Resend the patch that addressed Will's comments.

fmod/fmodf and remainder/remainderf could be expanded instead of library
call when fast-math build, which is much faster.

fmodf:
     fdivs   f0,f1,f2
     friz    f0,f0
     fnmsubs f1,f2,f0,f1

remainderf:
     fdivs   f0,f1,f2
     frin    f0,f0
     fnmsubs f1,f2,f0,f1

SPEC2017 Ofast P8LE: 511.povray_r +1.14%,  526.blender_r +1.72%

gcc/ChangeLog:

2021-09-03  Xionghu Luo  <luo...@linux.ibm.com>

        PR target/97142
        * config/rs6000/rs6000.md (fmod<mode>3): New define_expand.
        (remainder<mode>3): Likewise.

gcc/testsuite/ChangeLog:

2021-09-03  Xionghu Luo  <luo...@linux.ibm.com>

        PR target/97142
        * gcc.target/powerpc/pr97142.c: New test.
---
 gcc/config/rs6000/rs6000.md                | 36 ++++++++++++++++++++++
 gcc/testsuite/gcc.target/powerpc/pr97142.c | 35 +++++++++++++++++++++
 2 files changed, 71 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/powerpc/pr97142.c

diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index c8cdc42533c..84820d3b5cb 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -4932,6 +4932,42 @@ (define_insn "fre<sd>"
   [(set_attr "type" "fp")
    (set_attr "isa" "*,<Fisa>")])
 
+(define_expand "fmod<mode>3"
+  [(use (match_operand:SFDF 0 "gpc_reg_operand"))
+       (use (match_operand:SFDF 1 "gpc_reg_operand"))
+       (use (match_operand:SFDF 2 "gpc_reg_operand"))]
+  "TARGET_HARD_FLOAT
+  && TARGET_FPRND
+  && flag_unsafe_math_optimizations"
+{
+  rtx div = gen_reg_rtx (<MODE>mode);
+  emit_insn (gen_div<mode>3 (div, operands[1], operands[2]));
+
+  rtx friz = gen_reg_rtx (<MODE>mode);
+  emit_insn (gen_btrunc<mode>2 (friz, div));
+
+  emit_insn (gen_nfms<mode>4 (operands[0], operands[2], friz, operands[1]));
+  DONE;
+ })
+
+(define_expand "remainder<mode>3"
+  [(use (match_operand:SFDF 0 "gpc_reg_operand"))
+       (use (match_operand:SFDF 1 "gpc_reg_operand"))
+       (use (match_operand:SFDF 2 "gpc_reg_operand"))]
+  "TARGET_HARD_FLOAT
+  && TARGET_FPRND
+  && flag_unsafe_math_optimizations"
+{
+  rtx div = gen_reg_rtx (<MODE>mode);
+  emit_insn (gen_div<mode>3 (div, operands[1], operands[2]));
+
+  rtx frin = gen_reg_rtx (<MODE>mode);
+  emit_insn (gen_round<mode>2 (frin, div));
+
+  emit_insn (gen_nfms<mode>4 (operands[0], operands[2], frin, operands[1]));
+  DONE;
+ })
+
 (define_insn "*rsqrt<mode>2"
   [(set (match_operand:SFDF 0 "gpc_reg_operand" "=<Ff>,wa")
        (unspec:SFDF [(match_operand:SFDF 1 "gpc_reg_operand" "<Ff>,wa")]
diff --git a/gcc/testsuite/gcc.target/powerpc/pr97142.c 
b/gcc/testsuite/gcc.target/powerpc/pr97142.c
new file mode 100644
index 00000000000..e5306eb681b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr97142.c
@@ -0,0 +1,35 @@
+/* { dg-do compile } */
+/* { dg-options "-Ofast" } */
+
+#include <math.h>
+
+float test1 (float x, float y)
+{
+  return fmodf (x, y);
+}
+
+double test2 (double x, double y)
+{
+  return fmod (x, y);
+}
+
+float test3 (float x, float y)
+{
+  return remainderf (x, y);
+}
+
+double test4 (double x, double y)
+{
+  return remainder (x, y);
+}
+
+/* { dg-final { scan-assembler-not {\mbl fmod\M} } } */
+/* { dg-final { scan-assembler-not {\mbl fmodf\M} } } */
+/* { dg-final { scan-assembler-not {\mbl remainder\M} } } */
+/* { dg-final { scan-assembler-not {\mbl remainderf\M} } } */
+/* { dg-final { scan-assembler-times {\mfdiv\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mfdivs\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mfnmsub\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mfnmsubs\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mfriz\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mfrin\M} 2 } } */
-- 
2.25.1

Reply via email to