i386: Allow SI, DI and TImode pushes from XMM registers

Also change XMM register constraint from "x" to "v" in FP push insns.

gcc/ChangeLog:

2020-05-15  Uroš Bizjak  <ubizjak@gmail.com>

	* config/i386/i386.md (SWI48DWI): New mode iterator.
	(*push<mode>2): Allow XMM registers.
	(*pushdi2_rex64): Ditto.
	(*pushsi2_rex64): Ditto.
	(*pushsi2): Ditto.
	(push XMM reg splitter): New splitter

	(*pushdf) Change "x" operand constraint to "v".
	(*pushsf_rex64): Ditto.
	(*pushsf): Ditto.

2 files changed, 62 insertions, 26 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 5eaa1b8..d44ad8b 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,16 @@
+2020-05-15  Uroš Bizjak  <ubizjak@gmail.com>
+
+	* config/i386/i386.md (SWI48DWI): New mode iterator.
+	(*push<mode>2): Allow XMM registers.
+	(*pushdi2_rex64): Ditto.
+	(*pushsi2_rex64): Ditto.
+	(*pushsi2): Ditto.
+	(push XMM reg splitter): New splitter
+
+	(*pushdf) Change "x" operand constraint to "v".
+	(*pushsf_rex64): Ditto.
+	(*pushsf): Ditto.
+
 2020-05-15  Richard Biener  <rguenther@suse.de>
 
 	PR tree-optimization/92260
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index b555c16..1bf0c1a 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -1051,6 +1051,9 @@
 ;; SWI and DWI together.
 (define_mode_iterator SWIDWI [QI HI SI DI (TI "TARGET_64BIT")])
 
+;; SWI48 and DWI together.
+(define_mode_iterator SWI48DWI [SI DI (TI "TARGET_64BIT")])
+
 ;; GET_MODE_SIZE for selected modes.  As GET_MODE_SIZE is not
 ;; compile time constant, it is faster to use <MODE_SIZE> than
 ;; GET_MODE_SIZE (<MODE>mode).  For XFmode which depends on
@@ -1672,8 +1675,8 @@
 ;; Push/pop instructions.
 
 (define_insn "*push<mode>2"
-  [(set (match_operand:DWI 0 "push_operand" "=<")
-	(match_operand:DWI 1 "general_no_elim_operand" "riF*o"))]
+  [(set (match_operand:DWI 0 "push_operand" "=<,<")
+	(match_operand:DWI 1 "general_no_elim_operand" "riF*o,*v"))]
   ""
   "#"
   [(set_attr "type" "multi")
@@ -1687,13 +1690,14 @@
   "ix86_split_long_move (operands); DONE;")
 
 (define_insn "*pushdi2_rex64"
-  [(set (match_operand:DI 0 "push_operand" "=<,!<")
-	(match_operand:DI 1 "general_no_elim_operand" "re*m,n"))]
+  [(set (match_operand:DI 0 "push_operand" "=<,<,!<")
+	(match_operand:DI 1 "general_no_elim_operand" "re*m,*v,n"))]
   "TARGET_64BIT"
   "@
    push{q}\t%1
+   #
    #"
-  [(set_attr "type" "push,multi")
+  [(set_attr "type" "push,multi,multi")
    (set_attr "mode" "DI")])
 
 ;; Convert impossible pushes of immediate to existing instructions.
@@ -1727,34 +1731,53 @@
 			     plus_constant (Pmode, stack_pointer_rtx, 4));
 })
 
+;; For TARGET_64BIT we always round up to 8 bytes.
+(define_insn "*pushsi2_rex64"
+  [(set (match_operand:SI 0 "push_operand" "=X,X")
+	(match_operand:SI 1 "nonmemory_no_elim_operand" "ri,*v"))]
+  "TARGET_64BIT"
+  "@
+   push{q}\t%q1
+   #"
+  [(set_attr "type" "push,multi")
+   (set_attr "mode" "DI")])
+
 (define_insn "*pushsi2"
-  [(set (match_operand:SI 0 "push_operand" "=<")
-	(match_operand:SI 1 "general_no_elim_operand" "ri*m"))]
+  [(set (match_operand:SI 0 "push_operand" "=<,<")
+	(match_operand:SI 1 "general_no_elim_operand" "ri*m,*v"))]
   "!TARGET_64BIT"
-  "push{l}\t%1"
-  [(set_attr "type" "push")
+  "@
+   push{l}\t%1
+   #"
+  [(set_attr "type" "push,multi")
    (set_attr "mode" "SI")])
 
-;; emit_push_insn when it calls move_by_pieces requires an insn to
-;; "push a byte/word".  But actually we use pushl, which has the effect
-;; of rounding the amount pushed up to a word.
+(define_split
+  [(set (match_operand:SWI48DWI 0 "push_operand")
+	(match_operand:SWI48DWI 1 "sse_reg_operand"))]
+  "TARGET_SSE && 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 (<SWI48DWI:MODE>mode)));
+  /* Preserve memory attributes. */
+  operands[0] = replace_equiv_address (operands[0], stack_pointer_rtx);
+})
 
-;; For TARGET_64BIT we always round up to 8 bytes.
-(define_insn "*push<mode>2_rex64"
-  [(set (match_operand:SWI124 0 "push_operand" "=X")
-	(match_operand:SWI124 1 "nonmemory_no_elim_operand" "r<i>"))]
-  "TARGET_64BIT"
-  "push{q}\t%q1"
-  [(set_attr "type" "push")
-   (set_attr "mode" "DI")])
+;; emit_push_insn when it calls move_by_pieces requires an insn to
+;; "push a byte/word".  But actually we use push{l,q}, which has
+;; the effect of rounding the amount pushed up to a word.
 
 (define_insn "*push<mode>2"
   [(set (match_operand:SWI12 0 "push_operand" "=X")
 	(match_operand:SWI12 1 "nonmemory_no_elim_operand" "rn"))]
-  "!TARGET_64BIT"
-  "push{l}\t%k1"
+  ""
+  "* return TARGET_64BIT ? \"push{q}\t%q1\" : \"push{l}\t%k1\";"
   [(set_attr "type" "push")
-   (set_attr "mode" "SI")])
+   (set (attr "mode")
+	(if_then_else (match_test "TARGET_64BIT")
+	  (const_string "DI")
+	  (const_string "SI")))])
 
 (define_insn "*push<mode>2_prologue"
   [(set (match_operand:W 0 "push_operand" "=<")
@@ -3031,7 +3054,7 @@
 
 (define_insn "*pushdf"
   [(set (match_operand:DF 0 "push_operand" "=<,<,<,<,<,<")
-	(match_operand:DF 1 "general_no_elim_operand" "f,r,*r,oF,rmC,x"))]
+	(match_operand:DF 1 "general_no_elim_operand" "f,r,*r,oF,rmC,v"))]
   ""
 {
   /* This insn should be already split before reg-stack.  */
@@ -3064,7 +3087,7 @@
 
 (define_insn "*pushsf_rex64"
   [(set (match_operand:SF 0 "push_operand" "=X,X,X")
-	(match_operand:SF 1 "nonmemory_no_elim_operand" "f,rF,x"))]
+	(match_operand:SF 1 "nonmemory_no_elim_operand" "f,rF,v"))]
   "TARGET_64BIT"
 {
   /* Anything else should be already split before reg-stack.  */
@@ -3078,7 +3101,7 @@
 
 (define_insn "*pushsf"
   [(set (match_operand:SF 0 "push_operand" "=<,<,<")
-	(match_operand:SF 1 "general_no_elim_operand" "f,rmF,x"))]
+	(match_operand:SF 1 "general_no_elim_operand" "f,rmF,v"))]
   "!TARGET_64BIT"
 {
   /* Anything else should be already split before reg-stack.  */