Hi James,
Thanks for the feedback. Here is an update with the changes you proposed
and an updated changelog.
gcc/
2018-09-04 Sam Tebbs <sam.te...@arm.com>
PR target/85628
* config/aarch64/aarch64.md (*aarch64_bfxil):
Define.
* config/aarch64/constraints.md (Ulc): Define
* config/aarch64/aarch64-protos.h (aarch64_high_bits_all_ones_p):
Define.
* config/aarch64/aarch64.c (aarch64_high_bits_all_ones_p): New function.
gcc/testsuite
2018-09-04 Sam Tebbs <sam.te...@arm.com>
PR target/85628
* gcc.target/aarch64/combine_bfxil.c: New file.
* gcc.target/aarch64/combine_bfxil_2.c: New file.
On 08/28/2018 11:53 PM, James Greenhalgh wrote:
Hm, I'm not very sure about the naming here; "left consecutive" isn't a
common phrase to denote the mask you're looking for (exact_log2 (-i) != -1
if I'm reading right), and is misleading 0x0000ffff is 'left consecutive'
too, just with zeroes rather than ones.
* config/aarch64/aarch64.c (aarch64_is_left_consecutive):
New function.
gcc/testsuite
2018-08-01 Sam Tebbs<sam.te...@arm.com>
PR target/85628
* gcc.target/aarch64/combine_bfxil.c: New file.
* gcc.target/aarch64/combine_bfxil_2.c: New file.
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index
fa01475aa9ee579b6a3b2526295b622157120660..3cfa51b15af3e241672f1383cf881c12a44494a5
100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -1454,6 +1454,14 @@ aarch64_hard_regno_caller_save_mode (unsigned regno,
unsigned,
return SImode;
}
+/* Implement IS_LEFT_CONSECUTIVE. Check if I's bits are consecutive
What is IS_LEFT_CONSECUTIVE - I don't see it elsewhere in the GCC code, so
what does the comment refer to implementing?
+ ones from the MSB. */
+bool
+aarch64_is_left_consecutive (HOST_WIDE_INT i)
+{
+ return (i | (i - 1)) == HOST_WIDE_INT_M1;
exact_log2(-i) != HOST_WIDE_INT_M1?
diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h
index ef95fc829b83886e2ff00e4664e31af916e99b0c..b43e70285b3e6c45b830ce3790c38307b2294f81 100644
--- a/gcc/config/aarch64/aarch64-protos.h
+++ b/gcc/config/aarch64/aarch64-protos.h
@@ -575,4 +575,6 @@ rtl_opt_pass *make_pass_track_speculation (gcc::context *);
poly_uint64 aarch64_regmode_natural_size (machine_mode);
+bool aarch64_high_bits_all_ones_p (HOST_WIDE_INT);
+
#endif /* GCC_AARCH64_PROTOS_H */
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 1de76e075471acaa68584595023e3878b10538e2..352515e9fc92c7b14a631c76bbe3d25030174bcf 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -1474,6 +1474,13 @@ aarch64_hard_regno_caller_save_mode (unsigned regno, unsigned,
return SImode;
}
+/* Return true if I's bits are consecutive ones from the MSB. */
+bool
+aarch64_high_bits_all_ones_p (HOST_WIDE_INT i)
+{
+ return exact_log2(-i) != HOST_WIDE_INT_M1;
+}
+
/* Implement TARGET_CONSTANT_ALIGNMENT. Make strings word-aligned so
that strcpy from constants will be faster. */
diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
index 955769a64d2030839cdb337321a808626188190e..88f66104db31320389f05cdd5d161db9992a77b8 100644
--- a/gcc/config/aarch64/aarch64.md
+++ b/gcc/config/aarch64/aarch64.md
@@ -5336,6 +5336,31 @@
[(set_attr "type" "rev")]
)
+(define_insn "*aarch64_bfxil<mode>"
+ [(set (match_operand:GPI 0 "register_operand" "=r,r")
+ (ior:GPI (and:GPI (match_operand:GPI 1 "register_operand" "r,0")
+ (match_operand:GPI 3 "const_int_operand" "n, Ulc"))
+ (and:GPI (match_operand:GPI 2 "register_operand" "0,r")
+ (match_operand:GPI 4 "const_int_operand" "Ulc, n"))))]
+ "(INTVAL (operands[3]) == ~INTVAL (operands[4]))
+ && (aarch64_high_bits_all_ones_p (INTVAL (operands[3]))
+ || aarch64_high_bits_all_ones_p (INTVAL (operands[4])))"
+ {
+ switch (which_alternative)
+ {
+ case 0:
+ operands[3] = GEN_INT (ctz_hwi (~INTVAL (operands[3])));
+ return "bfxil\\t%<w>0, %<w>1, 0, %3";
+ case 1:
+ operands[3] = GEN_INT (ctz_hwi (~INTVAL (operands[4])));
+ return "bfxil\\t%<w>0, %<w>2, 0, %3";
+ default:
+ gcc_unreachable ();
+ }
+ }
+ [(set_attr "type" "bfm")]
+)
+
;; There are no canonicalisation rules for the position of the lshiftrt, ashift
;; operations within an IOR/AND RTX, therefore we have two patterns matching
;; each valid permutation.
diff --git a/gcc/config/aarch64/constraints.md b/gcc/config/aarch64/constraints.md
index 72cacdabdac52dcb40b480f7a5bfbf4997c742d8..31fc3eafd8bba03cc773e226223a6293c6dde8d4 100644
--- a/gcc/config/aarch64/constraints.md
+++ b/gcc/config/aarch64/constraints.md
@@ -172,6 +172,13 @@
A constraint that matches the immediate constant -1."
(match_test "op == constm1_rtx"))
+(define_constraint "Ulc"
+ "@internal
+ A constraint that matches a constant integer whose bits are consecutive ones
+ from the MSB."
+ (and (match_code "const_int")
+ (match_test "aarch64_high_bits_all_ones_p (ival)")))
+
(define_constraint "Usv"
"@internal
A constraint that matches a VG-based constant that can be loaded by
diff --git a/gcc/testsuite/gcc.target/aarch64/combine_bfxil.c b/gcc/testsuite/gcc.target/aarch64/combine_bfxil.c
new file mode 100644
index 0000000000000000000000000000000000000000..3bc1dd5b216477efe7494dbcdac7a5bf465af218
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/combine_bfxil.c
@@ -0,0 +1,98 @@
+/* { dg-do run } */
+/* { dg-options "-O2 --save-temps" } */
+
+extern void abort(void);
+
+unsigned long long
+combine_balanced (unsigned long long a, unsigned long long b)
+{
+ return (a & 0xffffffff00000000ll) | (b & 0x00000000ffffffffll);
+}
+
+unsigned long long
+combine_minimal (unsigned long long a, unsigned long long b)
+{
+ return (a & 0xfffffffffffffffe) | (b & 0x0000000000000001);
+}
+
+unsigned long long
+combine_unbalanced (unsigned long long a, unsigned long long b)
+{
+ return (a & 0xffffffffff000000ll) | (b & 0x0000000000ffffffll);
+}
+
+unsigned int
+combine_balanced_int (unsigned int a, unsigned int b)
+{
+ return (a & 0xffff0000ll) | (b & 0x0000ffffll);
+}
+
+unsigned int
+combine_unbalanced_int (unsigned int a, unsigned int b)
+{
+ return (a & 0xffffff00ll) | (b & 0x000000ffll);
+}
+
+__attribute__ ((noinline)) void
+foo (unsigned long long a, unsigned long long b, unsigned long long *c,
+ unsigned long long *d)
+{
+ *c = combine_minimal(a, b);
+ *d = combine_minimal(b, a);
+}
+
+__attribute__ ((noinline)) void
+foo2 (unsigned long long a, unsigned long long b, unsigned long long *c,
+ unsigned long long *d)
+{
+ *c = combine_balanced (a, b);
+ *d = combine_balanced (b, a);
+}
+
+__attribute__ ((noinline)) void
+foo3 (unsigned long long a, unsigned long long b, unsigned long long *c,
+ unsigned long long *d)
+{
+ *c = combine_unbalanced (a, b);
+ *d = combine_unbalanced (b, a);
+}
+
+void
+foo4 (unsigned int a, unsigned int b, unsigned int *c, unsigned int *d)
+{
+ *c = combine_balanced_int(a, b);
+ *d = combine_balanced_int(b, a);
+}
+
+void
+foo5 (unsigned int a, unsigned int b, unsigned int *c, unsigned int *d)
+{
+ *c = combine_unbalanced_int(a, b);
+ *d = combine_unbalanced_int(b, a);
+}
+
+int
+main(void)
+{
+ unsigned long long a = 0x0123456789ABCDEF, b = 0xFEDCBA9876543210, c, d;
+ foo3(a, b, &c, &d);
+ if(c != 0x0123456789543210) abort();
+ if(d != 0xfedcba9876abcdef) abort();
+ foo2(a, b, &c, &d);
+ if(c != 0x0123456776543210) abort();
+ if(d != 0xfedcba9889abcdef) abort();
+ foo(a, b, &c, &d);
+ if(c != 0x0123456789abcdee) abort();
+ if(d != 0xfedcba9876543211) abort();
+
+ unsigned int a2 = 0x01234567, b2 = 0xFEDCBA98, c2, d2;
+ foo4(a2, b2, &c2, &d2);
+ if(c2 != 0x0123ba98) abort();
+ if(d2 != 0xfedc4567) abort();
+ foo5(a2, b2, &c2, &d2);
+ if(c2 != 0x01234598) abort();
+ if(d2 != 0xfedcba67) abort();
+ return 0;
+}
+
+/* { dg-final { scan-assembler-times "bfxil\\t" 10 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/combine_bfxil_2.c b/gcc/testsuite/gcc.target/aarch64/combine_bfxil_2.c
new file mode 100644
index 0000000000000000000000000000000000000000..0fc140443bc67bcf12b93d72b7970e095620021e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/combine_bfxil_2.c
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+unsigned long long
+combine_non_consecutive (unsigned long long a, unsigned long long b)
+{
+ return (a & 0xfffffff200f00000ll) | (b & 0x00001000ffffffffll);
+}
+
+void
+foo4 (unsigned long long a, unsigned long long b, unsigned long long *c,
+ unsigned long long *d) {
+ /* { dg-final { scan-assembler-not "bfxil\\t" } } */
+ *c = combine_non_consecutive (a, b);
+ *d = combine_non_consecutive (b, a);
+}
