[AArch64] Recognize a missed usage of a sbfiz instruction

A customer reported the following missed opportunities to combine a couple
instructions into a sbfiz.

int sbfiz32 (int x)
{
  return x << 29 >> 10;
}

long sbfiz64 (long x)
{
  return x << 58 >> 20;
}

This gets converted to the following pattern:

(set (reg:SI 98)
    (ashift:SI (sign_extend:SI (reg:HI 0 x0 [ xD.3334 ]))
        (const_int 6 [0x6])))

Currently, gcc generates the following:

sbfiz32:
  lsl x0, x0, 29
  asr x0, x0, 10
  ret

sbfiz64:
  lsl x0, x0, 58
  asr x0, x0, 20
  ret

It could generate this instead:

sbfiz32:
  sbfiz   w0, w0, 19, 3
  ret

sbfiz64::
  sbfiz   x0, x0, 38, 6
  ret

The unsigned versions already generate ubfiz for the same code, so the lack of
a sbfiz pattern may have been an oversight.

This particular sbfiz pattern shows up in both CPU2006 (~ 80 hits) and
CPU2017 (~ 280 hits). It's not a lot, but seems beneficial in any case. No
significant performance differences, probably due to the small number of
occurrences or cases outside hot areas.

gcc/ChangeLog:

2018-05-22  Luis Machado  <luis.machado@linaro.org>

	gcc/
	* config/aarch64/aarch64.md (*ashift<mode>_extv_bfiz): New pattern.

gcc/testsuite/ChangeLog:

2018-05-22  Luis Machado  <luis.machado@linaro.org>

	gcc/testsuite/
	* gcc.target/aarch64/lsl_asr_sbfiz.c: New test.

From-SVN: r260546

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 7ba041b..d2e0b06 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,7 @@
+2018-05-22  Luis Machado  <luis.machado@linaro.org>
+
+       * config/aarch64/aarch64.md (*ashift<mode>_extv_bfiz): New pattern.
+
 2018-05-22  Martin Sebor  <msebor@redhat.com>
 
        * calls.c (maybe_warn_nonstring_arg): Fix a typo in a comment.

diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
index 8a894f8..7a0e34d 100644 (file)
--- a/gcc/config/aarch64/aarch64.md
+++ b/gcc/config/aarch64/aarch64.md
@@ -4790,6 +4790,20 @@
   [(set_attr "type" "bfx")]
 )
 
+;; Match sbfiz pattern in a shift left + shift right operation.
+
+(define_insn "*ashift<mode>_extv_bfiz"
+  [(set (match_operand:GPI 0 "register_operand" "=r")
+       (ashift:GPI (sign_extract:GPI (match_operand:GPI 1 "register_operand" "r")
+                                     (match_operand 2 "aarch64_simd_shift_imm_offset_<mode>" "n")
+                                     (const_int 0))
+                    (match_operand 3 "aarch64_simd_shift_imm_<mode>" "n")))]
+  "IN_RANGE (INTVAL (operands[2]) + INTVAL (operands[3]),
+            1, GET_MODE_BITSIZE (<MODE>mode) - 1)"
+  "sbfiz\\t%<w>0, %<w>1, %3, %2"
+  [(set_attr "type" "bfx")]
+)
+
 ;; When the bit position and width of the equivalent extraction add up to 32
 ;; we can use a W-reg LSL instruction taking advantage of the implicit
 ;; zero-extension of the X-reg.

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 12079ae..5ab91fd 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,7 @@
+2018-05-22  Luis Machado  <luis.machado@linaro.org>
+
+       * gcc.target/aarch64/lsl_asr_sbfiz.c: New test.
+
 2018-05-22  Janus Weil  <janus@gcc.gnu.org>
 
        PR fortran/85841

diff --git a/gcc/testsuite/gcc.target/aarch64/lsl_asr_sbfiz.c b/gcc/testsuite/gcc.target/aarch64/lsl_asr_sbfiz.c
new file mode 100644 (file)
index 0000000..106433d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/lsl_asr_sbfiz.c
@@ -0,0 +1,24 @@
+/* { dg-do compile } */
+/* { dg-options "-O3" } */
+
+/* Check that a LSL followed by an ASR can be combined into a single SBFIZ
+   instruction.  */
+
+/* Using W-reg */
+
+int
+sbfiz32 (int x)
+{
+  return x << 29 >> 10;
+}
+
+/* Using X-reg */
+
+long long
+sbfiz64 (long long x)
+{
+  return x << 58 >> 20;
+}
+
+/* { dg-final { scan-assembler "sbfiz\tw" } } */
+/* { dg-final { scan-assembler "sbfiz\tx" } } */