From c01c4331112aaf45f0de20ed8883dbeab83ed896 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Sun, 23 May 2021 22:14:21 +0200
Subject: [PATCH] i386: Add push insns for 4-byte vectors [PR100722]
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

2021-05-23  Uroš Bizjak  <ubizjak@gmail.com>

gcc/
	PR target/100722
	* config/i386/mmx.md (*push<VI_32:mode>2_rex64):
	New instruction pattern.
	(*push<VI_32:mode>2): Ditto.
	(push splitter for SSE registers): New splitter.

gcc/testsuite/

	PR target/100722
	* gcc.target/i386/pr100722.c: New test.
---
 gcc/config/i386/mmx.md                   | 33 ++++++++++++++++++++++++++++++++
 gcc/testsuite/gcc.target/i386/pr100722.c | 17 ++++++++++++++++
 2 files changed, 50 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/i386/pr100722.c

diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md
index 4c42e6d..453e8ea 100644
--- a/gcc/config/i386/mmx.md
+++ b/gcc/config/i386/mmx.md
@@ -302,6 +302,39 @@
 	   ]
 	   (symbol_ref "true")))])
 
+;; For TARGET_64BIT we always round up to 8 bytes.
+(define_insn "*push<mode>2_rex64"
+  [(set (match_operand:VI_32 0 "push_operand" "=X,X")
+	(match_operand:VI_32 1 "nonmemory_no_elim_operand" "rC,*v"))]
+  "TARGET_SSE2 && TARGET_64BIT"
+  "@
+   push{q}\t%q1
+   #"
+  [(set_attr "type" "push,multi")
+   (set_attr "mode" "DI")])
+
+(define_insn "*push<mode>2"
+  [(set (match_operand:VI_32 0 "push_operand" "=<,<")
+	(match_operand:VI_32 1 "general_no_elim_operand" "rC*m,*v"))]
+  "TARGET_SSE2 && !TARGET_64BIT"
+  "@
+   push{l}\t%1
+   #"
+  [(set_attr "type" "push,multi")
+   (set_attr "mode" "SI")])
+
+(define_split
+  [(set (match_operand:VI_32 0 "push_operand")
+	(match_operand:VI_32 1 "sse_reg_operand"))]
+  "TARGET_SSE2 && reload_completed"
+  [(set (reg:P SP_REG) (plus:P (reg:P SP_REG) (match_dup 2)))
+    (set (match_dup 0) (match_dup 1))]
+{
+  operands[2] = GEN_INT (-PUSH_ROUNDING (GET_MODE_SIZE (<VI_32:MODE>mode)));
+  /* Preserve memory attributes. */
+  operands[0] = replace_equiv_address (operands[0], stack_pointer_rtx);
+})
+
 (define_expand "movmisalign<mode>"
   [(set (match_operand:VI_32 0 "nonimmediate_operand")
 	(match_operand:VI_32 1 "nonimmediate_operand"))]
diff --git a/gcc/testsuite/gcc.target/i386/pr100722.c b/gcc/testsuite/gcc.target/i386/pr100722.c
new file mode 100644
index 0000000..f784039
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr100722.c
@@ -0,0 +1,17 @@
+/* PR target/100722 */
+/* { dg-do compile } */
+/* { dg-options "-O -msse2" } */
+
+typedef char int8x4_t __attribute__((vector_size(4)));
+
+void stack_callee (int8x4_t, int8x4_t, int8x4_t, int8x4_t,
+		   int8x4_t, int8x4_t, int8x4_t);
+
+int8x4_t stack_caller_x1;
+
+void stack_caller (void)
+{
+  stack_callee (stack_caller_x1, stack_caller_x1, stack_caller_x1,
+		stack_caller_x1, stack_caller_x1, stack_caller_x1,
+		stack_caller_x1);
+}
-- 
2.7.4