[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1501171791-23690-14-git-send-email-aleksandar.markovic@rt-rk.com>
Date: Thu, 27 Jul 2017 18:08:56 +0200
From: Aleksandar Markovic <aleksandar.markovic@...rk.com>
To: linux-mips@...ux-mips.org
Cc: Aleksandar Markovic <aleksandar.markovic@...tec.com>,
Miodrag Dinic <miodrag.dinic@...tec.com>,
Goran Ferenc <goran.ferenc@...tec.com>,
"# 4 . 7+" <stable@...r.kernel.org>, Bo Hu <bohu@...gle.com>,
Douglas Leung <douglas.leung@...tec.com>,
James Hogan <james.hogan@...tec.com>,
Jin Qian <jinqian@...gle.com>, linux-kernel@...r.kernel.org,
Paul Burton <paul.burton@...tec.com>,
Petar Jovanovic <petar.jovanovic@...tec.com>,
Raghu Gandham <raghu.gandham@...tec.com>,
Ralf Baechle <ralf@...ux-mips.org>
Subject: [PATCH v4 13/16] MIPS: math-emu: <MADDF|MSUBF>.<D|S>: Fix some cases of zero inputs
From: Aleksandar Markovic <aleksandar.markovic@...tec.com>
Fix the cases of <MADDF|MSUBF>.<D|S> when any of two multiplicands is
+0 or -0, and the third input is also +0 or -0. Depending on the signs
of inputs, certain special cases must be handled.
A relevant example:
MADDF.S fd,fs,ft:
If fs contains +0.0, ft contains -0.0, and fd contains 0.0, fd is
going to contain +0.0 (without this patch, it used to contain -0.0).
Fixes: e24c3bec3e8e ("MIPS: math-emu: Add support for the MIPS R6 MADDF FPU instruction")
Fixes: 83d43305a1df ("MIPS: math-emu: Add support for the MIPS R6 MSUBF FPU instruction")
Signed-off-by: Miodrag Dinic <miodrag.dinic@...tec.com>
Signed-off-by: Goran Ferenc <goran.ferenc@...tec.com>
Signed-off-by: Aleksandar Markovic <aleksandar.markovic@...tec.com>
Cc: <stable@...r.kernel.org> # 4.7+
Reviewed-by: James Hogan <james.hogan@...tec.com>
---
arch/mips/math-emu/dp_maddf.c | 18 +++++++++++++++++-
arch/mips/math-emu/sp_maddf.c | 18 +++++++++++++++++-
2 files changed, 34 insertions(+), 2 deletions(-)
diff --git a/arch/mips/math-emu/dp_maddf.c b/arch/mips/math-emu/dp_maddf.c
index 557a0a1..c38fe1b 100644
--- a/arch/mips/math-emu/dp_maddf.c
+++ b/arch/mips/math-emu/dp_maddf.c
@@ -113,7 +113,23 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
if (zc == IEEE754_CLASS_INF)
return ieee754dp_inf(zs);
- /* Multiplication is 0 so just return z */
+ if (zc == IEEE754_CLASS_ZERO) {
+ /* Handle cases +0 + (-0) and similar ones. */
+ if ((!(flags & maddf_negate_product)
+ && (zs == (xs ^ ys))) ||
+ ((flags & maddf_negate_product)
+ && (zs != (xs ^ ys))))
+ /*
+ * Cases of addition of zeros of equal signs
+ * or subtraction of zeroes of opposite signs.
+ * The sign of the resulting zero is in any
+ * such case determined only by the sign of z.
+ */
+ return z;
+
+ return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD);
+ }
+ /* x*y is here 0, and z is not 0, so just return z */
return z;
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
diff --git a/arch/mips/math-emu/sp_maddf.c b/arch/mips/math-emu/sp_maddf.c
index 0d8d25f..4241ec1 100644
--- a/arch/mips/math-emu/sp_maddf.c
+++ b/arch/mips/math-emu/sp_maddf.c
@@ -114,7 +114,23 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
if (zc == IEEE754_CLASS_INF)
return ieee754sp_inf(zs);
- /* Multiplication is 0 so just return z */
+ if (zc == IEEE754_CLASS_ZERO) {
+ /* Handle cases +0 + (-0) and similar ones. */
+ if ((!(flags & maddf_negate_product)
+ && (zs == (xs ^ ys))) ||
+ ((flags & maddf_negate_product)
+ && (zs != (xs ^ ys))))
+ /*
+ * Cases of addition of zeros of equal signs
+ * or subtraction of zeroes of opposite signs.
+ * The sign of the resulting zero is in any
+ * such case determined only by the sign of z.
+ */
+ return z;
+
+ return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD);
+ }
+ /* x*y is here 0, and z is not 0, so just return z */
return z;
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
--
2.7.4
Powered by blists - more mailing lists