[v2,02/10] Match: Simplify branch form 7 of unsigned SAT_ADD into branchless
Commit Message
From: Pan Li <pan2.li@intel.com>
There are sorts of forms for the unsigned SAT_ADD. Some of them are
complicated while others are cheap. This patch would like to simplify
the complicated form into the cheap ones. For example as below:
From the form 7 (branch):
SAT_U_ADD = x <= (T)(x + y) ? (x + y) : -1.
To (branchless):
SAT_U_ADD = (X + Y) | - ((X + Y) < X).
#define T uint8_t
T sat_add_u_1 (T x, T y)
{
return x <= (T)(x + y) ? (x + y) : -1;
}
Before this patch:
1 │ uint8_t sat_add_u_1 (uint8_t x, uint8_t y)
2 │ {
3 │ uint8_t D.2809;
4 │
5 │ _1 = x + y;
6 │ if (x <= _1) goto <D.2810>; else goto <D.2811>;
7 │ <D.2810>:
8 │ D.2809 = x + y;
9 │ goto <D.2812>;
10 │ <D.2811>:
11 │ D.2809 = 255;
12 │ <D.2812>:
13 │ return D.2809;
14 │ }
After this patch:
1 │ uint8_t sat_add_u_1 (uint8_t x, uint8_t y)
2 │ {
3 │ uint8_t D.2809;
4 │
5 │ _1 = x + y;
6 │ _2 = x + y;
7 │ _3 = x > _2;
8 │ _4 = (unsigned char) _3;
9 │ _5 = -_4;
10 │ D.2809 = _1 | _5;
11 │ return D.2809;
12 │ }
The simplify doesn't need to check if target support the SAT_ADD, it
is somehow the optimization in gimple level.
The below test suites are passed for this patch.
* The rv64gcv fully regression test.
* The x86 bootstrap test.
* The x86 fully regression test.
gcc/ChangeLog:
* match.pd: Remove unsigned branch form 7 for SAT_ADD, and
add simplify to branchless instead.
gcc/testsuite/ChangeLog:
* gcc.dg/sat_arith_simplify.h: Add test helper macros.
* gcc.dg/sat_u_add-simplify-3-u16.c: New test.
* gcc.dg/sat_u_add-simplify-3-u32.c: New test.
* gcc.dg/sat_u_add-simplify-3-u64.c: New test.
* gcc.dg/sat_u_add-simplify-3-u8.c: New test.
Signed-off-by: Pan Li <pan2.li@intel.com>
---
gcc/match.pd | 9 ++++-----
gcc/testsuite/gcc.dg/sat_arith_simplify.h | 6 ++++++
gcc/testsuite/gcc.dg/sat_u_add-simplify-3-u16.c | 11 +++++++++++
gcc/testsuite/gcc.dg/sat_u_add-simplify-3-u32.c | 11 +++++++++++
gcc/testsuite/gcc.dg/sat_u_add-simplify-3-u64.c | 11 +++++++++++
gcc/testsuite/gcc.dg/sat_u_add-simplify-3-u8.c | 11 +++++++++++
6 files changed, 54 insertions(+), 5 deletions(-)
create mode 100644 gcc/testsuite/gcc.dg/sat_u_add-simplify-3-u16.c
create mode 100644 gcc/testsuite/gcc.dg/sat_u_add-simplify-3-u32.c
create mode 100644 gcc/testsuite/gcc.dg/sat_u_add-simplify-3-u64.c
create mode 100644 gcc/testsuite/gcc.dg/sat_u_add-simplify-3-u8.c
@@ -3153,6 +3153,10 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(simplify (cond (ge (plus:c@2 @0 @1) @0) @2 integer_minus_onep)
(if (types_match (type, @0, @1))
(bit_ior (plus@2 @0 @1) (negate (convert (lt @2 @0))))))
+ /* From SAT_ADD = x <= (X + Y) ? (X + Y) : -1. */
+ (simplify (cond (le @0 (plus:c@2 @0 @1)) @2 integer_minus_onep)
+ (if (types_match (type, @0, @1))
+ (bit_ior (plus@2 @0 @1) (negate (convert (lt @2 @0))))))
/* From SAT_U_ADD = (X + Y) < x ? -1 : (X + Y). */
(simplify (cond (lt (plus:c@2 @0 @1) @0) integer_minus_onep @2)
(if (types_match (type, @0, @1))
@@ -3170,11 +3174,6 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(cond^ (ne (imagpart (IFN_ADD_OVERFLOW:c @0 @1)) integer_zerop)
integer_minus_onep (usadd_left_part_2 @0 @1)))
-/* Unsigned saturation add, case 7 (branch with le):
- SAT_ADD = x <= (X + Y) ? (X + Y) : -1. */
-(match (unsigned_integer_sat_add @0 @1)
- (cond^ (le @0 (usadd_left_part_1@2 @0 @1)) @2 integer_minus_onep))
-
/* Unsigned saturation add, case 8 (branch with gt):
SAT_ADD = x > (X + Y) ? -1 : (X + Y). */
(match (unsigned_integer_sat_add @0 @1)
@@ -7,4 +7,10 @@ T sat_u_add_##T##_2 (T x, T y) \
return (T)(x + y) < x ? -1 : (x + y); \
}
+#define DEF_SAT_U_ADD_3(T) \
+T sat_u_add_##T##_3 (T x, T y) \
+{ \
+ return x <= (T)(x + y) ? (x + y) : -1; \
+}
+
#endif
new file mode 100644
@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-gimple-details" } */
+
+#include <stdint.h>
+#include "sat_arith_simplify.h"
+
+DEF_SAT_U_ADD_3 (uint16_t)
+
+/* { dg-final { scan-tree-dump-not " if " "gimple" } } */
+/* { dg-final { scan-tree-dump-not " else " "gimple" } } */
+/* { dg-final { scan-tree-dump-not " goto " "gimple" } } */
new file mode 100644
@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-gimple-details" } */
+
+#include <stdint.h>
+#include "sat_arith_simplify.h"
+
+DEF_SAT_U_ADD_3 (uint32_t)
+
+/* { dg-final { scan-tree-dump-not " if " "gimple" } } */
+/* { dg-final { scan-tree-dump-not " else " "gimple" } } */
+/* { dg-final { scan-tree-dump-not " goto " "gimple" } } */
new file mode 100644
@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-gimple-details" } */
+
+#include <stdint.h>
+#include "sat_arith_simplify.h"
+
+DEF_SAT_U_ADD_3 (uint64_t)
+
+/* { dg-final { scan-tree-dump-not " if " "gimple" } } */
+/* { dg-final { scan-tree-dump-not " else " "gimple" } } */
+/* { dg-final { scan-tree-dump-not " goto " "gimple" } } */
new file mode 100644
@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-gimple-details" } */
+
+#include <stdint.h>
+#include "sat_arith_simplify.h"
+
+DEF_SAT_U_ADD_3 (uint8_t)
+
+/* { dg-final { scan-tree-dump-not " if " "gimple" } } */
+/* { dg-final { scan-tree-dump-not " else " "gimple" } } */
+/* { dg-final { scan-tree-dump-not " goto " "gimple" } } */