This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
[PATCH v3 2/2] soft-fp: Add inplementation for 128 bit self-contained
- From: Zong Li <zongbox at gmail dot com>
- To: joseph at codesourcery dot com, palmer at dabbelt dot com, jimw at sifive dot com, kito at andestech dot com, greentime at andestech dot com, zong at andestech dot com
- Cc: libc-alpha at sourceware dot org, Zong Li <zongbox at gmail dot com>
- Date: Thu, 1 Nov 2018 13:10:26 +0800
- Subject: [PATCH v3 2/2] soft-fp: Add inplementation for 128 bit self-contained
- References: <cover.1541048728.git.zongbox@gmail.com>
Here only add the implementation when building the RV32 port.
These macros are used when the following situations occur at the same
time: soft-fp fma, ldbl-128 and 32-bit _FP_W_TYPE_SIZE. The RISC-V
32-bit port is the first port which use all three together.
This is the building flow about the situation:
When building soft-fp/s_fmal.c, there uses the FP_FMA_Q in __fmal.
The _FP_W_TYPE_SIZE is defined to 32-bit in sysdeps/riscv/sfp-machine.h,
so the FP_FMA_Q was defined to _FP_FMA (Q, 4, 8, R, X, Y, Z) in
soft-fp/quad.h.
Something in the soft-fp/quad.h:
#if _FP_W_TYPE_SIZE < 64
# define FP_FMA_Q(R, X, Y, Z) _FP_FMA (Q, 4, 8, R, X, Y, Z)
#else
# define FP_FMA_Q(R, X, Y, Z) _FP_FMA (Q, 2, 4, R, X, Y, Z)
#endif
Finally, in _FP_FMA (fs, wc, dwc, R, X, Y, Z), it will use the
_FP_FRAC_HIGHBIT_DW_##dwc macro, and it will be expanded to
_FP_FRAC_HIGHBIT_DW_8, but the _FP_FRAC_HIGHBIT_DW_8 is not be
implemented in soft-fp/op-8.h. there is only _FP_FRAC_HIGHBIT_DW_1,
_FP_FRAC_HIGHBIT_DW_2 and _FP_FRAC_HIGHBIT_DW_4 in the
soft-fp/op-*.h.
After this modification, we can pass the soft floating testing of glibc
testsuites on RV32.
* soft-fp/op-8.h (_FP_FRAC_SET_8, _FP_FRAC_ADD_8, _FP_FRAC_SUB_8)
(_FP_FRAC_CLZ_8, _FP_MINFRAC_8, _FP_FRAC_NEGP_8, _FP_FRAC_ZEROP_8)
(_FP_FRAC_HIGHBIT_DW_8, _FP_FRAC_COPY_4_8, _FP_FRAC_COPY_8_4)
(__FP_FRAC_SET_8): Add implementation for RV32 use.
---
ChangeLog | 4 +++
soft-fp/op-8.h | 88 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 92 insertions(+)
diff --git a/ChangeLog b/ChangeLog
index 0cced2b..5c41833 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -2,6 +2,10 @@
* soft-fp/op-4.h (_FP_FRAC_SUB_3, _FP_FRAC_SUB_4): Use temporary
variable to avoid overlap arguments.
+ * soft-fp/op-8.h (_FP_FRAC_SET_8, _FP_FRAC_ADD_8, _FP_FRAC_SUB_8)
+ (_FP_FRAC_CLZ_8, _FP_MINFRAC_8, _FP_FRAC_NEGP_8, _FP_FRAC_ZEROP_8)
+ (_FP_FRAC_HIGHBIT_DW_8, _FP_FRAC_COPY_4_8, _FP_FRAC_COPY_8_4)
+ (__FP_FRAC_SET_8): Add implementation for RV32 use.
2018-10-31 Samuel Thibault <samuel.thibault@ens-lyon.org>
diff --git a/soft-fp/op-8.h b/soft-fp/op-8.h
index ffed258..4871c49 100644
--- a/soft-fp/op-8.h
+++ b/soft-fp/op-8.h
@@ -35,6 +35,7 @@
/* We need just a few things from here for op-4, if we ever need some
other macros, they can be added. */
#define _FP_FRAC_DECL_8(X) _FP_W_TYPE X##_f[8]
+#define _FP_FRAC_SET_8(X, I) __FP_FRAC_SET_8 (X, I)
#define _FP_FRAC_HIGH_8(X) (X##_f[7])
#define _FP_FRAC_LOW_8(X) (X##_f[0])
#define _FP_FRAC_WORD_8(X, w) (X##_f[w])
@@ -147,4 +148,91 @@
} \
while (0)
+#define _FP_FRAC_ADD_8(R, X, Y) \
+ do \
+ { \
+ _FP_W_TYPE _FP_FRAC_ADD_8_c = 0; \
+ _FP_I_TYPE _FP_FRAC_ADD_8_i; \
+ for (_FP_FRAC_ADD_8_i = 0; _FP_FRAC_ADD_8_i < 8; ++_FP_FRAC_ADD_8_i) \
+ { \
+ R##_f[_FP_FRAC_ADD_8_i] \
+ = (X##_f[_FP_FRAC_ADD_8_i] + Y##_f[_FP_FRAC_ADD_8_i] \
+ + _FP_FRAC_ADD_8_c); \
+ _FP_FRAC_ADD_8_c \
+ = (_FP_FRAC_ADD_8_c \
+ ? R##_f[_FP_FRAC_ADD_8_i] <= X##_f[_FP_FRAC_ADD_8_i] \
+ : R##_f[_FP_FRAC_ADD_8_i] < X##_f[_FP_FRAC_ADD_8_i]); \
+ } \
+ } \
+ while (0)
+
+#define _FP_FRAC_SUB_8(R, X, Y) \
+ do \
+ { \
+ _FP_W_TYPE _FP_FRAC_SUB_8_tmp[8]; \
+ _FP_W_TYPE _FP_FRAC_SUB_8_c = 0; \
+ _FP_I_TYPE _FP_FRAC_SUB_8_i; \
+ for (_FP_FRAC_SUB_8_i = 0; _FP_FRAC_SUB_8_i < 8; ++_FP_FRAC_SUB_8_i) \
+ { \
+ _FP_FRAC_SUB_8_tmp[_FP_FRAC_SUB_8_i] \
+ = (X##_f[_FP_FRAC_SUB_8_i] - Y##_f[_FP_FRAC_SUB_8_i] \
+ - _FP_FRAC_SUB_8_c); \
+ _FP_FRAC_SUB_8_c \
+ = (_FP_FRAC_SUB_8_c \
+ ? (_FP_FRAC_SUB_8_tmp[_FP_FRAC_SUB_8_i] \
+ >= X##_f[_FP_FRAC_SUB_8_i]) \
+ : (_FP_FRAC_SUB_8_tmp[_FP_FRAC_SUB_8_i] \
+ > X##_f[_FP_FRAC_SUB_8_i])); \
+ } \
+ for (_FP_FRAC_SUB_8_i = 0; _FP_FRAC_SUB_8_i < 8; ++_FP_FRAC_SUB_8_i) \
+ R##_f[_FP_FRAC_SUB_8_i] = _FP_FRAC_SUB_8_tmp[_FP_FRAC_SUB_8_i]; \
+ } \
+ while (0)
+
+#define _FP_FRAC_CLZ_8(R, X) \
+ do \
+ { \
+ _FP_I_TYPE _FP_FRAC_CLZ_8_i; \
+ for (_FP_FRAC_CLZ_8_i = 7; _FP_FRAC_CLZ_8_i > 0; _FP_FRAC_CLZ_8_i--) \
+ if (X##_f[_FP_FRAC_CLZ_8_i]) \
+ break; \
+ __FP_CLZ ((R), X##_f[_FP_FRAC_CLZ_8_i]); \
+ (R) += _FP_W_TYPE_SIZE * (7 - _FP_FRAC_CLZ_8_i); \
+ } \
+ while (0)
+
+#define _FP_MINFRAC_8 0, 0, 0, 0, 0, 0, 0, 1
+
+#define _FP_FRAC_NEGP_8(X) ((_FP_WS_TYPE) X##_f[7] < 0)
+#define _FP_FRAC_ZEROP_8(X) \
+ ((X##_f[0] | X##_f[1] | X##_f[2] | X##_f[3] \
+ | X##_f[4] | X##_f[5] | X##_f[6] | X##_f[7]) == 0)
+#define _FP_FRAC_HIGHBIT_DW_8(fs, X) \
+ (_FP_FRAC_HIGH_DW_##fs (X) & _FP_HIGHBIT_DW_##fs)
+
+#define _FP_FRAC_COPY_4_8(D, S) \
+ do \
+ { \
+ D##_f[0] = S##_f[0]; \
+ D##_f[1] = S##_f[1]; \
+ D##_f[2] = S##_f[2]; \
+ D##_f[3] = S##_f[3]; \
+ } \
+ while (0)
+
+#define _FP_FRAC_COPY_8_4(D, S) \
+ do \
+ { \
+ D##_f[0] = S##_f[0]; \
+ D##_f[1] = S##_f[1]; \
+ D##_f[2] = S##_f[2]; \
+ D##_f[3] = S##_f[3]; \
+ D##_f[4] = D##_f[5] = D##_f[6] = D##_f[7]= 0; \
+ } \
+ while (0)
+
+#define __FP_FRAC_SET_8(X, I7, I6, I5, I4, I3, I2, I1, I0) \
+ (X##_f[7] = I7, X##_f[6] = I6, X##_f[5] = I5, X##_f[4] = I4, \
+ X##_f[3] = I3, X##_f[2] = I2, X##_f[1] = I1, X##_f[0] = I0)
+
#endif /* !SOFT_FP_OP_8_H */
--
2.7.4