitized negation overflow, exact constants, and no side effects. This
keeps the original form with -fwrapv, -ftrapv, sanitization, volatile
operands, and explicit unsigned negation.
With this patch the tests restore the RISC-V saturation patterns.
Update pr103771.c because the direct form is
canonicalized before phiopt.
Bootstrapped and tested on aarch64-none-linux-gnu.
Ok for trunk?
Thanks,
Kyrill
gcc/ChangeLog:
PR tree-optimization/127166
* match.pd: Canonicalize conditional signed narrow clips before loop
if-conversion.
gcc/testsuite/ChangeLog:
PR tree-optimization/127166
* gcc.dg/tree-ssa/pr103771.c: Check the earlier canonicalization.
* gcc.dg/tree-ssa/pr127166.c: New test.
* gcc.dg/tree-ssa/pr127166-3.c: New test.
* gcc.dg/vect/pr127166.c: New test.
* gcc.target/riscv/rvv/autovec/pr120378-1.c: Update expected dump
counts.
* gcc.target/riscv/rvv/autovec/pr120378-2.c: Request an optimized dump.
* gcc.target/riscv/rvv/autovec/pr120378-3.c: Likewise. Update expected
dump counts.
* gcc.target/riscv/rvv/autovec/pr120378-4.c: Request an optimized dump.
Signed-off-by: Kyrylo Tkachov <[email protected]>
---
gcc/match.pd | 37 +++++++++++++
gcc/testsuite/gcc.dg/tree-ssa/pr103771.c | 5 +-
gcc/testsuite/gcc.dg/tree-ssa/pr127166-3.c | 15 ++++++
gcc/testsuite/gcc.dg/tree-ssa/pr127166.c | 53 +++++++++++++++++++
gcc/testsuite/gcc.dg/vect/pr127166.c | 50 +++++++++++++++++
.../gcc.target/riscv/rvv/autovec/pr120378-1.c | 4 +-
.../gcc.target/riscv/rvv/autovec/pr120378-2.c | 2 +-
.../gcc.target/riscv/rvv/autovec/pr120378-3.c | 6 +--
.../gcc.target/riscv/rvv/autovec/pr120378-4.c | 2 +-
9 files changed, 165 insertions(+), 9 deletions(-)
create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr127166-3.c
create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr127166.c
create mode 100644 gcc/testsuite/gcc.dg/vect/pr127166.c
diff --git a/gcc/match.pd b/gcc/match.pd
index 5777c833896..54cad1cd2bc 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -13372,6 +13372,43 @@ and,
(BUILT_IN_CONSTANT_P (nop_convert@1 @0))
(BUILT_IN_CONSTANT_P @0))
+/* Canonicalize a conditional signed narrow clip while the signed negation
+ has its original overflow semantics:
+
+ (NT) ((UT) X > NT_MAX ? (-X) >> (PREC - 1) : X)
+ -> (NT) MIN ((UT) MAX (X, 0), NT_MAX). */
+(if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type))
+ (simplify
+ (cond (gt (nop_convert@4 @0) INTEGER_CST@1)
+ (convert (rshift@5
+ (nop_convert? (negate@3 (nop_convert? @0)))
+ INTEGER_CST@2))
+ (convert @0))
+ (if (!TREE_SIDE_EFFECTS (@0)
+ && !TYPE_UNSIGNED (TREE_TYPE (@0))
+ && TYPE_UNSIGNED (TREE_TYPE (@4))
+ && !TYPE_UNSIGNED (TREE_TYPE (@5))
+ && TYPE_OVERFLOW_UNDEFINED (TREE_TYPE (@3))
+ && !TYPE_OVERFLOW_SANITIZED (TREE_TYPE (@3)))
+ (with
+ {
+ tree utype = TREE_TYPE (@4);
+ unsigned itype_precision = TYPE_PRECISION (TREE_TYPE (@0));
+ unsigned otype_precision = TYPE_PRECISION (type);
+ wide_int trunc_max = wi::mask (otype_precision, false, itype_precision);
+ wide_int int_cst_1 = wi::to_wide (@1, itype_precision);
+ wide_int int_cst_2 = wi::to_wide (@2, itype_precision);
+ wide_int shift_amount = wi::uhwi (itype_precision - 1,
+ itype_precision);
+ }
+ (if (otype_precision < itype_precision
+ && wi::eq_p (trunc_max, int_cst_1)
+ && wi::eq_p (int_cst_2, shift_amount))
+ (convert (min:utype
+ (convert:utype
+ (max @0 { build_zero_cst (TREE_TYPE (@0)); }))
+ @1)))))))
+
#if GIMPLE
/* Include the saturation alu match patterns. */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr103771.c
b/gcc/testsuite/gcc.dg/tree-ssa/pr103771.c
index 8061e2df79e..b3dde923281 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr103771.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr103771.c
@@ -1,6 +1,7 @@
/* { dg-do compile } */
-/* { dg-options "-O3 -fdump-tree-phiopt1-details" } */
-/* { dg-final { scan-tree-dump-times "changed to factor operation out from
COND_EXPR." 1 "phiopt1" } } */
+/* { dg-options "-O3 -fdump-tree-gimple" } */
+/* { dg-final { scan-tree-dump-times "MAX_EXPR" 1 "gimple" } } */
+/* { dg-final { scan-tree-dump-times "MIN_EXPR" 1 "gimple" } } */
typedef unsigned char uint8_t;
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr127166-3.c
b/gcc/testsuite/gcc.dg/tree-ssa/pr127166-3.c
new file mode 100644
index 00000000000..266b0aac75a
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr127166-3.c
@@ -0,0 +1,15 @@
+/* PR tree-optimization/127166 */
+/* { dg-do compile } */
+/* { dg-require-effective-target int32 } */
+/* { dg-options "-O2 -fsanitize=signed-integer-overflow" } */
+/* { dg-additional-options "-fdump-tree-optimized" } */
+
+unsigned short
+f (int x)
+{
+ return ((unsigned int) x > 65535u ? (-x) >> 31 : x);
+}
+
+/* Keep the conditional signed negation so that it is checked at runtime. */
+/* { dg-final { scan-tree-dump-not "MAX_EXPR|MIN_EXPR" "optimized" } } */
+/* { dg-final { scan-tree-dump {\.UBSAN_CHECK_SUB} "optimized" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr127166.c
b/gcc/testsuite/gcc.dg/tree-ssa/pr127166.c
new file mode 100644
index 00000000000..9bf89246dba
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr127166.c
@@ -0,0 +1,53 @@
+/* PR tree-optimization/127166 */
+/* { dg-do compile } */
+/* { dg-require-effective-target int32 } */
+/* { dg-options "-O2 -fdump-tree-gimple -fdump-tree-phiopt2" } */
+
+unsigned short
+signed_clip (int x)
+{
+ return ((unsigned int) x > 65535u ? (-x) >> 31 : x);
+}
+
+unsigned short
+unsigned_clip (int x)
+{
+ return ((unsigned int) x > 65535u
+ ? (int) (-(unsigned int) x) >> 31 : x);
+}
+
+unsigned short
+signed_split_clip (int x)
+{
+ int neg = -x;
+ int sign = neg >> 31;
+ unsigned short high = sign;
+
+ return ((unsigned int) x > 65535u ? high : x);
+}
+
+unsigned short
+unsigned_split_clip (int x)
+{
+ unsigned int ux = x;
+ unsigned int neg = -ux;
+ int sign = (int) neg >> 31;
+ unsigned short high = sign;
+
+ return (ux > 65535u ? high : x);
+}
+
+volatile int v;
+
+unsigned short
+volatile_clip (void)
+{
+ return ((unsigned int) v > 65535u ? (-v) >> 31 : v);
+}
+
+/* The direct signed form is canonicalized in GENERIC. The split signed form
+ is canonicalized in GIMPLE before loop if-conversion. */
+/* { dg-final { scan-tree-dump-times "MAX_EXPR" 1 "gimple" } } */
+/* { dg-final { scan-tree-dump-times "MIN_EXPR" 1 "gimple" } } */
+/* { dg-final { scan-tree-dump-times "MAX_EXPR" 2 "phiopt2" } } */
+/* { dg-final { scan-tree-dump-times "MIN_EXPR" 2 "phiopt2" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/pr127166.c
b/gcc/testsuite/gcc.dg/vect/pr127166.c
new file mode 100644
index 00000000000..5bc59ad3769
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr127166.c
@@ -0,0 +1,50 @@
+/* PR tree-optimization/127166 */
+/* { dg-additional-options "-fwrapv" } */
+/* { dg-require-effective-target int32 } */
+/* { dg-require-effective-target vect_int } */
+
+#include "tree-vect.h"
+
+#define N 64
+
+__attribute__ ((noipa)) void
+clip (unsigned short *__restrict out, const int *__restrict in, int n)
+{
+ for (int i = 0; i < n; ++i)
+ {
+ int x = in[i];
+ out[i] = ((unsigned int) x > 65535u ? (-x) >> 31 : x);
+ }
+}
+
+int
+main (void)
+{
+ int in[N];
+ unsigned short out[N];
+
+ check_vect ();
+
+ for (int i = 0; i < N; ++i)
+ in[i] = (i & 3) == 0 ? (-__INT_MAX__ - 1) : i * 12345 - 30000;
+
+ clip (out, in, N);
+
+#pragma GCC novector
+ for (int i = 0; i < N; ++i)
+ {
+ int x = in[i];
+ unsigned short ref;
+
+ if (x == (-__INT_MAX__ - 1) || x > 65535)
+ ref = 65535;
+ else if (x < 0)
+ ref = 0;
+ else
+ ref = x;
+ if (out[i] != ref)
+ abort ();
+ }
+
+ return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr120378-1.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr120378-1.c
index 54f25e0ceaa..f5a9acec858 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr120378-1.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr120378-1.c
@@ -16,6 +16,6 @@ clip_loop (uint8_t *res, int *x, int w)
res[i] = clip_uint8 (x[i]);
}
-/* { dg-final { scan-tree-dump-times ".SAT_TRUNC " 1 "optimized" } } */
-/* { dg-final { scan-tree-dump-times "MAX_EXPR " 1 "optimized" } } */
+/* { dg-final { scan-tree-dump-times ".SAT_TRUNC " 2 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "MAX_EXPR " 2 "optimized" } } */
/* { dg-final { scan-assembler-times {vnclipu\.wi} 2 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr120378-2.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr120378-2.c
index 9a880e0f67b..2208e954242 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr120378-2.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr120378-2.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -fdump-tree-optimized" } */
#include <stdint.h>
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr120378-3.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr120378-3.c
index d6b2ddd3f8d..5941b3b7543 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr120378-3.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr120378-3.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -fdump-tree-optimized" } */
#include <stdint.h>
@@ -16,6 +16,6 @@ clip_loop (uint8_t *res, int64_t *x, int w)
res[i] = clip_uint8 (x[i]);
}
-/* { dg-final { scan-tree-dump-times ".SAT_TRUNC " 1 "optimized" } } */
-/* { dg-final { scan-tree-dump-times "MAX_EXPR " 1 "optimized" } } */
+/* { dg-final { scan-tree-dump-times ".SAT_TRUNC " 2 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "MAX_EXPR " 2 "optimized" } } */
/* { dg-final { scan-assembler-times {vnclipu\.wi} 3 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr120378-4.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr120378-4.c
index 4657e52f883..57cca4504ba 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr120378-4.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr120378-4.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -fdump-tree-optimized" } */
#include <stdint.h>
--
2.50.1 (Apple Git-155)
