4.9-stable review patch. If anyone has any objections, please let me know.
------------------ From: Aleksandar Markovic <aleksandar.marko...@imgtec.com> commit ddbfff7429a75d954bf5bdff9f2222bceb4c236a upstream. If accumulator value is zero, just return the value of previously calculated product. This brings logic in MADDF/MSUBF implementation closer to the logic in ADD/SUB case. Signed-off-by: Miodrag Dinic <miodrag.di...@imgtec.com> Signed-off-by: Goran Ferenc <goran.fer...@imgtec.com> Signed-off-by: Aleksandar Markovic <aleksandar.marko...@imgtec.com> Cc: james.ho...@imgtec.com Cc: paul.bur...@imgtec.com Cc: raghu.gand...@imgtec.com Cc: leonid.yegos...@imgtec.com Cc: douglas.le...@imgtec.com Cc: petar.jovano...@imgtec.com Cc: linux-m...@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16512/ Signed-off-by: Ralf Baechle <r...@linux-mips.org> Signed-off-by: Greg Kroah-Hartman <gre...@linuxfoundation.org> --- arch/mips/math-emu/dp_maddf.c | 5 ++++- arch/mips/math-emu/sp_maddf.c | 5 ++++- 2 files changed, 8 insertions(+), 2 deletions(-) --- a/arch/mips/math-emu/dp_maddf.c +++ b/arch/mips/math-emu/dp_maddf.c @@ -54,7 +54,7 @@ static union ieee754dp _dp_maddf(union i return ieee754dp_nanxcpt(z); case IEEE754_CLASS_DNORM: DPDNORMZ; - /* QNAN is handled separately below */ + /* QNAN and ZERO cases are handled separately below */ } switch (CLPAIR(xc, yc)) { @@ -210,6 +210,9 @@ static union ieee754dp _dp_maddf(union i } assert(rm & (DP_HIDDEN_BIT << 3)); + if (zc == IEEE754_CLASS_ZERO) + return ieee754dp_format(rs, re, rm); + /* And now the addition */ assert(zm & DP_HIDDEN_BIT); --- a/arch/mips/math-emu/sp_maddf.c +++ b/arch/mips/math-emu/sp_maddf.c @@ -54,7 +54,7 @@ static union ieee754sp _sp_maddf(union i return ieee754sp_nanxcpt(z); case IEEE754_CLASS_DNORM: SPDNORMZ; - /* QNAN is handled separately below */ + /* QNAN and ZERO cases are handled separately below */ } switch (CLPAIR(xc, yc)) { @@ -203,6 +203,9 @@ static union ieee754sp _sp_maddf(union i } assert(rm & (SP_HIDDEN_BIT << 3)); + if (zc == IEEE754_CLASS_ZERO) + return ieee754sp_format(rs, re, rm); + /* And now the addition */ assert(zm & SP_HIDDEN_BIT);
