diff options
| author | Zong Li <zong@andestech.com> | 2018-11-01 17:34:39 +0000 |
|---|---|---|
| committer | Joseph Myers <joseph@codesourcery.com> | 2018-11-01 17:34:39 +0000 |
| commit | ff48ea6787526d7e669af93ce2681b911d39675c (patch) | |
| tree | e62f4b7c05f630df014ad5a2524535b990a804c1 /soft-fp/op-4.h | |
| parent | eac4405af00464a4268cfd13b25224901c193988 (diff) | |
| download | glibc-ff48ea6787526d7e669af93ce2681b911d39675c.zip glibc-ff48ea6787526d7e669af93ce2681b911d39675c.tar.gz glibc-ff48ea6787526d7e669af93ce2681b911d39675c.tar.bz2 | |
soft-fp: Use temporary variable in FP_FRAC_SUB_3/FP_FRAC_SUB_4
In FRAC_SUB_3(R, X, Y) and FRAC_SUB_4(R,, X, Y), it reference both
the X[N] and X[N] after R[N] have been set. If one of the X and Y is
the same address with R, the result of the calculation is wrong,
because the value of the original X and Y are overwritten.
In glibc, there are two places use FRAC_SUB and occurs the overlap.
The first is _FP_DIV_MEAT_N_loop in op-common.h, it uses the source
_FP_DIV_MEAT_N_loop_u as the destination. This macro only be used
when N is one(_FP_DIV_MEAT_1_loop) and then the _FP_FRAC_SUB_##wc
extend to _FP_FRAC_SUB_1 in this macro. so it also work because
_FP_FRAC_SUB_1 has no overlap problem in its implementation.
The second places is _FP_DIV_MEAT_4_udiv, the original value of X##_f[0]
is overwritten before the calculatation.
In FRAC_SUB_1 and FRAC_SUB_2, there don't refer the source after
destination have been set, so they have no problem.
After this modification, we can pass the soft floating testing of glibc
testsuites on RV32.
* soft-fp/op-4.h (_FP_FRAC_SUB_3, _FP_FRAC_SUB_4): Use temporary
variable to avoid overlap arguments.
Diffstat (limited to 'soft-fp/op-4.h')
| -rw-r--r-- | soft-fp/op-4.h | 63 |
1 files changed, 35 insertions, 28 deletions
diff --git a/soft-fp/op-4.h b/soft-fp/op-4.h index 01b87d0..b429801 100644 --- a/soft-fp/op-4.h +++ b/soft-fp/op-4.h @@ -696,39 +696,46 @@ #endif #ifndef __FP_FRAC_SUB_3 -# define __FP_FRAC_SUB_3(r2, r1, r0, x2, x1, x0, y2, y1, y0) \ - do \ - { \ - _FP_W_TYPE __FP_FRAC_SUB_3_c1, __FP_FRAC_SUB_3_c2; \ - r0 = x0 - y0; \ - __FP_FRAC_SUB_3_c1 = r0 > x0; \ - r1 = x1 - y1; \ - __FP_FRAC_SUB_3_c2 = r1 > x1; \ - r1 -= __FP_FRAC_SUB_3_c1; \ - __FP_FRAC_SUB_3_c2 |= __FP_FRAC_SUB_3_c1 && (y1 == x1); \ - r2 = x2 - y2 - __FP_FRAC_SUB_3_c2; \ - } \ +# define __FP_FRAC_SUB_3(r2, r1, r0, x2, x1, x0, y2, y1, y0) \ + do \ + { \ + _FP_W_TYPE __FP_FRAC_SUB_3_tmp[2]; \ + _FP_W_TYPE __FP_FRAC_SUB_3_c1, __FP_FRAC_SUB_3_c2; \ + __FP_FRAC_SUB_3_tmp[0] = x0 - y0; \ + __FP_FRAC_SUB_3_c1 = __FP_FRAC_SUB_3_tmp[0] > x0; \ + __FP_FRAC_SUB_3_tmp[1] = x1 - y1; \ + __FP_FRAC_SUB_3_c2 = __FP_FRAC_SUB_3_tmp[1] > x1; \ + __FP_FRAC_SUB_3_tmp[1] -= __FP_FRAC_SUB_3_c1; \ + __FP_FRAC_SUB_3_c2 |= __FP_FRAC_SUB_3_c1 && (y1 == x1); \ + r2 = x2 - y2 - __FP_FRAC_SUB_3_c2; \ + r1 = __FP_FRAC_SUB_3_tmp[1]; \ + r0 = __FP_FRAC_SUB_3_tmp[0]; \ + } \ while (0) #endif #ifndef __FP_FRAC_SUB_4 # define __FP_FRAC_SUB_4(r3, r2, r1, r0, x3, x2, x1, x0, y3, y2, y1, y0) \ - do \ - { \ - _FP_W_TYPE __FP_FRAC_SUB_4_c1, __FP_FRAC_SUB_4_c2; \ - _FP_W_TYPE __FP_FRAC_SUB_4_c3; \ - r0 = x0 - y0; \ - __FP_FRAC_SUB_4_c1 = r0 > x0; \ - r1 = x1 - y1; \ - __FP_FRAC_SUB_4_c2 = r1 > x1; \ - r1 -= __FP_FRAC_SUB_4_c1; \ - __FP_FRAC_SUB_4_c2 |= __FP_FRAC_SUB_4_c1 && (y1 == x1); \ - r2 = x2 - y2; \ - __FP_FRAC_SUB_4_c3 = r2 > x2; \ - r2 -= __FP_FRAC_SUB_4_c2; \ - __FP_FRAC_SUB_4_c3 |= __FP_FRAC_SUB_4_c2 && (y2 == x2); \ - r3 = x3 - y3 - __FP_FRAC_SUB_4_c3; \ - } \ + do \ + { \ + _FP_W_TYPE __FP_FRAC_SUB_4_tmp[3]; \ + _FP_W_TYPE __FP_FRAC_SUB_4_c1, __FP_FRAC_SUB_4_c2; \ + _FP_W_TYPE __FP_FRAC_SUB_4_c3; \ + __FP_FRAC_SUB_4_tmp[0] = x0 - y0; \ + __FP_FRAC_SUB_4_c1 = __FP_FRAC_SUB_4_tmp[0] > x0; \ + __FP_FRAC_SUB_4_tmp[1] = x1 - y1; \ + __FP_FRAC_SUB_4_c2 = __FP_FRAC_SUB_4_tmp[1] > x1; \ + __FP_FRAC_SUB_4_tmp[1] -= __FP_FRAC_SUB_4_c1; \ + __FP_FRAC_SUB_4_c2 |= __FP_FRAC_SUB_4_c1 && (y1 == x1); \ + __FP_FRAC_SUB_4_tmp[2] = x2 - y2; \ + __FP_FRAC_SUB_4_c3 = __FP_FRAC_SUB_4_tmp[2] > x2; \ + __FP_FRAC_SUB_4_tmp[2] -= __FP_FRAC_SUB_4_c2; \ + __FP_FRAC_SUB_4_c3 |= __FP_FRAC_SUB_4_c2 && (y2 == x2); \ + r3 = x3 - y3 - __FP_FRAC_SUB_4_c3; \ + r2 = __FP_FRAC_SUB_4_tmp[2]; \ + r1 = __FP_FRAC_SUB_4_tmp[1]; \ + r0 = __FP_FRAC_SUB_4_tmp[0]; \ + } \ while (0) #endif |