mirror of git://sourceware.org/git/glibc.git
79bfbc93de
The generic implementation is slight more optimized than the powerpc one, where it has a more optimized inf/nan check (by not using FP unit checks, along with branch prediction hints), and removed one branch by issuing trunc instead of a combination of floor/ceil (which also generated less code). On power10 with gcc 14.2.1: reciprocal-throughput master patch difference workload-0_1 1.1351 0.9067 20.12% workload-1_maxint 1.4230 0.9040 36.47% workload-maxint_maxfloat 1.5038 0.9076 39.65% workload-integral 1.1280 0.9111 19.23% latency master patch difference workload-0_1 1.1440 2.7117 -137.03% workload-1_maxint 4.0556 2.7070 33.25% workload-maxint_maxfloat 3.2122 2.7164 15.43% workload-integral 3.2381 2.7281 15.75% Checked on powerpc64le-linux-gnu. Reviewed-by: Sachin Monga <smonga@linux.ibm.com> |
||
|---|---|---|
| .. | ||
| bits | ||
| fpu | ||
| nofpu | ||
| nptl | ||
| power4 | ||
| power6 | ||
| powerpc32 | ||
| powerpc64 | ||
| sys/platform | ||
| Makefile | ||
| Versions | ||
| abort-instr.h | ||
| atomic-machine.h | ||
| dl-diagnostics-cpu.c | ||
| dl-lookupcfg.h | ||
| dl-procinfo.c | ||
| dl-tls.c | ||
| dl-tls.h | ||
| dl-tunables.list | ||
| elf-initfini.h | ||
| fpu_control.h | ||
| gccframe.h | ||
| hwcapinfo.c | ||
| hwcapinfo.h | ||
| ifunc-sel.h | ||
| jmpbuf-offsets.h | ||
| jmpbuf-unwind.h | ||
| ldsodefs.h | ||
| libc-tls.c | ||
| locale-defines.sym | ||
| longjmp.c | ||
| machine-gmon.h | ||
| math-tests-snan-cast.h | ||
| math-use-builtins-ffs.h | ||
| mod-cache-ppc.c | ||
| mod-tlsopt-powerpc.c | ||
| mp_clz_tab.c | ||
| novmx-longjmp.c | ||
| novmx-sigjmp.c | ||
| novmxsetjmp.h | ||
| preconfigure | ||
| preconfigure.ac | ||
| rtld-global-offsets.sym | ||
| sigjmp.c | ||
| sotruss-lib.c | ||
| string-fza.h | ||
| sysdep.h | ||
| test-arith.c | ||
| test-arithf.c | ||
| test-get_hwcap-static.c | ||
| test-get_hwcap.c | ||
| test-gettimebase.c | ||
| thread_pointer.h | ||
| tst-cache-ppc-static-dlopen.c | ||
| tst-cache-ppc-static.c | ||
| tst-cache-ppc.c | ||
| tst-set_ppr.c | ||
| tst-stack-align.h | ||
| tst-tlsifunc-static.c | ||
| tst-tlsifunc.c | ||
| tst-tlsopt-powerpc.c | ||
| utmp-size.h | ||