aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorsayle <sayle@138bc75d-0d04-0410-961f-82ee72b054a4>2003-06-15 13:32:31 +0000
committersayle <sayle@138bc75d-0d04-0410-961f-82ee72b054a4>2003-06-15 13:32:31 +0000
commit839151adeebaaf0dd12395ad390eb2dbcd955879 (patch)
tree373d2c373f5f8302c62429a4f3bfecb9e2795db6
parent53d487a4dd9bcfec13bde1738801328c18756a2d (diff)
* config/i386/i386.md (expsf2, expdf2, expxf2): New patterns to
implement exp, expf and expl built-ins as inline x87 intrinsics. (UNSPEC_FSCALE, UNSPEC_FRNDINT, UNSPEC_F2XM1): New unspecs to represent x87's fscale, frndint and f2xm1 insns respectively. (*fscale_sfxf3, *fscale_dfxf3, *fscale_xf3): New insn patterns to encode x87's "fscale" instruction followed by a pop. (*frndintxf2): New insn pattern for "frndint". (*f2xm1xf2): New insn pattern for "f2xm1". * reg-stack.c (subst_stack_regs_pat): Handle UNSPEC_FRNDINT and UNSPEC_F2XM1 like UNSPEC_{SIN,COS} and handle UNSPEC_FSCALE like UNSPEC_FPATAN. * gcc.dg/builtins-22.c: New test case. * gcc.dg/i386-387-1.c: Update to test exp. * gcc.dg/i386-387-2.c: Likewise. git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@67973 138bc75d-0d04-0410-961f-82ee72b054a4
-rw-r--r--gcc/ChangeLog15
-rw-r--r--gcc/config/i386/i386.md132
-rw-r--r--gcc/reg-stack.c3
-rw-r--r--gcc/testsuite/ChangeLog6
-rw-r--r--gcc/testsuite/gcc.dg/builtins-22.c12
-rw-r--r--gcc/testsuite/gcc.dg/i386-387-1.c2
-rw-r--r--gcc/testsuite/gcc.dg/i386-387-2.c2
7 files changed, 171 insertions, 1 deletions
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index e9ab9457cac..74fad5bc6cf 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,18 @@
+2003-06-15 Roger Sayle <roger@eyesopen.com>
+
+ * config/i386/i386.md (expsf2, expdf2, expxf2): New patterns to
+ implement exp, expf and expl built-ins as inline x87 intrinsics.
+ (UNSPEC_FSCALE, UNSPEC_FRNDINT, UNSPEC_F2XM1): New unspecs to
+ represent x87's fscale, frndint and f2xm1 insns respectively.
+ (*fscale_sfxf3, *fscale_dfxf3, *fscale_xf3): New insn patterns
+ to encode x87's "fscale" instruction followed by a pop.
+ (*frndintxf2): New insn pattern for "frndint".
+ (*f2xm1xf2): New insn pattern for "f2xm1".
+
+ * reg-stack.c (subst_stack_regs_pat): Handle UNSPEC_FRNDINT and
+ UNSPEC_F2XM1 like UNSPEC_{SIN,COS} and handle UNSPEC_FSCALE like
+ UNSPEC_FPATAN.
+
2003-06-15 Richard Kenner <kenner@vlsi1.ultra.nyu.edu>
* Makefile.in (stagefeedback-start): Use $(SUBDIRS) instead of
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index faf0e5a5b98..7ea02a7a7f9 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -113,9 +113,12 @@
; x87 Floating point
(UNSPEC_FPATAN 65)
(UNSPEC_FYL2X 66)
+ (UNSPEC_FSCALE 67)
+ (UNSPEC_FRNDINT 68)
+ (UNSPEC_F2XM1 69)
; REP instruction
- (UNSPEC_REP 67)
+ (UNSPEC_REP 75)
])
(define_constants
@@ -15725,6 +15728,133 @@
temp = standard_80387_constant_rtx (4); /* fldln2 */
emit_move_insn (operands[2], temp);
})
+
+(define_insn "*fscale_sfxf3"
+ [(parallel [(set (match_operand:SF 0 "register_operand" "=f")
+ (unspec:SF [(match_operand:XF 2 "register_operand" "0")
+ (match_operand:XF 1 "register_operand" "u")]
+ UNSPEC_FSCALE))
+ (clobber (match_dup 1))])]
+ "! TARGET_NO_FANCY_MATH_387 && TARGET_80387
+ && flag_unsafe_math_optimizations"
+ "fscale\;fstp\t%y1"
+ [(set_attr "type" "fpspc")
+ (set_attr "mode" "SF")])
+
+(define_insn "*fscale_dfxf3"
+ [(parallel [(set (match_operand:DF 0 "register_operand" "=f")
+ (unspec:DF [(match_operand:XF 2 "register_operand" "0")
+ (match_operand:XF 1 "register_operand" "u")]
+ UNSPEC_FSCALE))
+ (clobber (match_dup 1))])]
+ "! TARGET_NO_FANCY_MATH_387 && TARGET_80387
+ && flag_unsafe_math_optimizations"
+ "fscale\;fstp\t%y1"
+ [(set_attr "type" "fpspc")
+ (set_attr "mode" "DF")])
+
+(define_insn "*fscale_xf3"
+ [(parallel [(set (match_operand:XF 0 "register_operand" "=f")
+ (unspec:XF [(match_operand:XF 2 "register_operand" "0")
+ (match_operand:XF 1 "register_operand" "u")]
+ UNSPEC_FSCALE))
+ (clobber (match_dup 1))])]
+ "! TARGET_NO_FANCY_MATH_387 && TARGET_80387
+ && flag_unsafe_math_optimizations"
+ "fscale\;fstp\t%y1"
+ [(set_attr "type" "fpspc")
+ (set_attr "mode" "XF")])
+
+(define_insn "*frndintxf2"
+ [(set (match_operand:XF 0 "register_operand" "=f")
+ (unspec:XF [(match_operand:XF 1 "register_operand" "0")]
+ UNSPEC_FRNDINT))]
+ "! TARGET_NO_FANCY_MATH_387 && TARGET_80387
+ && flag_unsafe_math_optimizations"
+ "frndint"
+ [(set_attr "type" "fpspc")
+ (set_attr "mode" "XF")])
+
+(define_insn "*f2xm1xf2"
+ [(set (match_operand:XF 0 "register_operand" "=f")
+ (unspec:XF [(match_operand:XF 1 "register_operand" "0")]
+ UNSPEC_F2XM1))]
+ "! TARGET_NO_FANCY_MATH_387 && TARGET_80387
+ && flag_unsafe_math_optimizations"
+ "f2xm1"
+ [(set_attr "type" "fpspc")
+ (set_attr "mode" "XF")])
+
+(define_expand "expsf2"
+ [(set (match_dup 2)
+ (float_extend:XF (match_operand:SF 1 "register_operand" "")))
+ (set (match_dup 4) (mult:XF (match_dup 2) (match_dup 3)))
+ (set (match_dup 5) (unspec:XF [(match_dup 4)] UNSPEC_FRNDINT))
+ (set (match_dup 6) (minus:XF (match_dup 4) (match_dup 5)))
+ (set (match_dup 7) (unspec:XF [(match_dup 6)] UNSPEC_F2XM1))
+ (set (match_dup 9) (plus:XF (match_dup 7) (match_dup 8)))
+ (parallel [(set (match_operand:SF 0 "register_operand" "")
+ (unspec:SF [(match_dup 9) (match_dup 5)] UNSPEC_FSCALE))
+ (clobber (match_dup 5))])]
+ "! TARGET_NO_FANCY_MATH_387 && TARGET_80387
+ && flag_unsafe_math_optimizations"
+{
+ rtx temp;
+ int i;
+
+ for (i=2; i<10; i++)
+ operands[i] = gen_reg_rtx (XFmode);
+ temp = standard_80387_constant_rtx (5); /* fldl2e */
+ emit_move_insn (operands[3], temp);
+ emit_move_insn (operands[8], CONST1_RTX (XFmode)); /* fld1 */
+})
+
+(define_expand "expdf2"
+ [(set (match_dup 2)
+ (float_extend:XF (match_operand:DF 1 "register_operand" "")))
+ (set (match_dup 4) (mult:XF (match_dup 2) (match_dup 3)))
+ (set (match_dup 5) (unspec:XF [(match_dup 4)] UNSPEC_FRNDINT))
+ (set (match_dup 6) (minus:XF (match_dup 4) (match_dup 5)))
+ (set (match_dup 7) (unspec:XF [(match_dup 6)] UNSPEC_F2XM1))
+ (set (match_dup 9) (plus:XF (match_dup 7) (match_dup 8)))
+ (parallel [(set (match_operand:DF 0 "register_operand" "")
+ (unspec:DF [(match_dup 9) (match_dup 5)] UNSPEC_FSCALE))
+ (clobber (match_dup 5))])]
+ "! TARGET_NO_FANCY_MATH_387 && TARGET_80387
+ && flag_unsafe_math_optimizations"
+{
+ rtx temp;
+ int i;
+
+ for (i=2; i<10; i++)
+ operands[i] = gen_reg_rtx (XFmode);
+ temp = standard_80387_constant_rtx (5); /* fldl2e */
+ emit_move_insn (operands[3], temp);
+ emit_move_insn (operands[8], CONST1_RTX (XFmode)); /* fld1 */
+})
+
+(define_expand "expxf2"
+ [(set (match_dup 3) (mult:XF (match_operand:XF 1 "register_operand" "")
+ (match_dup 2)))
+ (set (match_dup 4) (unspec:XF [(match_dup 3)] UNSPEC_FRNDINT))
+ (set (match_dup 5) (minus:XF (match_dup 3) (match_dup 4)))
+ (set (match_dup 6) (unspec:XF [(match_dup 5)] UNSPEC_F2XM1))
+ (set (match_dup 8) (plus:XF (match_dup 6) (match_dup 7)))
+ (parallel [(set (match_operand:XF 0 "register_operand" "")
+ (unspec:XF [(match_dup 8) (match_dup 4)] UNSPEC_FSCALE))
+ (clobber (match_dup 4))])]
+ "! TARGET_NO_FANCY_MATH_387 && TARGET_80387
+ && flag_unsafe_math_optimizations"
+{
+ rtx temp;
+ int i;
+
+ for (i=2; i<9; i++)
+ operands[i] = gen_reg_rtx (XFmode);
+ temp = standard_80387_constant_rtx (5); /* fldl2e */
+ emit_move_insn (operands[2], temp);
+ emit_move_insn (operands[7], CONST1_RTX (XFmode)); /* fld1 */
+})
;; Block operation instructions
diff --git a/gcc/reg-stack.c b/gcc/reg-stack.c
index 6efea36d6dc..5b3a359d606 100644
--- a/gcc/reg-stack.c
+++ b/gcc/reg-stack.c
@@ -1711,6 +1711,8 @@ subst_stack_regs_pat (insn, regstack, pat)
{
case UNSPEC_SIN:
case UNSPEC_COS:
+ case UNSPEC_FRNDINT:
+ case UNSPEC_F2XM1:
/* These insns only operate on the top of the stack. */
src1 = get_true_reg (&XVECEXP (pat_src, 0, 0));
@@ -1734,6 +1736,7 @@ subst_stack_regs_pat (insn, regstack, pat)
case UNSPEC_FPATAN:
case UNSPEC_FYL2X:
+ case UNSPEC_FSCALE:
/* These insns operate on the top two stack slots. */
src1 = get_true_reg (&XVECEXP (pat_src, 0, 0));
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 5c2b747b719..4371663f1a5 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,9 @@
+2003-06-15 Roger Sayle <roger@eyesopen.com>
+
+ * gcc.dg/builtins-22.c: New test case.
+ * gcc.dg/i386-387-1.c: Update to test exp.
+ * gcc.dg/i386-387-2.c: Likewise.
+
2003-06-13 Kaveh R. Ghazi <ghazi@caip.rutgers.edu>
* gcc.dg/format/asm_fprintf-1.c: Update width/precision checks.
diff --git a/gcc/testsuite/gcc.dg/builtins-22.c b/gcc/testsuite/gcc.dg/builtins-22.c
new file mode 100644
index 00000000000..916890b4094
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/builtins-22.c
@@ -0,0 +1,12 @@
+/* Related to PR optimization/10764 */
+
+/* { dg-do compile } */
+/* { dg-options "-O2 -ffast-math" } */
+
+double exp(double x);
+
+double foo(double x)
+{
+ return exp(exp(x));
+}
+
diff --git a/gcc/testsuite/gcc.dg/i386-387-1.c b/gcc/testsuite/gcc.dg/i386-387-1.c
index 07389106f50..79d25e2432e 100644
--- a/gcc/testsuite/gcc.dg/i386-387-1.c
+++ b/gcc/testsuite/gcc.dg/i386-387-1.c
@@ -6,9 +6,11 @@
/* { dg-final { scan-assembler "call\t_?sqrt" } } */
/* { dg-final { scan-assembler "call\t_?atan2" } } */
/* { dg-final { scan-assembler "call\t_?log" } } */
+/* { dg-final { scan-assembler "call\t_?exp" } } */
double f1(double x) { return __builtin_sin(x); }
double f2(double x) { return __builtin_cos(x); }
double f3(double x) { return __builtin_sqrt(x); }
double f4(double x, double y) { return __builtin_atan2(x,y); }
double f5(double x) { return __builtin_log(x); }
+double f6(double x) { return __builtin_exp(x); }
diff --git a/gcc/testsuite/gcc.dg/i386-387-2.c b/gcc/testsuite/gcc.dg/i386-387-2.c
index 3bebc758f2a..bfda85bc171 100644
--- a/gcc/testsuite/gcc.dg/i386-387-2.c
+++ b/gcc/testsuite/gcc.dg/i386-387-2.c
@@ -6,9 +6,11 @@
/* { dg-final { scan-assembler "fsqrt" } } */
/* { dg-final { scan-assembler "fpatan" } } */
/* { dg-final { scan-assembler "fyl2x" } } */
+/* { dg-final { scan-assembler "f2xm1" } } */
double f1(double x) { return __builtin_sin(x); }
double f2(double x) { return __builtin_cos(x); }
double f3(double x) { return __builtin_sqrt(x); }
double f4(double x, double y) { return __builtin_atan2(x,y); }
double f5(double x) { return __builtin_log(x); }
+double f6(double x) { return __builtin_exp(x); }