From: "Emilio G. Cota" <cota@braap.org>
To: qemu-devel@nongnu.org
Cc: "Aurelien Jarno" <aurelien@aurel32.net>,
"Peter Maydell" <peter.maydell@linaro.org>,
"Alex Bennée" <alex.bennee@linaro.org>,
"Laurent Vivier" <laurent@vivier.eu>,
"Richard Henderson" <richard.henderson@linaro.org>,
"Paolo Bonzini" <pbonzini@redhat.com>,
"Mark Cave-Ayland" <mark.cave-ayland@ilande.co.uk>
Subject: [Qemu-devel] [PATCH v1 08/14] hostfloat: support float32/64 addition and subtraction
Date: Wed, 21 Mar 2018 16:11:43 -0400 [thread overview]
Message-ID: <1521663109-32262-9-git-send-email-cota@braap.org> (raw)
In-Reply-To: <1521663109-32262-1-git-send-email-cota@braap.org>
Performance results (single and double precision) for
fp-bench run under aarch64-linux-user on an Intel(R)
Core(TM) i7-4790K CPU @ 4.00GHz host:
- before:
add-single: 86.74 MFlops
add-double: 86.46 MFlops
sub-single: 83.33 MFlops
sub-double: 84.57 MFlops
- after:
add-single: 188.26 MFlops
add-double: 186.60 MFlops
sub-single: 186.19 MFlops
sub-double: 187.77 MFlops
Signed-off-by: Emilio G. Cota <cota@braap.org>
---
include/fpu/hostfloat.h | 6 ++++++
include/fpu/softfloat.h | 8 ++++----
fpu/hostfloat.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++++
fpu/softfloat.c | 16 ++++++++--------
4 files changed, 68 insertions(+), 12 deletions(-)
diff --git a/include/fpu/hostfloat.h b/include/fpu/hostfloat.h
index b01291b..db49efa 100644
--- a/include/fpu/hostfloat.h
+++ b/include/fpu/hostfloat.h
@@ -11,4 +11,10 @@
#error fpu/hostfloat.h must only be included from softfloat.h
#endif
+float32 float32_add(float32 a, float32 b, float_status *status);
+float32 float32_sub(float32 a, float32 b, float_status *status);
+
+float64 float64_add(float64 a, float64 b, float_status *status);
+float64 float64_sub(float64 a, float64 b, float_status *status);
+
#endif /* HOSTFLOAT_H */
diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h
index 8963b68..eb7e9bc 100644
--- a/include/fpu/softfloat.h
+++ b/include/fpu/softfloat.h
@@ -342,8 +342,8 @@ float128 float32_to_float128(float32, float_status *status);
| Software IEC/IEEE single-precision operations.
*----------------------------------------------------------------------------*/
float32 float32_round_to_int(float32, float_status *status);
-float32 float32_add(float32, float32, float_status *status);
-float32 float32_sub(float32, float32, float_status *status);
+float32 soft_float32_add(float32, float32, float_status *status);
+float32 soft_float32_sub(float32, float32, float_status *status);
float32 float32_mul(float32, float32, float_status *status);
float32 float32_div(float32, float32, float_status *status);
float32 float32_rem(float32, float32, float_status *status);
@@ -482,8 +482,8 @@ float128 float64_to_float128(float64, float_status *status);
*----------------------------------------------------------------------------*/
float64 float64_round_to_int(float64, float_status *status);
float64 float64_trunc_to_int(float64, float_status *status);
-float64 float64_add(float64, float64, float_status *status);
-float64 float64_sub(float64, float64, float_status *status);
+float64 soft_float64_add(float64, float64, float_status *status);
+float64 soft_float64_sub(float64, float64, float_status *status);
float64 float64_mul(float64, float64, float_status *status);
float64 float64_div(float64, float64, float_status *status);
float64 float64_rem(float64, float64, float_status *status);
diff --git a/fpu/hostfloat.c b/fpu/hostfloat.c
index cab0341..502552b 100644
--- a/fpu/hostfloat.c
+++ b/fpu/hostfloat.c
@@ -94,3 +94,53 @@ GEN_TYPE_CONV(double_to_float64, float64, double)
GEN_INPUT_FLUSH(float32)
GEN_INPUT_FLUSH(float64)
#undef GEN_INPUT_FLUSH
+
+#define GEN_FPU_ADDSUB(add_name, sub_name, soft_t, host_t, \
+ host_abs_func, min_normal) \
+ static inline __attribute__((always_inline)) soft_t \
+ fpu_ ## soft_t ## _addsub(soft_t a, soft_t b, bool subtract, \
+ float_status *s) \
+ { \
+ soft_t ## _input_flush2(&a, &b, s); \
+ if (likely((soft_t ## _is_normal(a) || soft_t ## _is_zero(a)) && \
+ (soft_t ## _is_normal(b) || soft_t ## _is_zero(b)) && \
+ s->float_exception_flags & float_flag_inexact && \
+ s->float_rounding_mode == float_round_nearest_even)) { \
+ host_t ha = soft_t ## _to_ ## host_t(a); \
+ host_t hb = soft_t ## _to_ ## host_t(b); \
+ host_t hr; \
+ soft_t r; \
+ \
+ if (subtract) { \
+ hb = -hb; \
+ } \
+ hr = ha + hb; \
+ r = host_t ## _to_ ## soft_t(hr); \
+ if (unlikely(soft_t ## _is_infinity(r))) { \
+ s->float_exception_flags |= float_flag_overflow; \
+ } else if (unlikely(host_abs_func(hr) <= min_normal)) { \
+ goto soft; \
+ } \
+ return r; \
+ } \
+ soft: \
+ if (subtract) { \
+ return soft_ ## soft_t ## _sub(a, b, s); \
+ } else { \
+ return soft_ ## soft_t ## _add(a, b, s); \
+ } \
+ } \
+ \
+ soft_t add_name(soft_t a, soft_t b, float_status *status) \
+ { \
+ return fpu_ ## soft_t ## _addsub(a, b, false, status); \
+ } \
+ \
+ soft_t sub_name(soft_t a, soft_t b, float_status *status) \
+ { \
+ return fpu_ ## soft_t ## _addsub(a, b, true, status); \
+ } \
+
+GEN_FPU_ADDSUB(float32_add, float32_sub, float32, float, fabsf, FLT_MIN)
+GEN_FPU_ADDSUB(float64_add, float64_sub, float64, double, fabs, DBL_MIN)
+#undef GEN_FPU_ADDSUB
diff --git a/fpu/softfloat.c b/fpu/softfloat.c
index ee615a9..bd82adf 100644
--- a/fpu/softfloat.c
+++ b/fpu/softfloat.c
@@ -738,8 +738,8 @@ float16 __attribute__((flatten)) float16_add(float16 a, float16 b,
return float16_round_pack_canonical(pr, status);
}
-float32 __attribute__((flatten)) float32_add(float32 a, float32 b,
- float_status *status)
+float32 __attribute__((flatten)) soft_float32_add(float32 a, float32 b,
+ float_status *status)
{
FloatParts pa = float32_unpack_canonical(a, status);
FloatParts pb = float32_unpack_canonical(b, status);
@@ -748,8 +748,8 @@ float32 __attribute__((flatten)) float32_add(float32 a, float32 b,
return float32_round_pack_canonical(pr, status);
}
-float64 __attribute__((flatten)) float64_add(float64 a, float64 b,
- float_status *status)
+float64 __attribute__((flatten)) soft_float64_add(float64 a, float64 b,
+ float_status *status)
{
FloatParts pa = float64_unpack_canonical(a, status);
FloatParts pb = float64_unpack_canonical(b, status);
@@ -768,8 +768,8 @@ float16 __attribute__((flatten)) float16_sub(float16 a, float16 b,
return float16_round_pack_canonical(pr, status);
}
-float32 __attribute__((flatten)) float32_sub(float32 a, float32 b,
- float_status *status)
+float32 __attribute__((flatten)) soft_float32_sub(float32 a, float32 b,
+ float_status *status)
{
FloatParts pa = float32_unpack_canonical(a, status);
FloatParts pb = float32_unpack_canonical(b, status);
@@ -778,8 +778,8 @@ float32 __attribute__((flatten)) float32_sub(float32 a, float32 b,
return float32_round_pack_canonical(pr, status);
}
-float64 __attribute__((flatten)) float64_sub(float64 a, float64 b,
- float_status *status)
+float64 __attribute__((flatten)) soft_float64_sub(float64 a, float64 b,
+ float_status *status)
{
FloatParts pa = float64_unpack_canonical(a, status);
FloatParts pb = float64_unpack_canonical(b, status);
--
2.7.4
next prev parent reply other threads:[~2018-03-21 20:12 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-03-21 20:11 [Qemu-devel] [PATCH v1 00/14] fp-test + hostfloat Emilio G. Cota
2018-03-21 20:11 ` [Qemu-devel] [PATCH v1 01/14] tests: add fp-bench, a collection of simple floating-point microbenchmarks Emilio G. Cota
2018-03-27 8:45 ` Alex Bennée
2018-03-27 17:21 ` Emilio G. Cota
2018-03-21 20:11 ` [Qemu-devel] [PATCH v1 02/14] tests: add fp-test, a floating point test suite Emilio G. Cota
2018-03-27 10:13 ` Alex Bennée
2018-03-27 18:00 ` Emilio G. Cota
2018-03-28 9:51 ` Alex Bennée
2018-03-28 15:36 ` Emilio G. Cota
2018-03-21 20:11 ` [Qemu-devel] [PATCH v1 03/14] softfloat: fix {min, max}nummag for same-abs-value inputs Emilio G. Cota
2018-03-27 10:15 ` Alex Bennée
2018-03-27 10:15 ` Alex Bennée
2018-03-21 20:11 ` [Qemu-devel] [PATCH v1 04/14] fp-test: add muladd variants Emilio G. Cota
2018-03-27 11:33 ` Alex Bennée
2018-03-27 18:03 ` Emilio G. Cota
2018-03-21 20:11 ` [Qemu-devel] [PATCH v1 05/14] softfloat: add float32_is_normal and float64_is_normal Emilio G. Cota
2018-03-27 11:34 ` Alex Bennée
2018-03-27 18:05 ` Emilio G. Cota
2018-03-21 20:11 ` [Qemu-devel] [PATCH v1 06/14] softfloat: add float32_is_denormal and float64_is_denormal Emilio G. Cota
2018-03-27 11:35 ` Alex Bennée
2018-03-21 20:11 ` [Qemu-devel] [PATCH v1 07/14] fpu: introduce hostfloat Emilio G. Cota
2018-03-21 20:41 ` Laurent Vivier
2018-03-21 21:45 ` Emilio G. Cota
2018-03-27 11:49 ` Alex Bennée
2018-03-27 18:16 ` Emilio G. Cota
2018-03-21 20:11 ` Emilio G. Cota [this message]
2018-03-22 5:05 ` [Qemu-devel] [PATCH v1 08/14] hostfloat: support float32/64 addition and subtraction Richard Henderson
2018-03-22 5:57 ` Emilio G. Cota
2018-03-22 6:41 ` Richard Henderson
2018-03-22 15:08 ` Emilio G. Cota
2018-03-22 15:12 ` Laurent Vivier
2018-03-22 19:57 ` Emilio G. Cota
2018-03-27 11:41 ` Alex Bennée
2018-03-27 18:08 ` Emilio G. Cota
2018-03-21 20:11 ` [Qemu-devel] [PATCH v1 09/14] hostfloat: support float32/64 multiplication Emilio G. Cota
2018-03-21 20:11 ` [Qemu-devel] [PATCH v1 10/14] hostfloat: support float32/64 division Emilio G. Cota
2018-03-21 20:11 ` [Qemu-devel] [PATCH v1 11/14] hostfloat: support float32/64 fused multiply-add Emilio G. Cota
2018-03-21 20:11 ` [Qemu-devel] [PATCH v1 12/14] hostfloat: support float32/64 square root Emilio G. Cota
2018-03-22 1:29 ` Alex Bennée
2018-03-22 4:02 ` Emilio G. Cota
2018-03-21 20:11 ` [Qemu-devel] [PATCH v1 13/14] hostfloat: support float32/64 comparison Emilio G. Cota
2018-03-21 20:11 ` [Qemu-devel] [PATCH v1 14/14] hostfloat: support float32_to_float64 Emilio G. Cota
2018-03-21 20:36 ` [Qemu-devel] [PATCH v1 00/14] fp-test + hostfloat no-reply
2018-03-22 5:02 ` no-reply
2018-03-22 8:56 ` Alex Bennée
2018-03-22 15:28 ` Emilio G. Cota
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1521663109-32262-9-git-send-email-cota@braap.org \
--to=cota@braap.org \
--cc=alex.bennee@linaro.org \
--cc=aurelien@aurel32.net \
--cc=laurent@vivier.eu \
--cc=mark.cave-ayland@ilande.co.uk \
--cc=pbonzini@redhat.com \
--cc=peter.maydell@linaro.org \
--cc=qemu-devel@nongnu.org \
--cc=richard.henderson@linaro.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.