This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
[SH] PR 49880 - Fix some more -mdiv option issues
- From: Oleg Endo <oleg dot endo at t-online dot de>
- To: gcc-patches <gcc-patches at gcc dot gnu dot org>
- Date: Wed, 13 Mar 2013 01:22:06 +0100
- Subject: [SH] PR 49880 - Fix some more -mdiv option issues
Hi,
Initially I just wanted to simplify two lines as mentioned in the PR.
However, when I started writing the test cases a small can of worms
popped up.
'-m4 -mdiv=call-div1' would not link on bare metal configs because of
missing functions in libgcc, '-m2a -mdiv=call-fp' would ICE and/or not
link and '*-nofpu -mdiv=call-fp' would invoke library functions that use
the FPU.
I've also run across some confusions regarding TARGET_FPU_SINGLE and
friends, but I'm leaving a better cleanup for 4.9. Basically it's not
possible to distinguish between -m4-nofpu and -m4-single-only, because
there are no corresponding bits. Thus the two new mask bits in sh.opt,
which required converting some of the existing mask bit into a var, as
we already ran out of bits once in the past.
The attached patch should make the -mdiv= option work as it is described
in the documentation (which I updated recently as part of PR 56529).
Tested with 'make all' and
make -k check-gcc RUNTESTFLAGS="sh.exp=pr49880* --target_board=sh-sim
\{-m2,-m2a,-m2a-nofpu,-m2a-single,-m2a-single-only,-m3,-m3e,-m4,-m4-single,
-m4-single-only,-m4a,-m4a-single,-m4a-single-only}"
OK for 4.8 and 4.7?
Cheers,
Oleg
gcc/ChangeLog:
PR target/49880
* config/sh/sh.opt (FPU_SINGLE_ONLY): New mask.
(musermode): Convert to Var(TARGET_USERMODE).
* config/sh/sh.h (SELECT_SH2A_SINGLE_ONLY,
SELECT_SH4_SINGLE_ONLY, MASK_ARCH): Add MASK_FPU_SINGLE_ONLY.
* config/sh/sh.c (sh_option_override): Use
TARGET_FPU_DOUBLE || TARGET_FPU_SINGLE_ONLY for call-fp case.
* config/sh/sh.md (udivsi3_i1, divsi3_i1): Remove ! TARGET_SH4
condition.
(udivsi3_i4, divsi3_i4): Use TARGET_FPU_DOUBLE condition instead
of TARGET_SH4.
(udivsi3_i4_single, divsi3_i4_single): Use
TARGET_FPU_SINGLE_ONLY || TARGET_FPU_DOUBLE instead of
TARGET_HARD_SH4.
libgcc/ChangeLog:
PR target/49880
* config/sh/lib1funcs.S (sdivsi3_i4, udivsi3_i4): Enable for
SH2A.
(sdivsi3, udivsi3): Remove SH4 check and always compile these
functions.
testsuite/ChangeLog:
PR target/49880
* testsuite/gcc.target/sh/pr49880-1.c: New.
* testsuite/gcc.target/sh/pr49880-2.c: New.
* testsuite/gcc.target/sh/pr49880-3.c: New.
* testsuite/gcc.target/sh/pr49880-4.c: New.
* testsuite/gcc.target/sh/pr49880-5.c: New.
Index: gcc/config/sh/sh.md
===================================================================
--- gcc/config/sh/sh.md (revision 196589)
+++ gcc/config/sh/sh.md (working copy)
@@ -2154,7 +2154,7 @@
(clobber (reg:SI PR_REG))
(clobber (reg:SI R4_REG))
(use (match_operand:SI 1 "arith_reg_operand" "r"))]
- "TARGET_SH1 && (! TARGET_SH4 || TARGET_DIVIDE_CALL_DIV1)"
+ "TARGET_SH1 && TARGET_DIVIDE_CALL_DIV1"
"jsr @%1%#"
[(set_attr "type" "sfunc")
(set_attr "needs_delay_slot" "yes")])
@@ -2217,7 +2217,7 @@
(clobber (reg:SI R5_REG))
(use (reg:PSI FPSCR_REG))
(use (match_operand:SI 1 "arith_reg_operand" "r"))]
- "TARGET_SH4 && ! TARGET_FPU_SINGLE"
+ "TARGET_FPU_DOUBLE && ! TARGET_FPU_SINGLE"
"jsr @%1%#"
[(set_attr "type" "sfunc")
(set_attr "fp_mode" "double")
@@ -2236,7 +2236,8 @@
(clobber (reg:SI R4_REG))
(clobber (reg:SI R5_REG))
(use (match_operand:SI 1 "arith_reg_operand" "r"))]
- "(TARGET_HARD_SH4 || TARGET_SHCOMPACT) && TARGET_FPU_SINGLE"
+ "(TARGET_FPU_SINGLE_ONLY || TARGET_FPU_DOUBLE || TARGET_SHCOMPACT)
+ && TARGET_FPU_SINGLE"
"jsr @%1%#"
[(set_attr "type" "sfunc")
(set_attr "needs_delay_slot" "yes")])
@@ -2358,7 +2359,7 @@
(clobber (reg:SI R2_REG))
(clobber (reg:SI R3_REG))
(use (match_operand:SI 1 "arith_reg_operand" "r"))]
- "TARGET_SH1 && (! TARGET_SH4 || TARGET_DIVIDE_CALL_DIV1)"
+ "TARGET_SH1 && TARGET_DIVIDE_CALL_DIV1"
"jsr @%1%#"
[(set_attr "type" "sfunc")
(set_attr "needs_delay_slot" "yes")])
@@ -2487,7 +2488,7 @@
(clobber (reg:DF DR2_REG))
(use (reg:PSI FPSCR_REG))
(use (match_operand:SI 1 "arith_reg_operand" "r"))]
- "TARGET_SH4 && ! TARGET_FPU_SINGLE"
+ "TARGET_FPU_DOUBLE && ! TARGET_FPU_SINGLE"
"jsr @%1%#"
[(set_attr "type" "sfunc")
(set_attr "fp_mode" "double")
@@ -2501,7 +2502,8 @@
(clobber (reg:DF DR2_REG))
(clobber (reg:SI R2_REG))
(use (match_operand:SI 1 "arith_reg_operand" "r"))]
- "(TARGET_HARD_SH4 || TARGET_SHCOMPACT) && TARGET_FPU_SINGLE"
+ "(TARGET_FPU_SINGLE_ONLY || TARGET_FPU_DOUBLE || TARGET_SHCOMPACT)
+ && TARGET_FPU_SINGLE"
"jsr @%1%#"
[(set_attr "type" "sfunc")
(set_attr "needs_delay_slot" "yes")])
Index: gcc/config/sh/sh.opt
===================================================================
--- gcc/config/sh/sh.opt (revision 196589)
+++ gcc/config/sh/sh.opt (working copy)
@@ -24,6 +24,10 @@
;; Set if the default precision of th FPU is single.
Mask(FPU_SINGLE)
+;; Set if the a double-precision FPU is present but is restricted to
+;; single precision usage only.
+Mask(FPU_SINGLE_ONLY)
+
;; Set if we should generate code using type 2A insns.
Mask(HARD_SH2A)
@@ -339,7 +343,7 @@
Cost to assume for a multiply insn
musermode
-Target Report RejectNegative Mask(USERMODE)
+Target Report RejectNegative Var(TARGET_USERMODE)
Don't generate privileged-mode only code; implies -mno-inline-ic_invalidate if the inline code would not work in user mode.
;; We might want to enable this by default for TARGET_HARD_SH4, because
Index: gcc/config/sh/sh.c
===================================================================
--- gcc/config/sh/sh.c (revision 196589)
+++ gcc/config/sh/sh.c (working copy)
@@ -816,8 +816,7 @@
if (! strcmp (sh_div_str, "call-div1"))
sh_div_strategy = SH_DIV_CALL_DIV1;
else if (! strcmp (sh_div_str, "call-fp")
- && (TARGET_FPU_DOUBLE
- || (TARGET_HARD_SH4 && TARGET_SH2E)
+ && (TARGET_FPU_DOUBLE || TARGET_FPU_SINGLE_ONLY
|| (TARGET_SHCOMPACT && TARGET_FPU_ANY)))
sh_div_strategy = SH_DIV_CALL_FP;
else if (! strcmp (sh_div_str, "call-table") && TARGET_DYNSHIFT)
Index: gcc/config/sh/sh.h
===================================================================
--- gcc/config/sh/sh.h (revision 196589)
+++ gcc/config/sh/sh.h (working copy)
@@ -138,14 +138,16 @@
| MASK_SH2 | MASK_SH1)
#define SELECT_SH2A_NOFPU (MASK_HARD_SH2A | MASK_SH2 | MASK_SH1)
#define SELECT_SH2A_SINGLE_ONLY (MASK_SH_E | MASK_HARD_SH2A | MASK_SH2 \
- | MASK_SH1 | MASK_FPU_SINGLE)
+ | MASK_SH1 | MASK_FPU_SINGLE \
+ | MASK_FPU_SINGLE_ONLY)
#define SELECT_SH2A_SINGLE (MASK_SH_E | MASK_HARD_SH2A \
| MASK_FPU_SINGLE | MASK_HARD_SH2A_DOUBLE \
| MASK_SH2 | MASK_SH1)
#define SELECT_SH3 (MASK_SH3 | SELECT_SH2)
#define SELECT_SH3E (MASK_SH_E | MASK_FPU_SINGLE | SELECT_SH3)
#define SELECT_SH4_NOFPU (MASK_HARD_SH4 | SELECT_SH3)
-#define SELECT_SH4_SINGLE_ONLY (MASK_HARD_SH4 | SELECT_SH3E)
+#define SELECT_SH4_SINGLE_ONLY (MASK_HARD_SH4 | SELECT_SH3E \
+ | MASK_FPU_SINGLE_ONLY)
#define SELECT_SH4 (MASK_SH4 | MASK_SH_E | MASK_HARD_SH4 \
| SELECT_SH3)
#define SELECT_SH4_SINGLE (MASK_FPU_SINGLE | SELECT_SH4)
@@ -212,7 +214,8 @@
/* Reset all target-selection flags. */
#define MASK_ARCH (MASK_SH1 | MASK_SH2 | MASK_SH3 | MASK_SH_E | MASK_SH4 \
| MASK_HARD_SH2A | MASK_HARD_SH2A_DOUBLE | MASK_SH4A \
- | MASK_HARD_SH4 | MASK_FPU_SINGLE | MASK_SH5)
+ | MASK_HARD_SH4 | MASK_FPU_SINGLE | MASK_SH5 \
+ | MASK_FPU_SINGLE_ONLY)
/* This defaults us to big-endian. */
#ifndef TARGET_ENDIAN_DEFAULT
Index: gcc/testsuite/gcc.target/sh/pr49880-4.c
===================================================================
--- gcc/testsuite/gcc.target/sh/pr49880-4.c (revision 0)
+++ gcc/testsuite/gcc.target/sh/pr49880-4.c (revision 0)
@@ -0,0 +1,19 @@
+/* Check that the option -mdiv=call-fp does not produce calls to the
+ library function that uses FPU to implement integer division if FPU insns
+ are not supported or are disabled. */
+/* { dg-do compile { target "sh*-*-*" } } */
+/* { dg-options "-mdiv=call-fp" } */
+/* { dg-skip-if "" { "sh*-*-*" } { "*"} { "-m1" "-m2" "-m3" "-m4al" "*nofpu" "-m4-340*" "-m4-400*" "-m4-500*" } } */
+/* { dg-final { scan-assembler-not "sdivsi3_i4\n|udivsi3_i4\n" } } */
+
+int
+test00 (int a, int b)
+{
+ return a / b;
+}
+
+unsigned int
+test01 (unsigned int a, unsigned b)
+{
+ return a / b;
+}
Index: gcc/testsuite/gcc.target/sh/pr49880-1.c
===================================================================
--- gcc/testsuite/gcc.target/sh/pr49880-1.c (revision 0)
+++ gcc/testsuite/gcc.target/sh/pr49880-1.c (revision 0)
@@ -0,0 +1,22 @@
+/* Check that the option -mdiv=call-div1 works. */
+/* { dg-do link { target "sh*-*-*" } } */
+/* { dg-options "-mdiv=call-div1" } */
+/* { dg-skip-if "" { "sh*-*-*" } { "-m5*"} { "" } } */
+
+int
+test00 (int a, int b)
+{
+ return a / b;
+}
+
+unsigned int
+test01 (unsigned int a, unsigned b)
+{
+ return a / b;
+}
+
+int
+main (int argc, char** argv)
+{
+ return test00 (argc, 123) + test01 (argc, 123);
+}
Index: gcc/testsuite/gcc.target/sh/pr49880-5.c
===================================================================
--- gcc/testsuite/gcc.target/sh/pr49880-5.c (revision 0)
+++ gcc/testsuite/gcc.target/sh/pr49880-5.c (revision 0)
@@ -0,0 +1,19 @@
+/* Check that the option -mdiv=call-fp results in the corresponding library
+ function calls on targets that have a double precision FPU. */
+/* { dg-do compile { target "sh*-*-*" } } */
+/* { dg-options "-mdiv=call-fp" } */
+/* { dg-skip-if "" { "sh*-*-*" } { "*"} { "-m2a" "-m4" "-m4a" "*single-only" } } */
+/* { dg-final { scan-assembler "sdivsi3_i4\n" } } */
+/* { dg-final { scan-assembler "udivsi3_i4\n" } } */
+
+int
+test00 (int a, int b)
+{
+ return a / b;
+}
+
+unsigned int
+test01 (unsigned int a, unsigned b)
+{
+ return a / b;
+}
Index: gcc/testsuite/gcc.target/sh/pr49880-2.c
===================================================================
--- gcc/testsuite/gcc.target/sh/pr49880-2.c (revision 0)
+++ gcc/testsuite/gcc.target/sh/pr49880-2.c (revision 0)
@@ -0,0 +1,22 @@
+/* Check that the option -mdiv=call-fp works. */
+/* { dg-do link { target "sh*-*-*" } } */
+/* { dg-options "-mdiv=call-fp" } */
+/* { dg-skip-if "" { "sh*-*-*" } { "-m5*"} { "" } } */
+
+int
+test00 (int a, int b)
+{
+ return a / b;
+}
+
+unsigned int
+test01 (unsigned int a, unsigned b)
+{
+ return a / b;
+}
+
+int
+main (int argc, char** argv)
+{
+ return test00 (argc, 123) + test01 (argc, 123);
+}
Index: gcc/testsuite/gcc.target/sh/pr49880-3.c
===================================================================
--- gcc/testsuite/gcc.target/sh/pr49880-3.c (revision 0)
+++ gcc/testsuite/gcc.target/sh/pr49880-3.c (revision 0)
@@ -0,0 +1,22 @@
+/* Check that the option -mdiv=call-table works. */
+/* { dg-do link { target "sh*-*-*" } } */
+/* { dg-options "-mdiv=call-table" } */
+/* { dg-skip-if "" { "sh*-*-*" } { "-m5*"} { "" } } */
+
+int
+test00 (int a, int b)
+{
+ return a / b;
+}
+
+unsigned int
+test01 (unsigned int a, unsigned b)
+{
+ return a / b;
+}
+
+int
+main (int argc, char** argv)
+{
+ return test00 (argc, 123) + test01 (argc, 123);
+}
Index: libgcc/config/sh/lib1funcs.S
===================================================================
--- libgcc/config/sh/lib1funcs.S (revision 196589)
+++ libgcc/config/sh/lib1funcs.S (working copy)
@@ -1006,7 +1006,7 @@
#ifdef L_sdivsi3_i4
.title "SH DIVIDE"
!! 4 byte integer Divide code for the Renesas SH
-#ifdef __SH4__
+#if defined (__SH4__) || defined (__SH2A__)
!! args in r4 and r5, result in fpul, clobber dr0, dr2
.global GLOBAL(sdivsi3_i4)
@@ -1021,7 +1021,7 @@
ftrc dr0,fpul
ENDFUNC(GLOBAL(sdivsi3_i4))
-#elif defined(__SH4_SINGLE__) || defined(__SH4_SINGLE_ONLY__) || (defined (__SH5__) && ! defined __SH4_NOFPU__)
+#elif defined (__SH2A_SINGLE__) || defined (__SH2A_SINGLE_ONLY__) || defined(__SH4_SINGLE__) || defined(__SH4_SINGLE_ONLY__) || (defined (__SH5__) && ! defined __SH4_NOFPU__)
!! args in r4 and r5, result in fpul, clobber r2, dr0, dr2
#if ! __SH5__ || __SH5__ == 32
@@ -1046,13 +1046,12 @@
ENDFUNC(GLOBAL(sdivsi3_i4))
#endif /* ! __SH5__ || __SH5__ == 32 */
-#endif /* ! __SH4__ */
+#endif /* ! __SH4__ || __SH2A__ */
#endif
#ifdef L_sdivsi3
/* __SH4_SINGLE_ONLY__ keeps this part for link compatibility with
sh2e/sh3e code. */
-#if (! defined(__SH4__) && ! defined (__SH4_SINGLE__)) || defined (__linux__)
!!
!! Steve Chamberlain
!! sac@cygnus.com
@@ -1369,13 +1368,12 @@
ENDFUNC(GLOBAL(sdivsi3))
#endif /* ! __SHMEDIA__ */
-#endif /* ! __SH4__ */
#endif
#ifdef L_udivsi3_i4
.title "SH DIVIDE"
!! 4 byte integer Divide code for the Renesas SH
-#ifdef __SH4__
+#if defined (__SH4__) || defined (__SH2A__)
!! args in r4 and r5, result in fpul, clobber r0, r1, r4, r5, dr0, dr2, dr4,
!! and t bit
@@ -1417,7 +1415,7 @@
.double 2147483648
ENDFUNC(GLOBAL(udivsi3_i4))
-#elif defined (__SH5__) && ! defined (__SH4_NOFPU__)
+#elif defined (__SH5__) && ! defined (__SH4_NOFPU__) && ! defined (__SH2A_NOFPU__)
#if ! __SH5__ || __SH5__ == 32
!! args in r4 and r5, result in fpul, clobber r20, r21, dr0, fr33
.mode SHmedia
@@ -1438,7 +1436,7 @@
ENDFUNC(GLOBAL(udivsi3_i4))
#endif /* ! __SH5__ || __SH5__ == 32 */
-#elif defined(__SH4_SINGLE__) || defined(__SH4_SINGLE_ONLY__)
+#elif defined (__SH2A_SINGLE__) || defined (__SH2A_SINGLE_ONLY__) || defined(__SH4_SINGLE__) || defined(__SH4_SINGLE_ONLY__)
!! args in r4 and r5, result in fpul, clobber r0, r1, r4, r5, dr0, dr2, dr4
.global GLOBAL(udivsi3_i4)
@@ -1493,7 +1491,6 @@
#ifdef L_udivsi3
/* __SH4_SINGLE_ONLY__ keeps this part for link compatibility with
sh2e/sh3e code. */
-#if (! defined(__SH4__) && ! defined (__SH4_SINGLE__)) || defined (__linux__)
!! args in r4 and r5, result in r0, clobbers r4, pr, and t bit
.global GLOBAL(udivsi3)
@@ -1688,7 +1685,6 @@
ENDFUNC(GLOBAL(udivsi3))
#endif /* ! __SHMEDIA__ */
-#endif /* __SH4__ */
#endif /* L_udivsi3 */
#ifdef L_udivdi3