]> git.proxmox.com Git - qemu.git/commit - fpu/softfloat-specialize.h
projects / qemu.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: b8b8ea0) | patch
softfloat: Implement fused multiply-add
authorPeter Maydell <peter.maydell@linaro.org>
Wed, 19 Oct 2011 16:14:06 +0000 (16:14 +0000)
committerPeter Maydell <peter.maydell@linaro.org>
Wed, 19 Oct 2011 16:14:06 +0000 (16:14 +0000)
commit369be8f618ac145d2421ea4bfff86ee774ad618c
tree6b7f1e6b30e8cc6a60febe9c25f9f17f841db34ctree
parentb8b8ea05c4008343afcedf99b9c91fd750ea90e5commit | diff
softfloat: Implement fused multiply-add

Implement fused multiply-add as a softfloat primitive. This implements
"a+b*c" as a single step without any intermediate rounding; it is
specified in IEEE 754-2008 and implemented in a number of CPUs.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
fpu/softfloat-specialize.h diff | blob | blame | history
fpu/softfloat.c diff | blob | blame | history
fpu/softfloat.h diff | blob | blame | history
Qemu copy for testing