re PR target/54089 ([SH] Refactor shift patterns)

	PR target/54089
	* config/sh/sh.h (SH_DYNAMIC_SHIFT_COST): Set always to 1 if
	dynamic shifts are available.
	(SHIFT_COUNT_TRUNCATED): Always define to 0.  Correct comment.
	* config/sh/sh.c (ashl_lshr_seq, ext_ashl_lshr_seq): Add comments.
	* config/sh/predicates.md (shift_count_operand): Allow
	arith_reg_operand even if TARGET_DYNSHIFT is false.
	* config/sh/sh.md (ashlsi3, lshrsi3): Expand library call patterns
	if needed.
	(ashlsi3_d_call, lshrsi3_d_call): New insns.

	PR target/54089
	* config/sh/lib1funcs.S (ashlsi3): Reimplement as ashlsi3_r0.
	(lshrsi3): Reimplement as lshrsi3_r0.

	PR target/54089
	* gcc.target/sh/pr54089-3.c: New.

From-SVN: r191161

1 files changed, 243 insertions, 208 deletions

diff --git a/libgcc/config/sh/lib1funcs.S b/libgcc/config/sh/lib1funcs.S
index 2f0ca16cd91..c5a00db9a20 100644
--- a/libgcc/config/sh/lib1funcs.S
+++ b/libgcc/config/sh/lib1funcs.S
@@ -1,5 +1,5 @@
 /* Copyright (C) 1994, 1995, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
-   2004, 2005, 2006, 2009
+   2004, 2005, 2006, 2009, 2012
    Free Software Foundation, Inc.
 
 This file is free software; you can redistribute it and/or modify it
@@ -241,7 +241,7 @@ GLOBAL(ashiftrt_r4_0):
 ! Entry:
 !
 ! r4: Value to shift
-! r5: Shifts
+! r5: Shift count
 !
 ! Exit:
 !
@@ -249,7 +249,7 @@ GLOBAL(ashiftrt_r4_0):
 !
 ! Destroys:
 !
-! (none)
+! T bit, r5
 !
 
 	.global	GLOBAL(ashrsi3)
@@ -388,318 +388,353 @@ LOCAL(ashrsi3_0):
 
 !
 ! GLOBAL(ashlsi3)
+! (For compatibility with older binaries, not used by compiler)
 !
 ! Entry:
-!
-! r4: Value to shift
-! r5: Shifts
+!	r4: Value to shift
+!	r5: Shift count
 !
 ! Exit:
-!
-! r0: Result
+!	r0: Result
 !
 ! Destroys:
+!	T bit
+!
 !
-! (none)
+! GLOBAL(ashlsi3_r0)
 !
+! Entry:
+!	r4: Value to shift
+!	r0: Shift count
+!
+! Exit:
+!	r0: Result
+!
+! Destroys:
+!	T bit
+
 	.global	GLOBAL(ashlsi3)
+	.global GLOBAL(ashlsi3_r0)
 	HIDDEN_FUNC(GLOBAL(ashlsi3))
-	.align	2
+	HIDDEN_FUNC(GLOBAL(ashlsi3_r0))
 GLOBAL(ashlsi3):
-	mov	#31,r0
-	and	r0,r5
-	mova	LOCAL(ashlsi3_table),r0
-	mov.b	@(r0,r5),r5
+	mov	r5,r0
+	.align	2
+GLOBAL(ashlsi3_r0):
+
 #ifdef __sh1__
-	add	r5,r0
+	and	#31,r0
+	shll2	r0
+	mov.l	r4,@-r15
+	mov	r0,r4
+	mova	LOCAL(ashlsi3_table),r0
+	add	r4,r0
+	mov.l	@r15+,r4
 	jmp	@r0
+	mov	r4,r0
+	.align 2
 #else
-	braf	r5
-#endif
+	and	#31,r0
+	shll2	r0
+	braf	r0
 	mov	r4,r0
+#endif
 
-	.align	2
 LOCAL(ashlsi3_table):
-	.byte		LOCAL(ashlsi3_0)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_1)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_2)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_3)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_4)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_5)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_6)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_7)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_8)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_9)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_10)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_11)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_12)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_13)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_14)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_15)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_16)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_17)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_18)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_19)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_20)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_21)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_22)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_23)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_24)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_25)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_26)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_27)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_28)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_29)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_30)-LOCAL(ashlsi3_table)
-	.byte		LOCAL(ashlsi3_31)-LOCAL(ashlsi3_table)
-
-LOCAL(ashlsi3_6):
-	shll2	r0
-LOCAL(ashlsi3_4):
-	shll2	r0
-LOCAL(ashlsi3_2):
+	rts				// << 0
+	nop
+LOCAL(ashlsi_1):
+	rts				// << 1
+	shll	r0
+LOCAL(ashlsi_2):			// << 2
 	rts
 	shll2	r0
-
-LOCAL(ashlsi3_7):
-	shll2	r0
-LOCAL(ashlsi3_5):
+	bra	LOCAL(ashlsi_1)		// << 3
 	shll2	r0
-LOCAL(ashlsi3_3):
+	bra	LOCAL(ashlsi_2)		// << 4
 	shll2	r0
-LOCAL(ashlsi3_1):
-	rts
+	bra	LOCAL(ashlsi_5)		// << 5
 	shll	r0
-
-LOCAL(ashlsi3_14):
-	shll2	r0
-LOCAL(ashlsi3_12):
+	bra	LOCAL(ashlsi_6)		// << 6
 	shll2	r0
-LOCAL(ashlsi3_10):
-	shll2	r0
-LOCAL(ashlsi3_8):
+	bra	LOCAL(ashlsi_7)		// << 7
+	shll	r0
+LOCAL(ashlsi_8):			// << 8
 	rts
 	shll8	r0
-
-LOCAL(ashlsi3_15):
-	shll2	r0
-LOCAL(ashlsi3_13):
+	bra	LOCAL(ashlsi_8)		// << 9
+	shll	r0
+	bra	LOCAL(ashlsi_8)		// << 10
 	shll2	r0
-LOCAL(ashlsi3_11):
+	bra	LOCAL(ashlsi_11)	// << 11
+	shll	r0
+	bra	LOCAL(ashlsi_12)	// << 12
 	shll2	r0
-LOCAL(ashlsi3_9):
+	bra	LOCAL(ashlsi_13)	// << 13
+	shll	r0
+	bra	LOCAL(ashlsi_14)	// << 14
+	shll8	r0
+	bra	LOCAL(ashlsi_15)	// << 15
 	shll8	r0
+LOCAL(ashlsi_16):			// << 16
 	rts
+	shll16	r0
+	bra	LOCAL(ashlsi_16)	// << 17
 	shll	r0
-
-LOCAL(ashlsi3_22):
-	shll2	r0
-LOCAL(ashlsi3_20):
+	bra	LOCAL(ashlsi_16)	// << 18
 	shll2	r0
-LOCAL(ashlsi3_18):
+	bra	LOCAL(ashlsi_19)	// << 19
+	shll	r0
+	bra	LOCAL(ashlsi_20)	// << 20
 	shll2	r0
-LOCAL(ashlsi3_16):
-	rts
+	bra	LOCAL(ashlsi_21)	// << 21
+	shll	r0
+	bra	LOCAL(ashlsi_22)	// << 22
 	shll16	r0
-
-LOCAL(ashlsi3_23):
-	shll2	r0
-LOCAL(ashlsi3_21):
+	bra	LOCAL(ashlsi_23)	// << 23
+	shll16	r0
+	bra	LOCAL(ashlsi_16)	// << 24
+	shll8	r0
+	bra	LOCAL(ashlsi_25)	// << 25
+	shll	r0
+	bra	LOCAL(ashlsi_26)	// << 26
 	shll2	r0
-LOCAL(ashlsi3_19):
+	bra	LOCAL(ashlsi_27)	// << 27
+	shll	r0
+	bra	LOCAL(ashlsi_28)	// << 28
 	shll2	r0
-LOCAL(ashlsi3_17):
+	bra	LOCAL(ashlsi_29)	// << 29
+	shll16	r0
+	bra	LOCAL(ashlsi_30)	// << 30
 	shll16	r0
+	and	#1,r0			// << 31
 	rts
-	shll	r0
+	rotr	r0
 
-LOCAL(ashlsi3_30):
-	shll2	r0
-LOCAL(ashlsi3_28):
+LOCAL(ashlsi_7):
 	shll2	r0
-LOCAL(ashlsi3_26):
+LOCAL(ashlsi_5):
+LOCAL(ashlsi_6):
 	shll2	r0
-LOCAL(ashlsi3_24):
-	shll16	r0
 	rts
-	shll8	r0
-
-LOCAL(ashlsi3_31):
+LOCAL(ashlsi_13):
 	shll2	r0
-LOCAL(ashlsi3_29):
+LOCAL(ashlsi_12):
+LOCAL(ashlsi_11):
+	shll8	r0
+	rts
+LOCAL(ashlsi_21):
 	shll2	r0
-LOCAL(ashlsi3_27):
+LOCAL(ashlsi_20):
+LOCAL(ashlsi_19):
+	shll16	r0
+	rts
+LOCAL(ashlsi_28):
+LOCAL(ashlsi_27):
 	shll2	r0
-LOCAL(ashlsi3_25):
+LOCAL(ashlsi_26):
+LOCAL(ashlsi_25):
 	shll16	r0
+	rts
+	shll8	r0
+
+LOCAL(ashlsi_22):
+LOCAL(ashlsi_14):
+	shlr2	r0
+	rts
 	shll8	r0
+
+LOCAL(ashlsi_23):
+LOCAL(ashlsi_15):
+	shlr	r0
 	rts
-	shll	r0
+	shll8	r0
 
-LOCAL(ashlsi3_0):
+LOCAL(ashlsi_29):
+	shlr	r0
+LOCAL(ashlsi_30):
+	shlr2	r0
 	rts
-	nop
+	shll16	r0	
 
 	ENDFUNC(GLOBAL(ashlsi3))
+	ENDFUNC(GLOBAL(ashlsi3_r0))
 #endif
 
 #ifdef L_lshiftrt
 
 !
 ! GLOBAL(lshrsi3)
+! (For compatibility with older binaries, not used by compiler)
 !
 ! Entry:
-!
-! r4: Value to shift
-! r5: Shifts
+!	r4: Value to shift
+!	r5: Shift count
 !
 ! Exit:
-!
-! r0: Result
+!	r0: Result
 !
 ! Destroys:
+!	T bit
 !
-! (none)
 !
+! GLOBAL(lshrsi3_r0)
+!
+! Entry:
+!	r4: Value to shift
+!	r0: Shift count
+!
+! Exit:
+!	r0: Result
+!
+! Destroys:
+!	T bit
+
 	.global	GLOBAL(lshrsi3)
+	.global	GLOBAL(lshrsi3_r0)
 	HIDDEN_FUNC(GLOBAL(lshrsi3))
-	.align	2
+	HIDDEN_FUNC(GLOBAL(lshrsi3_r0))
 GLOBAL(lshrsi3):
-	mov	#31,r0
-	and	r0,r5
-	mova	LOCAL(lshrsi3_table),r0
-	mov.b	@(r0,r5),r5
+	mov	r5,r0
+	.align	2
+GLOBAL(lshrsi3_r0):
+
 #ifdef __sh1__
-	add	r5,r0
+	and	#31,r0
+	shll2	r0
+	mov.l	r4,@-r15
+	mov	r0,r4
+	mova	LOCAL(lshrsi3_table),r0
+	add	r4,r0
+	mov.l	@r15+,r4
 	jmp	@r0
+	mov	r4,r0
+	.align 2
 #else
-	braf	r5
-#endif
+	and	#31,r0
+	shll2	r0
+	braf	r0
 	mov	r4,r0
-
-	.align	2
+#endif
 LOCAL(lshrsi3_table):
-	.byte		LOCAL(lshrsi3_0)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_1)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_2)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_3)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_4)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_5)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_6)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_7)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_8)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_9)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_10)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_11)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_12)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_13)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_14)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_15)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_16)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_17)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_18)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_19)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_20)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_21)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_22)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_23)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_24)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_25)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_26)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_27)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_28)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_29)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_30)-LOCAL(lshrsi3_table)
-	.byte		LOCAL(lshrsi3_31)-LOCAL(lshrsi3_table)
-
-LOCAL(lshrsi3_6):
-	shlr2	r0
-LOCAL(lshrsi3_4):
-	shlr2	r0
-LOCAL(lshrsi3_2):
+	rts				// >> 0
+	nop
+LOCAL(lshrsi_1):			// >> 1
+	rts
+	shlr	r0
+LOCAL(lshrsi_2):			// >> 2
 	rts
 	shlr2	r0
-
-LOCAL(lshrsi3_7):
-	shlr2	r0
-LOCAL(lshrsi3_5):
+	bra	LOCAL(lshrsi_1)		// >> 3
 	shlr2	r0
-LOCAL(lshrsi3_3):
+	bra	LOCAL(lshrsi_2)		// >> 4
 	shlr2	r0
-LOCAL(lshrsi3_1):
-	rts
+	bra	LOCAL(lshrsi_5)		// >> 5
 	shlr	r0
-
-LOCAL(lshrsi3_14):
-	shlr2	r0
-LOCAL(lshrsi3_12):
-	shlr2	r0
-LOCAL(lshrsi3_10):
+	bra	LOCAL(lshrsi_6)		// >> 6
 	shlr2	r0
-LOCAL(lshrsi3_8):
+	bra	LOCAL(lshrsi_7)		// >> 7
+	shlr	r0
+LOCAL(lshrsi_8):			// >> 8
 	rts
 	shlr8	r0
-
-LOCAL(lshrsi3_15):
-	shlr2	r0
-LOCAL(lshrsi3_13):
+	bra	LOCAL(lshrsi_8)		// >> 9
+	shlr	r0
+	bra	LOCAL(lshrsi_8)		// >> 10
 	shlr2	r0
-LOCAL(lshrsi3_11):
+	bra	LOCAL(lshrsi_11)	// >> 11
+	shlr	r0
+	bra	LOCAL(lshrsi_12)	// >> 12
 	shlr2	r0
-LOCAL(lshrsi3_9):
+	bra	LOCAL(lshrsi_13)	// >> 13
+	shlr	r0
+	bra	LOCAL(lshrsi_14)	// >> 14
 	shlr8	r0
+	bra	LOCAL(lshrsi_15)	// >> 15
+	shlr8	r0
+LOCAL(lshrsi_16):			// >> 16
 	rts
+	shlr16	r0
+	bra	LOCAL(lshrsi_16)	// >> 17
 	shlr	r0
-
-LOCAL(lshrsi3_22):
+	bra	LOCAL(lshrsi_16)	// >> 18
 	shlr2	r0
-LOCAL(lshrsi3_20):
-	shlr2	r0
-LOCAL(lshrsi3_18):
+	bra	LOCAL(lshrsi_19)	// >> 19
+	shlr	r0
+	bra	LOCAL(lshrsi_20)	// >> 20
 	shlr2	r0
-LOCAL(lshrsi3_16):
-	rts
+	bra	LOCAL(lshrsi_21)	// >> 21
+	shlr	r0
+	bra	LOCAL(lshrsi_22)	// >> 22
 	shlr16	r0
-
-LOCAL(lshrsi3_23):
-	shlr2	r0
-LOCAL(lshrsi3_21):
+	bra	LOCAL(lshrsi_23)	// >> 23
+	shlr16	r0
+	bra	LOCAL(lshrsi_16)	// >> 24
+	shlr8	r0
+	bra	LOCAL(lshrsi_25)	// >> 25
+	shlr	r0
+	bra	LOCAL(lshrsi_26)	// >> 26
 	shlr2	r0
-LOCAL(lshrsi3_19):
+	bra	LOCAL(lshrsi_27)	// >> 27
+	shlr	r0
+	bra	LOCAL(lshrsi_28)	// >> 28
 	shlr2	r0
-LOCAL(lshrsi3_17):
+	bra	LOCAL(lshrsi_29)	// >> 29
 	shlr16	r0
+	bra	LOCAL(lshrsi_30)	// >> 30
+	shlr16	r0
+	shll	r0			// >> 31
 	rts
-	shlr	r0
+	movt	r0
 
-LOCAL(lshrsi3_30):
+LOCAL(lshrsi_7):
 	shlr2	r0
-LOCAL(lshrsi3_28):
+LOCAL(lshrsi_5):
+LOCAL(lshrsi_6):
 	shlr2	r0
-LOCAL(lshrsi3_26):
-	shlr2	r0
-LOCAL(lshrsi3_24):
-	shlr16	r0
 	rts
-	shlr8	r0
-
-LOCAL(lshrsi3_31):
+LOCAL(lshrsi_13):
 	shlr2	r0
-LOCAL(lshrsi3_29):
+LOCAL(lshrsi_12):
+LOCAL(lshrsi_11):
+	shlr8	r0
+	rts
+LOCAL(lshrsi_21):
 	shlr2	r0
-LOCAL(lshrsi3_27):
+LOCAL(lshrsi_20):
+LOCAL(lshrsi_19):
+	shlr16	r0
+	rts
+LOCAL(lshrsi_28):
+LOCAL(lshrsi_27):
 	shlr2	r0
-LOCAL(lshrsi3_25):
+LOCAL(lshrsi_26):
+LOCAL(lshrsi_25):
 	shlr16	r0
+	rts
+	shlr8	r0
+
+LOCAL(lshrsi_22):
+LOCAL(lshrsi_14):
+	shll2	r0
+	rts
 	shlr8	r0
+
+LOCAL(lshrsi_23):
+LOCAL(lshrsi_15):
+	shll	r0
 	rts
-	shlr	r0
+	shlr8	r0
 
-LOCAL(lshrsi3_0):
+LOCAL(lshrsi_29):
+	shll	r0
+LOCAL(lshrsi_30):
+	shll2	r0
 	rts
-	nop
+	shlr16	r0	
 
 	ENDFUNC(GLOBAL(lshrsi3))
+	ENDFUNC(GLOBAL(lshrsi3_r0))
 #endif
 
 #ifdef L_movmem