On Thu, Jul 09, 2015 at 01:58:22PM -0700, H.J. Lu wrote:
> On Thu, Jul 09, 2015 at 12:13:38PM -0700, H.J. Lu wrote:
> > ix86_split_long_move can optimize floating point constant move, which
> > can be used to optimize SFmode move for IA MCU.
> >
> > OK for trunk if there is no regression?
> >
> >
> > H.J.
> > ---
> > gcc/
> >
> > PR target/66824
> > * config/i386/i386.c (ix86_split_to_parts): Allow SFmode move
> > for IA MCU.
> > (ix86_split_long_move): Support single move.
> > * config/i386/i386.md (FP splitter): Allow SFmode for IA MCU.
> >
> > gcc/testsuite/
> >
> > PR target/66824
> > * gcc.target/i386/pr66824.c: New test.
> > ---
>
>
> I missed the testcase. Here is the updated patch.
>
ix86_split_long_move can optimize floating point constant move, which
can be used to optimize SFmode move with software floating point.
OK for trunk if there are no regressions?
H.J.
--
gcc/
PR target/66824
* config/i386/i386.c (ix86_split_to_parts): Allow SFmode move
without 387, MMX nor SSE.
(ix86_split_long_move): Support single move.
* config/i386/i386.md (FP splitter): Allow SFmode without 387,
MMX nor SSE.
gcc/testsuite/
PR target/66824
* gcc.target/i386/pr66824.c: New test.
---
gcc/config/i386/i386.c | 18 +++++++++++++++++-
gcc/config/i386/i386.md | 6 +++++-
gcc/testsuite/gcc.target/i386/pr66824.c | 29 +++++++++++++++++++++++++++++
3 files changed, 51 insertions(+), 2 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/i386/pr66824.c
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 6b5af11..108f211 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -22756,7 +22756,13 @@ ix86_split_to_parts (rtx operand, rtx *parts,
machine_mode mode)
size = (GET_MODE_SIZE (mode) + 4) / 8;
gcc_assert (!REG_P (operand) || !MMX_REGNO_P (REGNO (operand)));
- gcc_assert (size >= 2 && size <= 4);
+ /* For software floating point, we also optimize SFmode move. */
+ gcc_assert ((size >= 2
+ || (mode == SFmode
+ && !TARGET_80387
+ && !TARGET_MMX
+ && !TARGET_SSE))
+ && size <= 4);
/* Optimize constant pool reference to immediates. This is used by fp
moves, that force all constants to memory to allow combining. */
@@ -22834,10 +22840,14 @@ ix86_split_to_parts (rtx operand, rtx *parts,
machine_mode mode)
case DFmode:
REAL_VALUE_TO_TARGET_DOUBLE (r, l);
break;
+ case SFmode:
+ REAL_VALUE_TO_TARGET_SINGLE (r, l[0]);
+ goto part0;
default:
gcc_unreachable ();
}
parts[1] = gen_int_mode (l[1], SImode);
+part0:
parts[0] = gen_int_mode (l[0], SImode);
}
else
@@ -22944,6 +22954,12 @@ ix86_split_long_move (rtx operands[])
nparts = ix86_split_to_parts (operands[1], part[1], GET_MODE (operands[0]));
ix86_split_to_parts (operands[0], part[0], GET_MODE (operands[0]));
+ if (nparts == 1)
+ {
+ emit_move_insn (part[0][0], part[1][0]);
+ return;
+ }
+
/* When emitting push, take care for source operands on the stack. */
if (push && MEM_P (operands[1])
&& reg_overlap_mentioned_p (stack_pointer_rtx, operands[1]))
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index bc98389..0351c36 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -3507,7 +3507,11 @@
"reload_completed
&& (GET_MODE (operands[0]) == TFmode
|| GET_MODE (operands[0]) == XFmode
- || GET_MODE (operands[0]) == DFmode)
+ || GET_MODE (operands[0]) == DFmode
+ || (GET_MODE (operands[0]) == SFmode
+ && !TARGET_80387
+ && !TARGET_MMX
+ && !TARGET_SSE))
&& !(ANY_FP_REG_P (operands[0]) || ANY_FP_REG_P (operands[1]))"
[(const_int 0)]
"ix86_split_long_move (operands); DONE;")
diff --git a/gcc/testsuite/gcc.target/i386/pr66824.c
b/gcc/testsuite/gcc.target/i386/pr66824.c
new file mode 100644
index 0000000..3511e4c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr66824.c
@@ -0,0 +1,29 @@
+/* { dg-do compile { target ia32 } } */
+/* { dg-options "-O2 -mno-sse -mno-mmx -mno-80387" } */
+/* { dg-final { scan-assembler-not "\.LC\[0-9\]" } } */
+
+double foo (float);
+
+double
+f1 (void)
+{
+ return foo (1.0);
+}
+
+double
+f2 (void)
+{
+ return foo (0.0);
+}
+
+void
+f3 (float *x, float t)
+{
+ *x = 0.0 + t;
+}
+
+float
+f4 (void)
+{
+ return 1.0;
+}
--
2.4.3
