diff options
author | Joseph Myers <joseph@codesourcery.com> | 2018-05-16 00:05:28 +0000 |
---|---|---|
committer | Joseph Myers <joseph@codesourcery.com> | 2018-05-16 00:05:28 +0000 |
commit | 69a01461ee1417578d2ba20aac935828b50f1118 (patch) | |
tree | 1801dbdbca57e3e1ce053aec41e83938d2d19e06 /math/math-narrow.h | |
parent | a15529fda8d132621328c3fe32997a3d9c55aef4 (diff) | |
download | glibc-69a01461ee1417578d2ba20aac935828b50f1118.tar.gz glibc-69a01461ee1417578d2ba20aac935828b50f1118.tar.xz glibc-69a01461ee1417578d2ba20aac935828b50f1118.zip |
Add narrowing multiply functions.
This patch adds the narrowing multiply functions from TS 18661-1 to glibc's libm: fmul, fmull, dmull, f32mulf64, f32mulf32x, f32xmulf64 for all configurations; f32mulf64x, f32mulf128, f64mulf64x, f64mulf128, f32xmulf64x, f32xmulf128, f64xmulf128 for configurations with _Float64x and _Float128; __nldbl_dmull for ldbl-opt. The changes are mostly essentially the same as for the narrowing add functions, so the description of those generally applies to this patch as well. f32xmulf64 for i386 cannot use precision control as used for add and subtract, because that would result in double rounding for subnormal results, so that uses round-to-odd with long double intermediate result instead. The soft-fp support involves adding a new FP_TRUNC_COOKED since soft-fp multiplication uses cooked inputs and outputs. Tested for x86_64, x86, mips64 (all three ABIs, both hard and soft float) and powerpc, and with build-many-glibcs.py. * math/Makefile (libm-narrow-fns): Add mul. (libm-test-funcs-narrow): Likewise. * math/Versions (GLIBC_2.28): Add narrowing multiply functions. * math/bits/mathcalls-narrow.h (mul): Use __MATHCALL_NARROW. * math/gen-auto-libm-tests.c (test_functions): Add mul. * math/math-narrow.h (CHECK_NARROW_MUL): New macro. (NARROW_MUL_ROUND_TO_ODD): Likewise. (NARROW_MUL_TRIVIAL): Likewise. * soft-fp/op-common.h (FP_TRUNC_COOKED): Likewise. * sysdeps/ieee754/float128/float128_private.h (__fmull): New macro. (__dmull): Likewise. * sysdeps/ieee754/ldbl-opt/Makefile (libnldbl-calls): Add fmul and dmul. (CFLAGS-nldbl-dmul.c): New variable. (CFLAGS-nldbl-fmul.c): Likewise. * sysdeps/ieee754/ldbl-opt/Versions (GLIBC_2.28): Add __nldbl_dmull. * sysdeps/ieee754/ldbl-opt/nldbl-compat.h (__nldbl_dmull): New prototype. * manual/arith.texi (Misc FP Arithmetic): Document fmul, fmull, dmull, fMmulfN, fMmulfNx, fMxmulfN and fMxmulfNx. * math/auto-libm-test-in: Add tests of mul. * math/auto-libm-test-out-narrow-mul: New generated file. * math/libm-test-narrow-mul.inc: New file. * sysdeps/i386/fpu/s_f32xmulf64.c: Likewise. * sysdeps/ieee754/dbl-64/s_f32xmulf64.c: Likewise. * sysdeps/ieee754/dbl-64/s_fmul.c: Likewise. * sysdeps/ieee754/float128/s_f32mulf128.c: Likewise. * sysdeps/ieee754/float128/s_f64mulf128.c: Likewise. * sysdeps/ieee754/float128/s_f64xmulf128.c: Likewise. * sysdeps/ieee754/ldbl-128/s_dmull.c: Likewise. * sysdeps/ieee754/ldbl-128/s_f64xmulf128.c: Likewise. * sysdeps/ieee754/ldbl-128/s_fmull.c: Likewise. * sysdeps/ieee754/ldbl-128ibm/s_dmull.c: Likewise. * sysdeps/ieee754/ldbl-128ibm/s_fmull.c: Likewise. * sysdeps/ieee754/ldbl-96/s_dmull.c: Likewise. * sysdeps/ieee754/ldbl-96/s_fmull.c: Likewise. * sysdeps/ieee754/ldbl-opt/nldbl-dmul.c: Likewise. * sysdeps/ieee754/ldbl-opt/nldbl-fmul.c: Likewise. * sysdeps/ieee754/soft-fp/s_dmull.c: Likewise. * sysdeps/ieee754/soft-fp/s_fmul.c: Likewise. * sysdeps/ieee754/soft-fp/s_fmull.c: Likewise. * sysdeps/powerpc/fpu/libm-test-ulps: Update. * sysdeps/mach/hurd/i386/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/aarch64/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/alpha/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/arm/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/hppa/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/i386/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/ia64/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/m68k/coldfire/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/m68k/m680x0/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/microblaze/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/mips/mips32/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/mips/mips64/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/nios2/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc32/fpu/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc32/nofpu/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc64/libm-le.abilist: Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc64/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/riscv/rv64/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/s390/s390-32/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/s390/s390-64/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/sh/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/sparc/sparc32/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/sparc/sparc64/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/x86_64/64/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/x86_64/x32/libm.abilist: Likewise.
Diffstat (limited to 'math/math-narrow.h')
-rw-r--r-- | math/math-narrow.h | 53 |
1 files changed, 53 insertions, 0 deletions
diff --git a/math/math-narrow.h b/math/math-narrow.h index b6982f2396..f769830643 100644 --- a/math/math-narrow.h +++ b/math/math-narrow.h @@ -166,6 +166,59 @@ } \ while (0) +/* Check for error conditions from a narrowing multiply function + returning RET with arguments X and Y and set errno as needed. + Overflow and underflow can occur for finite arguments and a domain + error for Inf * 0. */ +#define CHECK_NARROW_MUL(RET, X, Y) \ + do \ + { \ + if (!isfinite (RET)) \ + { \ + if (isnan (RET)) \ + { \ + if (!isnan (X) && !isnan (Y)) \ + __set_errno (EDOM); \ + } \ + else if (isfinite (X) && isfinite (Y)) \ + __set_errno (ERANGE); \ + } \ + else if ((RET) == 0 && (X) != 0 && (Y) != 0) \ + __set_errno (ERANGE); \ + } \ + while (0) + +/* Implement narrowing multiply using round-to-odd. The arguments are + X and Y, the return type is TYPE and UNION, MANTISSA and SUFFIX are + as for ROUND_TO_ODD. */ +#define NARROW_MUL_ROUND_TO_ODD(X, Y, TYPE, UNION, SUFFIX, MANTISSA) \ + do \ + { \ + TYPE ret; \ + \ + ret = (TYPE) ROUND_TO_ODD (math_opt_barrier (X) * (Y), \ + UNION, SUFFIX, MANTISSA); \ + \ + CHECK_NARROW_MUL (ret, (X), (Y)); \ + return ret; \ + } \ + while (0) + +/* Implement a narrowing multiply function that is not actually + narrowing or where no attempt is made to be correctly rounding (the + latter only applies to IBM long double). The arguments are X and Y + and the return type is TYPE. */ +#define NARROW_MUL_TRIVIAL(X, Y, TYPE) \ + do \ + { \ + TYPE ret; \ + \ + ret = (TYPE) ((X) * (Y)); \ + CHECK_NARROW_MUL (ret, (X), (Y)); \ + return ret; \ + } \ + while (0) + /* The following macros declare aliases for a narrowing function. The sole argument is the base name of a family of functions, such as "add". If any platform changes long double format after the |