This is a rework of
https://gcc.gnu.org/ml/gcc-patches/2014-07/msg01998.html
After second thinking, I feel it's better to fix this in earlier stage
during RTL expand which is more generic, and we also avoid making the
already complex combine pass complexer.
Currently gcc expand wide mode left shift to some generic complex
instruction sequences, while if we have known the high part of wide mode
all comes from sign extension, the expand logic could be simplifed.
Given the following example,
T A = (T) B << const_imm_shift
We know the high part of A are all comes from sign extension, if
* T is the next wider type of word_mode.
For example, for aarch64, if type T is 128int (TImode), and B is with
type SImode or DImode, then tree analyzer know that the high part of
TImode result all comes from sign extension, and kept them in range info.
|< T >|
| high | low |
|<- sizel ->|
For above example, we could simplify the expand logic into
1. low = low << const_imm_shift;
2. high = low >> (sizel - const_imm_shift) */
We can utilize the arithmetic right shift to do the sign
extension. Those reduntant instructions will be optimized out later.
For actual .s improvement,
AArch64
=======
__int128_t
foo (int data)
{
return (__int128_t) data << 50;
}
old:
sxtw x2, w0
asr x1, x2, 63
lsl x0, x2, 50
lsl x1, x1, 50
orr x1, x1, x2, lsr 14
new:
sxtw x1, w0
lsl x0, x1, 50
asr x1, x1, 14
ARM (.fpu softvfp)
===========
long long
shift (int data)
{
return (long long) data << 20;
}
old:
stmfd sp!, {r4, r5}
mov r5, r0, asr #31
mov r3, r0
mov r0, r0, asl #20
mov r1, r5, asl #20
orr r1, r1, r3, lsr #12
ldmfd sp!, {r4, r5}
bx lr
new:
mov r1, r0
mov r0, r0, asl #20
mov r1, r1, asr #12
bx lr
Test
====
x86 bootstrap OK, regression test OK.
AArch64 bootstrap OK, regression test on board OK.
Regards,
Jiong
2015-04-116 Jiong.Wang <jiong.w...@arm.com>
gcc/
* expr.c (expand_expr_real_2): Take tree range info into account when
expanding LSHIFT_EXPR.
gcc/testsuite
* gcc.dg/wide_shift_64_1.c: New testcase.
* gcc.dg/wide_shift_128_1.c: Ditto.
* gcc.target/aarch64/ashlti3_1.c: Ditto.
* gcc.target/arm/ashldisi_1.c: Ditto.
diff --git a/gcc/expr.c b/gcc/expr.c
index 89ca129..96d64cc 100644
--- a/gcc/expr.c
+++ b/gcc/expr.c
@@ -8984,23 +8984,85 @@ expand_expr_real_2 (sepops ops, rtx target, machine_mode tmode,
case LSHIFT_EXPR:
case RSHIFT_EXPR:
- /* If this is a fixed-point operation, then we cannot use the code
- below because "expand_shift" doesn't support sat/no-sat fixed-point
- shifts. */
- if (ALL_FIXED_POINT_MODE_P (mode))
- goto binop;
-
- if (! safe_from_p (subtarget, treeop1, 1))
- subtarget = 0;
- if (modifier == EXPAND_STACK_PARM)
- target = 0;
- op0 = expand_expr (treeop0, subtarget,
- VOIDmode, EXPAND_NORMAL);
- temp = expand_variable_shift (code, mode, op0, treeop1, target,
- unsignedp);
- if (code == LSHIFT_EXPR)
- temp = REDUCE_BIT_FIELD (temp);
- return temp;
+ {
+ /* If this is a fixed-point operation, then we cannot use the code
+ below because "expand_shift" doesn't support sat/no-sat fixed-point
+ shifts. */
+ if (ALL_FIXED_POINT_MODE_P (mode))
+ goto binop;
+
+ if (! safe_from_p (subtarget, treeop1, 1))
+ subtarget = 0;
+ if (modifier == EXPAND_STACK_PARM)
+ target = 0;
+
+ op0 = expand_expr (treeop0, subtarget,
+ VOIDmode, EXPAND_NORMAL);
+
+ /* If mode == GET_MODE_WIDER_MODE (word_mode),
+ then normally, there will no native instructions to support
+ this wide mode left shift.
+
+ given below example,
+
+ T A = (T) B << C
+
+ |< T >|
+ | high | low |
+
+ |<- sizel ->|
+
+ if from range info, we could deduce that the high part are all sign
+ bit extension, then this left shift operation could be largely
+ simplified into.
+
+ 1. low = low << C;
+ 2. high = low >> (sizel - C) */
+
+ int o_bits = GET_MODE_SIZE (mode) * BITS_PER_UNIT;
+ wide_int min, max;
+
+ if (code == LSHIFT_EXPR
+ && !unsignedp
+ && mode == GET_MODE_WIDER_MODE (word_mode)
+ && !have_insn_for (LSHIFT_EXPR, mode)
+ && TREE_CONSTANT (treeop1)
+ && get_range_info (treeop0, &min, &max) == VR_RANGE
+ && (wi::cmp (min,
+ wide_int::from (wi::min_value
+ ((unsigned) (BITS_PER_WORD),
+ SIGNED), o_bits, SIGNED),
+ SIGNED) != -1)
+ && (wi::cmp (max,
+ wide_int::from (wi::max_value
+ ((unsigned)(BITS_PER_WORD),
+ SIGNED), o_bits, SIGNED),
+ SIGNED) != 1))
+ {
+ rtx low = simplify_gen_subreg (word_mode, op0, mode, 0);
+ rtx t_low = simplify_gen_subreg (word_mode, target, mode, 0);
+ rtx t_high = simplify_gen_subreg (word_mode, target, mode,
+ UNITS_PER_WORD);
+ tree high_shift =
+ build_int_cst (TREE_TYPE (treeop1),
+ BITS_PER_WORD -TREE_INT_CST_LOW (treeop1));
+
+ temp = expand_variable_shift (code, word_mode, low, treeop1,
+ t_low, unsignedp);
+
+ temp = expand_variable_shift (RSHIFT_EXPR, word_mode, low,
+ high_shift, t_high, unsignedp);
+
+ gcc_assert (GET_CODE (temp) == SUBREG);
+ temp = XEXP (temp, 0);
+ }
+ else
+ temp = expand_variable_shift (code, mode, op0, treeop1, target,
+ unsignedp);
+ if (code == LSHIFT_EXPR)
+ temp = REDUCE_BIT_FIELD (temp);
+ return temp;
+ }
/* Could determine the answer when only additive constants differ. Also,
the addition of one can be handled by changing the condition. */
diff --git a/gcc/testsuite/gcc.dg/wide-shift-128.c b/gcc/testsuite/gcc.dg/wide-shift-128.c
new file mode 100644
index 0000000..9b62715
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/wide-shift-128.c
@@ -0,0 +1,12 @@
+/* { dg-do compile { target aarch64*-*-* mips64*-*-* sparc64*-*-* } } */
+/* { dg-require-effective-target int128 } */
+/* { dg-options "-O2 -fdump-rtl-combine" } */
+
+__int128_t
+load2 (int data)
+{
+ return (__int128_t) data << 50;
+}
+
+/* { dg-final { scan-rtl-dump-not "ior" "combine" } } */
+/* { dg-final { cleanup-rtl-dump "combine" } } */
diff --git a/gcc/testsuite/gcc.dg/wide-shift-64.c b/gcc/testsuite/gcc.dg/wide-shift-64.c
new file mode 100644
index 0000000..5bc278f
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/wide-shift-64.c
@@ -0,0 +1,11 @@
+/* { dg-do compile { target arm*-*-* mips*-*-* sparc*-*-* } } */
+/* { dg-options "-O2 -fdump-rtl-combine" } */
+
+long long
+load1 (int data)
+{
+ return (long long) data << 12;
+}
+
+/* { dg-final { scan-rtl-dump-not "ior" "combine" } } */
+/* { dg-final { cleanup-rtl-dump "combine" } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/ashltidisi.c b/gcc/testsuite/gcc.target/aarch64/ashltidisi.c
new file mode 100644
index 0000000..aeb2a24
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/ashltidisi.c
@@ -0,0 +1,49 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -save-temps" } */
+
+extern void abort (void);
+
+#define GEN_TEST_CASE(x, y, z)\
+__uint128_t __attribute__ ((noinline))\
+ushift_##x##_##z (unsigned y data)\
+{\
+ return (__uint128_t) data << x;\
+}\
+__int128_t __attribute__ ((noinline)) \
+shift_##x##_##z (y data) \
+{\
+ return (__int128_t) data << x;\
+}
+
+GEN_TEST_CASE (53, int, i)
+GEN_TEST_CASE (3, long long, ll)
+GEN_TEST_CASE (13, long long, ll)
+GEN_TEST_CASE (53, long long, ll)
+
+int
+main (int argc, char **argv)
+{
+
+#define SHIFT_CHECK(x, y, z, p) \
+ if (ushift_##y##_##p (x)\
+ != ((__uint128_t) (unsigned z) x << y)) \
+ abort ();\
+ if (shift_##y##_##p (x)\
+ != ((__uint128_t) (signed z) x << y)) \
+ abort ();
+
+ SHIFT_CHECK (0x12345678, 53, int, i)
+ SHIFT_CHECK (0xcafecafe, 53, int, i)
+
+ SHIFT_CHECK (0x1234567890abcdefLL, 3, long long, ll)
+ SHIFT_CHECK (0x1234567890abcdefLL, 13, long long, ll)
+ SHIFT_CHECK (0x1234567890abcdefLL, 53, long long, ll)
+ SHIFT_CHECK (0xcafecafedeaddeadLL, 3, long long, ll)
+ SHIFT_CHECK (0xcafecafedeaddeadLL, 13, long long, ll)
+ SHIFT_CHECK (0xcafecafedeaddeadLL, 53, long long, ll)
+
+ return 0;
+}
+
+/* { dg-final { scan-assembler-times "asr" 4 } } */
+/* { dg-final { cleanup-saved-temps } } */
diff --git a/gcc/testsuite/gcc.target/arm/ashldisi.c b/gcc/testsuite/gcc.target/arm/ashldisi.c
new file mode 100644
index 0000000..00dc06e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/ashldisi.c
@@ -0,0 +1,44 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -save-temps" } */
+
+extern void abort (void);
+
+#define GEN_TEST_CASE(x)\
+unsigned long long __attribute__ ((noinline))\
+ushift_ ## x (unsigned int data)\
+{\
+ return (unsigned long long) data << x;\
+}\
+long long __attribute__ ((noinline)) \
+shift_ ## x (int data) \
+{\
+ return (long long) data << x;\
+}
+
+GEN_TEST_CASE (3)
+GEN_TEST_CASE (23)
+GEN_TEST_CASE (30)
+int
+main (int argc, char **argv)
+{
+
+#define SHIFT_CHECK(x, y) \
+ if (ushift_ ## y (x)\
+ != ((unsigned long long) (unsigned) x << y)) \
+ abort (); \
+ if (shift_ ## y (x)\
+ != ((long long) (signed) x << y)) \
+ abort ();
+
+ SHIFT_CHECK (0x12345678, 3)
+ SHIFT_CHECK (0xcafecafe, 3)
+ SHIFT_CHECK (0x12345678, 23)
+ SHIFT_CHECK (0xcafecafe, 23)
+ SHIFT_CHECK (0x12345678, 30)
+ SHIFT_CHECK (0xcafecafe, 30)
+
+ return 0;
+}
+
+/* { dg-final { scan-assembler-times "asr" 3 } } */
+/* { dg-final { cleanup-saved-temps } } */
