SH optimized software floating point routines

[Kaz Kojima]

Joern Rennecke <joern.rennecke@embecosm.com> wrote:
> I've found two bugs in truncdfsf2;
> I've also added back a number of hunks that Naveen had dropped.
> 
> Note that most of the patch has been prepared in 2006, so that is the
> proper most recent copyright date for those files that haven't been touched
> save for swapping the Copyright notice.

I've got some regressions with "make check" on sh4-unknown-linux-gnu.
It looks that all of them are failed with the undefined references to
__unorddf2/__unordsf2 when -mieee enabled.
I'm trying the attached patch over sh-softfp-20100718-2131 patch.
All regressions go away with it on cross sh4-unknown-linux-gnu,
though the native bootstrap will take a few days more.

BTW, it looks that softfp __unord?f2 routines check signaling NaNs
only.  This makes __builtin_isnan return false for quiet NaNs for
which current fp-bit ones return true when -mieee enabled.  Perhaps
that change of behavior might be OK for software FP.

Regards,
	kaz
--

diff -uprN ORIG/trunk/gcc/config/sh/ieee-754-df.S trunk/gcc/config/sh/ieee-754-df.S
--- ORIG/trunk/gcc/config/sh/ieee-754-df.S	2010-07-20 11:39:29.000000000 +0900
+++ trunk/gcc/config/sh/ieee-754-df.S	2010-07-20 11:36:15.000000000 +0900
@@ -23,11 +23,11 @@ see the files COPYING3 and COPYING.RUNTI
 !! STMicroelectronics ST40 CPUs
 !! Contributed by J"orn Rennecke joern.rennecke@st.com
 
-#ifndef __SH_FPU_DOUBLE__
-
 #include "lib1funcs.h"
 #include "insn-constants.h"
 
+#ifndef __SH_FPU_DOUBLE__
+
 /* Double-precision floating-point emulation.
    We handle NANs, +-infinity, and +-zero.
    However, we assume that for NANs, the topmost bit of the fraction is set.  */
@@ -123,7 +123,7 @@ GLOBAL(unorddf2):
 	mov.l	LOCAL(c_DF_NAN_MASK),r1
 	not	DBL0H,r0
 	tst	r1,r0
-	not	r6,r0
+	not	DBL1H,r0
 	bt	LOCAL(unord)
 	tst	r1,r0
 LOCAL(unord):
@@ -788,4 +788,52 @@ LOCAL(x7ff80000):
 #endif /* L_divdf3 */
 #endif /* DYN_SHIFT */
 
+#else /* __SH_FPU_DOUBLE__ */
+
+#ifdef L_unorddf2
+	.balign 4
+	.global GLOBAL(unorddf2)
+	FUNC(GLOBAL(unorddf2))
+GLOBAL(unorddf2):
+	flds	fr4,fpul
+	sts	fpul,r4
+	shll	r4
+	mov.l	LOCAL(c_DF_QNAN_MASK),r1
+	shlr	r4
+	cmp/eq	r4,r1
+	bf/s	LOCAL(unord_check_qnan0)
+	flds	fr5,fpul
+	sts	fpul,r5
+	tst	r5,r5
+	bt	LOCAL(unord_next)
+LOCAL(unord_check_qnan0):
+	not	r4,r0
+	tst	r1,r0
+	bt	LOCAL(unord)
+LOCAL(unord_next):
+	flds	fr6,fpul
+	sts	fpul,r6
+	shll	r6
+	shlr	r6
+	cmp/eq	r6,r1
+	bf/s	LOCAL(unord_check_qnan1)
+	flds	fr7,fpul
+	sts	fpul,r7
+	tst	r7,r7
+	bt	LOCAL(unord_fail)	
+LOCAL(unord_check_qnan1):
+	not	r6,r0
+	tst	r1,r0
+LOCAL(unord):
+	rts
+	movt	r0
+LOCAL(unord_fail):
+	rts
+	mov	#0,r0
+	.balign	4
+LOCAL(c_DF_QNAN_MASK):
+	.long 0x7ff00000
+	ENDFUNC(GLOBAL(unorddf2))
+#endif /* L_unorddf2 */
+
 #endif /* __SH_FPU_DOUBLE__ */
diff -uprN ORIG/trunk/gcc/config/sh/ieee-754-sf.S trunk/gcc/config/sh/ieee-754-sf.S
--- ORIG/trunk/gcc/config/sh/ieee-754-sf.S	2010-07-20 11:39:30.000000000 +0900
+++ trunk/gcc/config/sh/ieee-754-sf.S	2010-07-20 11:35:58.000000000 +0900
@@ -23,11 +23,11 @@ see the files COPYING3 and COPYING.RUNTI
 !! STMicroelectronics ST40 CPUs
 !! Contributed by J"orn Rennecke joern.rennecke@st.com
 
-#ifndef __SH_FPU_ANY__
-
 #include "lib1funcs.h"
 #include "insn-constants.h"
 
+#ifndef __SH_FPU_ANY__
+
 /* Single-precision floating-point emulation.
    We handle NANs, +-infinity, and +-zero.
    However, we assume that for NANs, the topmost bit of the fraction is set.  */
@@ -689,4 +689,42 @@ LOCAL(tab):
 #endif /* L_hypotf */
 #endif /* DYN_SHIFT */
 
+#else /* __SH_FPU_ANY__ */
+
+#ifdef L_unordsf2
+	.balign 4
+	.global GLOBAL(unordsf2)
+	FUNC(GLOBAL(unordsf2))
+GLOBAL(unordsf2):
+	flds	fr5,fpul
+	sts	fpul,r4
+	shll	r4
+	mov.l	LOCAL(c_SF_QNAN_MASK),r1
+	shlr	r4
+	cmp/eq	r4,r1
+	bt/s	LOCAL(unord_next)
+	not	r4,r0
+	tst	r1,r0
+	bt	LOCAL(unord)
+LOCAL(unord_next):
+	flds	fr4,fpul
+	sts	fpul,r5
+	shll	r5
+	shlr	r5
+	cmp/eq	r5,r1
+	bt/s	LOCAL(unord_fail)
+	not	r5,r0
+	tst	r1,r0
+LOCAL(unord):
+	rts
+	movt	r0
+LOCAL(unord_fail):
+	rts
+	mov	#0,r0
+	.balign	4
+LOCAL(c_SF_QNAN_MASK):
+	.long 0x7f800000
+	ENDFUNC(GLOBAL(unordsf2))
+#endif /* L_unordsf2 */
+
 #endif /* __SH_FPU_ANY__ */