This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
[PATCH 23/28] benchtests: hypot benchmark
- From: Adhemerval Zanella <adhemerval dot zanella at linaro dot org>
- To: libc-alpha at sourceware dot org
- Date: Fri, 29 Mar 2019 10:35:24 -0300
- Subject: [PATCH 23/28] benchtests: hypot benchmark
- References: <20190329133529.22523-1-adhemerval.zanella@linaro.org>
Inputs are based on argument reductions from generic and powerpc
implementation.
Checked on powerpc-linux-gnu (built without --with-cpu, with
--with-cpu=power4 and with --with-cpu=power5+ and --disable-multi-arch),
powerpc64-linux-gnu (built without --with-cp and with --with-cpu=power5+
and --disable-multi-arch).
* benchtests/Makefile (bench-math): Add hypot.
* benchtests/hypot-inputs: New file.
---
benchtests/Makefile | 2 +-
benchtests/hypot-inputs | 16 ++++++++++++++++
2 files changed, 17 insertions(+), 1 deletion(-)
create mode 100644 benchtests/hypot-inputs
diff --git a/benchtests/Makefile b/benchtests/Makefile
index 42bf13b27f..013653588e 100644
--- a/benchtests/Makefile
+++ b/benchtests/Makefile
@@ -24,7 +24,7 @@ include ../Makeconfig
bench-math := acos acosh asin asinh atan atanh cos cosh exp exp2 log log2 \
modf pow rint sin sincos sinh sqrt tan tanh fmin fmax fminf \
fmaxf powf trunc truncf expf exp2f logf log2f sincosf sinf \
- cosf isnan isinf isfinite
+ cosf isnan isinf isfinite hypot
bench-pthread := pthread_once thread_create
diff --git a/benchtests/hypot-inputs b/benchtests/hypot-inputs
new file mode 100644
index 0000000000..e987e5dd1b
--- /dev/null
+++ b/benchtests/hypot-inputs
@@ -0,0 +1,16 @@
+## includes: math.h
+## args: double:double
+## ret: double
+
+## name: overflow
+0x3.ffffffffffffcp-1024, 0x8p-152
+## name: higher_two500
+0x1.000002027941dp+500, 0x1.0000000000001p+500
+## name: subnormal
+0x0.fffffffffffffp-1022, 0x0.fffffffffffffp-1022
+## name: less_two500
+0x1.fffffffffffffp-501, 0x1.fffffffffffffp-501
+
+## name: default
+3.0 , 4.0
+5.0 , 4.0
--
2.17.1