qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Alex Bennée" <alex.bennee@linaro.org>
To: qemu-devel@nongnu.org
Cc: "Emilio G. Cota" <cota@braap.org>,
	"Alex Bennée" <alex.bennee@linaro.org>,
	"Aurelien Jarno" <aurelien@aurel32.net>,
	"Peter Maydell" <peter.maydell@linaro.org>
Subject: [Qemu-devel] [PATCH v3 07/11] softfloat: enforce softfloat if the host's FMA is broken
Date: Tue, 22 Jan 2019 21:50:12 +0000	[thread overview]
Message-ID: <20190122215016.18697-8-alex.bennee@linaro.org> (raw)
In-Reply-To: <20190122215016.18697-1-alex.bennee@linaro.org>

From: "Emilio G. Cota" <cota@braap.org>

The added branch to the FMA ops is marked as unlikely and therefore
its impact on performance (measured with fp-bench) is within noise range
when measured on an Intel(R) Xeon(R) Gold 6142 CPU @ 2.60GHz.

Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
---
 fpu/softfloat.c | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/fpu/softfloat.c b/fpu/softfloat.c
index 59eac97d10..9132d7a0b0 100644
--- a/fpu/softfloat.c
+++ b/fpu/softfloat.c
@@ -1542,6 +1542,8 @@ soft_f64_muladd(float64 a, float64 b, float64 c, int flags,
     return float64_round_pack_canonical(pr, status);
 }
 
+static bool force_soft_fma;
+
 float32 QEMU_FLATTEN
 float32_muladd(float32 xa, float32 xb, float32 xc, int flags, float_status *s)
 {
@@ -1562,6 +1564,11 @@ float32_muladd(float32 xa, float32 xb, float32 xc, int flags, float_status *s)
     if (unlikely(!f32_is_zon3(ua, ub, uc))) {
         goto soft;
     }
+
+    if (unlikely(force_soft_fma)) {
+        goto soft;
+    }
+
     /*
      * When (a || b) == 0, there's no need to check for under/over flow,
      * since we know the addend is (normal || 0) and the product is 0.
@@ -1623,6 +1630,11 @@ float64_muladd(float64 xa, float64 xb, float64 xc, int flags, float_status *s)
     if (unlikely(!f64_is_zon3(ua, ub, uc))) {
         goto soft;
     }
+
+    if (unlikely(force_soft_fma)) {
+        goto soft;
+    }
+
     /*
      * When (a || b) == 0, there's no need to check for under/over flow,
      * since we know the addend is (normal || 0) and the product is 0.
@@ -7974,3 +7986,24 @@ float128 float128_scalbn(float128 a, int n, float_status *status)
                                          , status);
 
 }
+
+static void __attribute__((constructor)) softfloat_init(void)
+{
+    union_float64 ua, ub, uc, ur;
+
+    if (QEMU_NO_HARDFLOAT) {
+        return;
+    }
+    /*
+     * Test that the host's FMA is not obviously broken. For example,
+     * glibc < 2.23 can perform an incorrect FMA on certain hosts; see
+     *   https://sourceware.org/bugzilla/show_bug.cgi?id=13304
+     */
+    ua.s = 0x0020000000000001ULL;
+    ub.s = 0x3ca0000000000000ULL;
+    uc.s = 0x0020000000000000ULL;
+    ur.h = fma(ua.h, ub.h, uc.h);
+    if (ur.s != 0x0020000000000001ULL) {
+        force_soft_fma = true;
+    }
+}
-- 
2.17.1

  parent reply	other threads:[~2019-01-22 21:50 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-22 21:50 [Qemu-devel] [PATCH v3 00/11] current fpu/next queue (tests & build fix) Alex Bennée
2019-01-22 21:50 ` [Qemu-devel] [PATCH v3 01/11] fp-bench: fix update_random_ops Alex Bennée
2019-01-22 21:50 ` [Qemu-devel] [PATCH v3 02/11] fp-bench: remove wrong exponent raise in fill_random Alex Bennée
2019-01-22 21:50 ` [Qemu-devel] [PATCH v3 03/11] berkeley-testfloat-3: pull changes Alex Bennée
2019-01-22 21:50 ` [Qemu-devel] [PATCH v3 04/11] tests/fp/Makefile: do not use gcc-only -W flags Alex Bennée
2019-01-22 21:50 ` [Qemu-devel] [PATCH v3 05/11] fp-test: fix signature of slow_clear_flags and qemu_clear_flags Alex Bennée
2019-01-22 21:50 ` [Qemu-devel] [PATCH v3 06/11] tests/fp/platform.h: include config-host.h Alex Bennée
2019-01-22 21:50 ` Alex Bennée [this message]
2019-01-22 21:50 ` [Qemu-devel] [PATCH v3 08/11] include/fpu/softfloat: Fix compilation with Clang on s390x Alex Bennée
2019-01-22 21:50 ` [Qemu-devel] [PATCH v3 09/11] tests/Makefile: add floating point tests Alex Bennée
2019-01-22 23:45   ` Emilio G. Cota
2019-01-22 21:50 ` [Qemu-devel] [PATCH v3 10/11] scripts/archive-source: include softfloat tests Alex Bennée
2019-01-22 21:50 ` [Qemu-devel] [PATCH v3 11/11] tests/Makfile: add check-softfloat rule Alex Bennée
2019-01-22 23:46   ` Emilio G. Cota
2019-01-31 17:56 ` [Qemu-devel] [PATCH v3 00/11] current fpu/next queue (tests & build fix) no-reply

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=20190122215016.18697-8-alex.bennee@linaro.org \
    --to=alex.bennee@linaro.org \
    --cc=aurelien@aurel32.net \
    --cc=cota@braap.org \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-devel@nongnu.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).