From e7429bc9d60c0cb9809a8040bb63dbb9390f40f1 Mon Sep 17 00:00:00 2001
From: Jakub Jelinek <jakub@redhat.com>
Date: Fri, 29 Jan 2021 11:54:22 +0100
Subject: [PATCH] arm: Fix up -mcpu=iwmmxt ICEs [PR98849]

The
https://gcc.gnu.org/r11-6707-g7432f255b70811dafaf325d94036ac580891de69
https://gcc.gnu.org/r11-6708-gbfab355012ca0f5219da8beb04f2fdaf757d34b7
changes moved the vashl/vashr/vlshr expanders from neon.md to vec-common.md
and changed their condition from TARGET_NEON to ARM_HAVE_<MODE>_ARITH,
so that they apply also for TARGET_HAVE_MVE.  But, the ARM_HAVE_<MODE>_ARITH
macros are sometimes true also for TARGET_REALLY_IWMMXT, which at least
from quick skimming of former iwmmxt*.md doesn't have such instructions,
so it seems incorrect to enable them for iwmmxt.  Furthermore, even if it
had them, iwmmxt doesn't support any way to broadcast values in those
modes (vec_duplicate and vec_init optabs) and the middle end relies on
if the vector x vector shift/rotate patterns are supported it can emit
vector x scalar shift/rotate by broadcasting the shift amount to a vector.

As the TARGET_NEON vs. TARGET_REALLY_IWMMXT vs. TARGET_HAVE_MVE never seem
to be enabled together, I think we can just write it the following way.

Note, seems iwmmxt actually does support vector x scalar shifts, but doesn't
really enable the optabs that would tell the middle-end code that it does
(and neon and mve don't seem to support those).  I'll defer that to anybody
that cares about iwmmxt (if any).

2021-01-29  Jakub Jelinek  <jakub@redhat.com>

	PR target/98849
	* config/arm/vec-common.md (mve_vshlq_<supf><mode>,
	vashl<mode>3, vashr<mode>3, vlshr<mode>3): Add
	&& !TARGET_REALLY_IWMMXT to conditions.

	* gcc.c-torture/compile/pr98849.c: New test.
---
 gcc/config/arm/vec-common.md                  |  8 +--
 gcc/testsuite/gcc.c-torture/compile/pr98849.c | 60 +++++++++++++++++++
 2 files changed, 64 insertions(+), 4 deletions(-)
 create mode 100644 gcc/testsuite/gcc.c-torture/compile/pr98849.c

diff --git a/gcc/config/arm/vec-common.md b/gcc/config/arm/vec-common.md
index 692b28ea8cc..345ada05523 100644
--- a/gcc/config/arm/vec-common.md
+++ b/gcc/config/arm/vec-common.md
@@ -301,7 +301,7 @@
 	(unspec:VDQIW [(match_operand:VDQIW 1 "s_register_operand" "w,w")
 		       (match_operand:VDQIW 2 "imm_lshift_or_reg_neon" "w,Dm")]
 	 VSHLQ))]
-  "ARM_HAVE_<MODE>_ARITH"
+  "ARM_HAVE_<MODE>_ARITH && !TARGET_REALLY_IWMMXT"
   "@
    vshl.<supf>%#<V_sz_elem>\t%<V_reg>0, %<V_reg>1, %<V_reg>2
    * return neon_output_shift_immediate (\"vshl\", 'i', &operands[2], <MODE>mode, VALID_NEON_QREG_MODE (<MODE>mode), true);"
@@ -312,7 +312,7 @@
   [(set (match_operand:VDQIW 0 "s_register_operand" "")
 	(ashift:VDQIW (match_operand:VDQIW 1 "s_register_operand" "")
 		      (match_operand:VDQIW 2 "imm_lshift_or_reg_neon" "")))]
-  "ARM_HAVE_<MODE>_ARITH"
+  "ARM_HAVE_<MODE>_ARITH && !TARGET_REALLY_IWMMXT"
 {
   emit_insn (gen_mve_vshlq_u<mode> (operands[0], operands[1], operands[2]));
   DONE;
@@ -325,7 +325,7 @@
   [(set (match_operand:VDQIW 0 "s_register_operand")
 	(ashiftrt:VDQIW (match_operand:VDQIW 1 "s_register_operand")
 			(match_operand:VDQIW 2 "imm_rshift_or_reg_neon")))]
-  "ARM_HAVE_<MODE>_ARITH"
+  "ARM_HAVE_<MODE>_ARITH && !TARGET_REALLY_IWMMXT"
 {
   if (s_register_operand (operands[2], <MODE>mode))
     {
@@ -343,7 +343,7 @@
   [(set (match_operand:VDQIW 0 "s_register_operand")
 	(lshiftrt:VDQIW (match_operand:VDQIW 1 "s_register_operand")
 			(match_operand:VDQIW 2 "imm_rshift_or_reg_neon")))]
-  "ARM_HAVE_<MODE>_ARITH"
+  "ARM_HAVE_<MODE>_ARITH && !TARGET_REALLY_IWMMXT"
 {
   if (s_register_operand (operands[2], <MODE>mode))
     {
diff --git a/gcc/testsuite/gcc.c-torture/compile/pr98849.c b/gcc/testsuite/gcc.c-torture/compile/pr98849.c
new file mode 100644
index 00000000000..988b625cc79
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/compile/pr98849.c
@@ -0,0 +1,60 @@
+/* PR target/98849 */
+
+unsigned int a[1024], b[1024];
+int c[1024], d[1024];
+
+void
+f1 (void)
+{
+  for (int i = 0; i < 1024; i++)
+    a[i] = b[i] << 3;
+}
+
+void
+f2 (int x)
+{
+  for (int i = 0; i < 1024; i++)
+    a[i] = b[i] << x;
+}
+
+void
+f3 (void)
+{
+  for (int i = 0; i < 1024; i++)
+    c[i] = d[i] << 3;
+}
+
+void
+f4 (int x)
+{
+  for (int i = 0; i < 1024; i++)
+    c[i] = d[i] << x;
+}
+
+void
+f5 (void)
+{
+  for (int i = 0; i < 1024; i++)
+    a[i] = b[i] >> 3;
+}
+
+void
+f6 (int x)
+{
+  for (int i = 0; i < 1024; i++)
+    a[i] = b[i] >> x;
+}
+
+void
+f7 (void)
+{
+  for (int i = 0; i < 1024; i++)
+    c[i] = d[i] >> 3;
+}
+
+void
+f8 (int x)
+{
+  for (int i = 0; i < 1024; i++)
+    c[i] = d[i] >> x;
+}
-- 
2.30.2