From: Kyrylo Tkachov <kyrylo.tkachov@arm.com>
Date: Tue, 23 May 2023 10:09:08 +0000 (+0100)
Subject: aarch64: PR target/109855 Add predicate and constraints to define_subst in aarch64... 
X-Git-Tag: basepoints/gcc-15~9011
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=75d1eff5933fc0d853af730627218f182612b561;p=thirdparty%2Fgcc.git

aarch64: PR target/109855 Add predicate and constraints to define_subst in aarch64-simd.md

In this PR we ICE because the substituted pattern for mla "lost" its predicate and constraint for operand 0
because the define_subst template:
  [(set (match_operand:<VDBL> 0)
        (vec_concat:<VDBL>
         (match_dup 1)
         (match_operand:VDZ 2 "aarch64_simd_or_scalar_imm_zero")))])

Uses match_operand instead of match_dup for operand 0. We can't use match_dup 0 for it because we need to specify the widened mode.
The problem is fixed by adding a "register_operand" predicate and "=w" constraint to the match_operand.
This makes sense conceptually too as the transformation we're targeting only applies to instructions that write a "w" register.
With this change the mddump pattern that ICEs goes from:
(define_insn ("aarch64_mlav4hi_vec_concatz_le")
     [
        (set (match_operand:V8HI 0 ("") ("")) <<------ Missing constraint!
            (vec_concat:V8HI (plus:V4HI (mult:V4HI (match_operand:V4HI 2 ("register_operand") ("w"))
                        (match_operand:V4HI 3 ("register_operand") ("w")))
                    (match_operand:V4HI 1 ("register_operand") ("0")))
                (match_operand:V4HI 4 ("aarch64_simd_or_scalar_imm_zero") (""))))
    ] ("(!BYTES_BIG_ENDIAN) && (TARGET_SIMD)") ("mla\t%0.4h, %2.4h, %3.4h")

to the proper:
(define_insn ("aarch64_mlav4hi_vec_concatz_le")
     [
        (set (match_operand:V8HI 0 ("register_operand") ("=w")) <<-------- Constraint in the right place
            (vec_concat:V8HI (plus:V4HI (mult:V4HI (match_operand:V4HI 2 ("register_operand") ("w"))
                        (match_operand:V4HI 3 ("register_operand") ("w")))
                    (match_operand:V4HI 1 ("register_operand") ("0")))
                (match_operand:V4HI 4 ("aarch64_simd_or_scalar_imm_zero") (""))))
    ] ("(!BYTES_BIG_ENDIAN) && (TARGET_SIMD)") ("mla\t%0.4h, %2.4h, %3.4h")

This seems to do the right thing for multi-alternative patterns as well, the annotated pattern for aarch64_cmltv8qi is:
(define_insn ("aarch64_cmltv8qi")
     [
        (set (match_operand:V8QI 0 ("register_operand") ("=w,w"))
            (neg:V8QI (lt:V8QI (match_operand:V8QI 1 ("register_operand") ("w,w"))
                    (match_operand:V8QI 2 ("aarch64_simd_reg_or_zero") ("w,ZDz")))))
    ]

whereas the substituted version now looks like:
(define_insn ("aarch64_cmltv8qi_vec_concatz_le")
     [
        (set (match_operand:V16QI 0 ("register_operand") ("=w,w"))
            (vec_concat:V16QI (neg:V8QI (lt:V8QI (match_operand:V8QI 1 ("register_operand") ("w,w"))
                        (match_operand:V8QI 2 ("aarch64_simd_reg_or_zero") ("w,ZDz"))))
                (match_operand:V8QI 3 ("aarch64_simd_or_scalar_imm_zero") (""))))
    ]

Bootstrapped and tested on aarch64-none-linux-gnu.

gcc/ChangeLog:

	PR target/109855
	* config/aarch64/aarch64-simd.md (add_vec_concat_subst_le): Add predicate
	and constraint for operand 0.
	(add_vec_concat_subst_be): Likewise.

gcc/testsuite/ChangeLog:

	PR target/109855
	* gcc.target/aarch64/pr109855.c: New test.
---

diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 61c815b9a1fc..af95bbb29a7b 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -26,7 +26,7 @@
   [(set (match_operand:VDZ 0)
         (match_operand:VDZ 1))]
   "!BYTES_BIG_ENDIAN"
-  [(set (match_operand:<VDBL> 0)
+  [(set (match_operand:<VDBL> 0 "register_operand" "=w")
         (vec_concat:<VDBL>
          (match_dup 1)
          (match_operand:VDZ 2 "aarch64_simd_or_scalar_imm_zero")))])
@@ -35,7 +35,7 @@
   [(set (match_operand:VDZ 0)
         (match_operand:VDZ 1))]
   "BYTES_BIG_ENDIAN"
-  [(set (match_operand:<VDBL> 0)
+  [(set (match_operand:<VDBL> 0 "register_operand" "=w")
         (vec_concat:<VDBL>
          (match_operand:VDZ 2 "aarch64_simd_or_scalar_imm_zero")
          (match_dup 1)))])
diff --git a/gcc/testsuite/gcc.target/aarch64/pr109855.c b/gcc/testsuite/gcc.target/aarch64/pr109855.c
new file mode 100644
index 000000000000..90db90c6cf9a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/pr109855.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-O" } */
+
+typedef char __attribute__((__vector_size__ (4))) U;
+typedef short __attribute__((__vector_size__ (8))) V;
+
+U
+foo (V v, V w)
+{
+  return __builtin_convertvector (w * w + w, U);
+}
+