re PR target/70873 ([7 Regressio] 20% performance regression at 482.sphinx3 after...

	PR target/70873
	* config/i386/i386-protos.h (ix86_standard_x87sse_constant_load_p):
	New prototype.
	* config/i386/i386.c (ix86_standard_x87sse_constant_load_p): New.
	* config/i386/i386.md (push mem splitter): Use find_constant_src in
	the splitter condition.
	(FP load splitter): Use ix86_standard_x87sse_constant_load_p in
	the splitter condition.
	(FP float_extend load splitter): Ditto.

From-SVN: r235936

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 230f5d34e8294474e1b7d3ee5ef6fab18dfab79a..6bf86daa042e472c29599c4e8701cd6e7766eb1d 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,8 +1,20 @@
+2016-05-06  Uros Bizjak  <ubizjak@gmail.com>
+
+       PR target/70873
+       * config/i386/i386-protos.h (ix86_standard_x87sse_constant_load_p):
+       New prototype.
+       * config/i386/i386.c (ix86_standard_x87sse_constant_load_p): New.
+       * config/i386/i386.md (push mem splitter): Use find_constant_src in
+       the splitter condition.
+       (FP load splitter): Use ix86_standard_x87sse_constant_load_p in
+       the splitter condition.
+       (FP float_extend load splitter): Ditto.
+
 2016-05-05  Uros Bizjak  <ubizjak@gmail.com>
 
        * config/i386/i386.md (peehole2 patterns): Change true_regnum
-       to REGNUM in all peephole2 patterns.
-       (post-reload splitters): Change true_regnum to REGNUM in
+       to REGNO in all peephole2 patterns.
+       (post-reload splitters): Change true_regnum to REGNO in
        post-reload splitters.
        (zero_extend splitters): Use general_reg_operand and
        nonimmediate_gr_operand predicates.

diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h
index 4145ed566582e439d02b523f2df7c0153e2930d0..447f67e2dff7fa566d399b7b2f95e568652a8fe7 100644 (file)
--- a/gcc/config/i386/i386-protos.h
+++ b/gcc/config/i386/i386-protos.h
@@ -52,6 +52,7 @@ extern const char *standard_80387_constant_opcode (rtx);
 extern rtx standard_80387_constant_rtx (int);
 extern int standard_sse_constant_p (rtx, machine_mode);
 extern const char *standard_sse_constant_opcode (rtx_insn *, rtx);
+extern bool ix86_standard_x87sse_constant_load_p (const rtx_insn *, rtx);
 extern bool symbolic_reference_mentioned_p (rtx);
 extern bool extended_reg_mentioned_p (rtx);
 extern bool x86_extended_QIreg_mentioned_p (rtx_insn *);

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 9680aaf3f5068f9ea0d2de4cf62bf97a4b742aef..05476f37449e932e6441949343c39186a62b4a3c 100644 (file)
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -11219,6 +11219,26 @@ standard_sse_constant_opcode (rtx_insn *insn, rtx x)
   gcc_unreachable ();
 }
 
+/* Returns true if INSN can be transformed from a memory load
+   to a supported FP constant load.  */
+
+bool
+ix86_standard_x87sse_constant_load_p (const rtx_insn *insn, rtx dst)
+{
+  rtx src = find_constant_src (insn);
+
+  gcc_assert (REG_P (dst));
+
+  if (src == NULL
+      || (SSE_REGNO_P (REGNO (dst))
+         && standard_sse_constant_p (src, GET_MODE (dst)) != 1)
+      || (STACK_REGNO_P (REGNO (dst))
+          && standard_80387_constant_p (src) < 1))
+    return false;
+
+  return true;
+}
+
 /* Returns true if OP contains a symbol reference */
 
 bool

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 22ad8221ef89434df43e098408c8a8cc0e216dee..0bf01ab1fadf5a123414ce50d15b82ab991a0597 100644 (file)
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -3072,14 +3072,10 @@
 (define_split
   [(set (match_operand:SF 0 "push_operand")
        (match_operand:SF 1 "memory_operand"))]
-  "reload_completed"
+  "reload_completed
+   && find_constant_src (insn)"
   [(set (match_dup 0) (match_dup 2))]
-{
-  operands[2] = find_constant_src (curr_insn);
-
-  if (operands[2] == NULL_RTX)
-    FAIL;
-})
+  "operands[2] = find_constant_src (curr_insn);")
 
 (define_split
   [(set (match_operand 0 "push_operand")
@@ -3601,19 +3597,10 @@
    && (GET_MODE (operands[0]) == TFmode
        || GET_MODE (operands[0]) == XFmode
        || GET_MODE (operands[0]) == DFmode
-       || GET_MODE (operands[0]) == SFmode)"
+       || GET_MODE (operands[0]) == SFmode)
+   && ix86_standard_x87sse_constant_load_p (insn, operands[0])"
   [(set (match_dup 0) (match_dup 2))]
-{
-  operands[2] = find_constant_src (curr_insn);
-
-  if (operands[2] == NULL_RTX
-      || (SSE_REGNO_P (REGNO (operands[0]))
-         && standard_sse_constant_p (operands[2],
-                                     GET_MODE (operands[0])) != 1)
-      || (STACK_REGNO_P (REGNO (operands[0]))
-          && standard_80387_constant_p (operands[2]) < 1))
-    FAIL;
-})
+  "operands[2] = find_constant_src (curr_insn);")
 
 (define_split
   [(set (match_operand 0 "any_fp_register_operand")
@@ -3621,19 +3608,10 @@
   "reload_completed
    && (GET_MODE (operands[0]) == TFmode
        || GET_MODE (operands[0]) == XFmode
-       || GET_MODE (operands[0]) == DFmode)"
+       || GET_MODE (operands[0]) == DFmode)
+   && ix86_standard_x87sse_constant_load_p (insn, operands[0])"
   [(set (match_dup 0) (match_dup 2))]
-{
-  operands[2] = find_constant_src (curr_insn);
-
-  if (operands[2] == NULL_RTX
-      || (SSE_REGNO_P (REGNO (operands[0]))
-         && standard_sse_constant_p (operands[2],
-                                     GET_MODE (operands[0])) != 1)
-      || (STACK_REGNO_P (REGNO (operands[0]))
-          && standard_80387_constant_p (operands[2]) < 1))
-    FAIL;
-})
+  "operands[2] = find_constant_src (curr_insn);")
 
 ;; Split the load of -0.0 or -1.0 into fldz;fchs or fld1;fchs sequence
 (define_split