about summary refs log tree commit diff
path: root/sysdeps/powerpc/powerpc32/fpu
diff options
context:
space:
mode:
authorAdhemerval Zanella <adhemerval.zanella@linaro.org>2016-12-16 19:13:14 +0000
committerAdhemerval Zanella <adhemerval.zanella@linaro.org>2016-12-27 17:42:09 -0200
commitcfee7d9cf403a1f801784c0d6f1d72994911d9d8 (patch)
tree7f22f5659670bcdbd1183a91de8169b15f5683a3 /sysdeps/powerpc/powerpc32/fpu
parentc32bb03c38d76cdc7147ce0441d5eac3ed576152 (diff)
downloadglibc-cfee7d9cf403a1f801784c0d6f1d72994911d9d8.tar.gz
glibc-cfee7d9cf403a1f801784c0d6f1d72994911d9d8.tar.xz
glibc-cfee7d9cf403a1f801784c0d6f1d72994911d9d8.zip
powerpc: Remove f{max,min}{f} assembly implementations
This patch removes the powerpc assembly implementation of fmax/fmin.
Based on benchtests, the assembly ones shows:

$ ./testrun.sh benchtests/bench-fmax
  "fmax": {
   "": {
    "duration": 5.07586e+09,
    "iterations": 2.01676e+09,
    "max": 1350.39,
    "min": 2.073,
    "mean": 2.51684
   },
   "qNaN": {
    "duration": 5.09315e+09,
    "iterations": 8.4568e+08,
    "max": 2788,
    "min": 5.806,
    "mean": 6.02255
   },
   "sNaN": {
    "duration": 5.09073e+09,
    "iterations": 8.42316e+08,
    "max": 4215.84,
    "min": 5.737,
    "mean": 6.04373
   }

And

$ ./testrun.sh benchtests/bench-fmin
  "fmin": {
   "": {
    "duration": 5.07711e+09,
    "iterations": 2.02982e+09,
    "max": 497.094,
    "min": 2.073,
    "mean": 2.50126
   },
   "qNaN": {
    "duration": 5.09134e+09,
    "iterations": 8.46968e+08,
    "max": 2255.14,
    "min": 5.807,
    "mean": 6.01125
   },
   "sNaN": {
    "duration": 5.09122e+09,
    "iterations": 8.4746e+08,
    "max": 1969.38,
    "min": 5.729,
    "mean": 6.00763
   }
  }

The default implementation (math/s_f{max.min}_template.c) shows slight better
latency for all cases:

$ ./testrun.sh benchtests/bench-fmax
  "fmax": {
   "": {
    "duration": 5.07044e+09,
    "iterations": 2.38695e+09,
    "max": 2048.58,
    "min": 2.073,
    "mean": 2.12423
   },
   "qNaN": {
    "duration": 5.09004e+09,
    "iterations": 9.45428e+08,
    "max": 3306.93,
    "min": 5.138,
    "mean": 5.38385
   },
   "sNaN": {
    "duration": 5.08458e+09,
    "iterations": 1.15959e+09,
    "max": 972.008,
    "min": 3.321,
    "mean": 4.3848
   }
  }

And:

$ ./testrun.sh benchtests/bench-fmin
  "fmin": {
   "": {
    "duration": 5.06817e+09,
    "iterations": 2.3913e+09,
    "max": 1177.9,
    "min": 2.073,
    "mean": 2.11942
   },
   "qNaN": {
    "duration": 5.08857e+09,
    "iterations": 9.45656e+08,
    "max": 2658.83,
    "min": 5.09,
    "mean": 5.38099
   },
   "sNaN": {
    "duration": 5.08093e+09,
    "iterations": 1.16725e+09,
    "max": 1030.74,
    "min": 3.323,
    "mean": 4.3529
   }
  }

Both were run with GCC 5.4 (ubuntu 16 default installation) using default
compiler flags on POWER8E 3.4GHz (powerpc64le-linux-gnu).
Diffstat (limited to 'sysdeps/powerpc/powerpc32/fpu')
-rw-r--r--sysdeps/powerpc/powerpc32/fpu/s_fmax.S5
-rw-r--r--sysdeps/powerpc/powerpc32/fpu/s_fmin.S5
2 files changed, 0 insertions, 10 deletions
diff --git a/sysdeps/powerpc/powerpc32/fpu/s_fmax.S b/sysdeps/powerpc/powerpc32/fpu/s_fmax.S
deleted file mode 100644
index 69735761ab..0000000000
--- a/sysdeps/powerpc/powerpc32/fpu/s_fmax.S
+++ /dev/null
@@ -1,5 +0,0 @@
-#include <math_ldbl_opt.h>
-#include <sysdeps/powerpc/fpu/s_fmax.S>
-#if LONG_DOUBLE_COMPAT(libm, GLIBC_2_1)
-compat_symbol (libm, __fmax, fmaxl, GLIBC_2_1)
-#endif
diff --git a/sysdeps/powerpc/powerpc32/fpu/s_fmin.S b/sysdeps/powerpc/powerpc32/fpu/s_fmin.S
deleted file mode 100644
index 6d4a0a946c..0000000000
--- a/sysdeps/powerpc/powerpc32/fpu/s_fmin.S
+++ /dev/null
@@ -1,5 +0,0 @@
-#include <math_ldbl_opt.h>
-#include <sysdeps/powerpc/fpu/s_fmin.S>
-#if LONG_DOUBLE_COMPAT(libm, GLIBC_2_1)
-compat_symbol (libm, __fmin, fminl, GLIBC_2_1)
-#endif