aarch64_add_offset contains code to decompose all SVE VL-based constants
into native operations. The worst-case fallback is to load the number
of SVE elements into a register and use a general multiplication.
This patch improves that fallback by reusing expand_mult if
can_create_pseudo_p, rather than emitting a MULT pattern directly.
In order to increase the chances of being able to use a simple
add-and-shift, the patch also tries to compute VG * the lowest set
bit of the multiplier, rather than always using CNTD as the basis
for the multiplication path.
This is tested by the ACLE patches but is really an independent
improvement.
Tested on aarch64-linux-gnu (with and without SVE) and aarch64_be-elf.
Applied as r274519.
Richard
2019-08-15 Richard Sandiford <richard.sandif...@arm.com>
gcc/
* config/aarch64/aarch64.c (aarch64_add_offset): In the fallback
multiplication case, try to compute VG * (lowest set bit) directly
rather than always basing the multiplication on VG. Use
expand_mult for the multiplication if we can.
gcc/testsuite/
* gcc.target/aarch64/sve/loop_add_4.c: Expect 10 INCWs and
INCDs rather than 8.
Index: gcc/config/aarch64/aarch64.c
===================================================================
--- gcc/config/aarch64/aarch64.c 2019-08-15 09:47:20.180358297 +0100
+++ gcc/config/aarch64/aarch64.c 2019-08-15 09:49:13.659521097 +0100
@@ -73,6 +73,7 @@ #define INCLUDE_STRING
#include "selftest-rtl.h"
#include "rtx-vector-builder.h"
#include "intl.h"
+#include "expmed.h"
/* This file should be included last. */
#include "target-def.h"
@@ -3465,20 +3466,36 @@ aarch64_add_offset (scalar_int_mode mode
}
else
{
- /* Use CNTD, then multiply it by FACTOR. */
- val = gen_int_mode (poly_int64 (2, 2), mode);
+ /* Base the factor on LOW_BIT if we can calculate LOW_BIT
+ directly, since that should increase the chances of being
+ able to use a shift and add sequence. If LOW_BIT itself
+ is out of range, just use CNTD. */
+ if (low_bit <= 16 * 8)
+ factor /= low_bit;
+ else
+ low_bit = 1;
+
+ val = gen_int_mode (poly_int64 (low_bit * 2, low_bit * 2), mode);
val = aarch64_force_temporary (mode, temp1, val);
- /* Go back to using a negative multiplication factor if we have
- no register from which to subtract. */
- if (code == MINUS && src == const0_rtx)
+ if (can_create_pseudo_p ())
+ {
+ rtx coeff1 = gen_int_mode (factor, mode);
+ val = expand_mult (mode, val, coeff1, NULL_RTX, false, true);
+ }
+ else
{
- factor = -factor;
- code = PLUS;
+ /* Go back to using a negative multiplication factor if we have
+ no register from which to subtract. */
+ if (code == MINUS && src == const0_rtx)
+ {
+ factor = -factor;
+ code = PLUS;
+ }
+ rtx coeff1 = gen_int_mode (factor, mode);
+ coeff1 = aarch64_force_temporary (mode, temp2, coeff1);
+ val = gen_rtx_MULT (mode, val, coeff1);
}
- rtx coeff1 = gen_int_mode (factor, mode);
- coeff1 = aarch64_force_temporary (mode, temp2, coeff1);
- val = gen_rtx_MULT (mode, val, coeff1);
}
if (shift > 0)
Index: gcc/testsuite/gcc.target/aarch64/sve/loop_add_4.c
===================================================================
--- gcc/testsuite/gcc.target/aarch64/sve/loop_add_4.c 2019-03-08
18:14:29.780994734 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve/loop_add_4.c 2019-08-15
09:49:13.659521097 +0100
@@ -68,7 +68,8 @@ TEST_ALL (LOOP)
/* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.s, w[0-9]+, w[0-9]+\n}
3 } } */
/* { dg-final { scan-assembler-times {\tld1w\tz[0-9]+\.s, p[0-7]+/z,
\[x[0-9]+, x[0-9]+, lsl 2\]} 8 } } */
/* { dg-final { scan-assembler-times {\tst1w\tz[0-9]+\.s, p[0-7]+, \[x[0-9]+,
x[0-9]+, lsl 2\]} 8 } } */
-/* { dg-final { scan-assembler-times {\tincw\tx[0-9]+\n} 8 } } */
+/* 2 for the calculations of -17 and 17. */
+/* { dg-final { scan-assembler-times {\tincw\tx[0-9]+\n} 10 } } */
/* { dg-final { scan-assembler-times {\tdecw\tz[0-9]+\.s, all, mul #16\n} 1 }
} */
/* { dg-final { scan-assembler-times {\tdecw\tz[0-9]+\.s, all, mul #15\n} 1 }
} */
@@ -85,7 +86,8 @@ TEST_ALL (LOOP)
/* { dg-final { scan-assembler-times {\tindex\tz[0-9]+\.d, x[0-9]+, x[0-9]+\n}
3 } } */
/* { dg-final { scan-assembler-times {\tld1d\tz[0-9]+\.d, p[0-7]+/z,
\[x[0-9]+, x[0-9]+, lsl 3\]} 8 } } */
/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d, p[0-7]+, \[x[0-9]+,
x[0-9]+, lsl 3\]} 8 } } */
-/* { dg-final { scan-assembler-times {\tincd\tx[0-9]+\n} 8 } } */
+/* 2 for the calculations of -17 and 17. */
+/* { dg-final { scan-assembler-times {\tincd\tx[0-9]+\n} 10 } } */
/* { dg-final { scan-assembler-times {\tdecd\tz[0-9]+\.d, all, mul #16\n} 1 }
} */
/* { dg-final { scan-assembler-times {\tdecd\tz[0-9]+\.d, all, mul #15\n} 1 }
} */
