Reviewers: Jakob,
Description:
[ia32] Require SSE2 for all 32-bit Linux builds.
This way we stay in sync with what Chromium does and we reduce the
number of bugs caused by 80-to-{32,64}-bit rounding errors.
[email protected]
Please review this at https://codereview.chromium.org/864483002/
Base URL: https://chromium.googlesource.com/v8/v8.git@master
Affected files (+39, -0 lines):
M build/toolchain.gypi
Index: build/toolchain.gypi
diff --git a/build/toolchain.gypi b/build/toolchain.gypi
index
ee8efe13c4c0f8d960b8e39e354445bfd059c099..56b2e338eed352f3b2a95c408ad7fdfdb39653bf
100644
--- a/build/toolchain.gypi
+++ b/build/toolchain.gypi
@@ -811,6 +811,45 @@
}],
['(OS=="linux" or OS=="freebsd" or OS=="openbsd" or OS=="solaris" \
or OS=="netbsd" or OS=="mac" or OS=="android" or OS=="qnx") and \
+ v8_target_arch=="ia32"', {
+ # All floating-point computations on x87 happens in 80-bit
+ # precision. Because the C and C++ language standards allow
+ # the compiler to keep the floating-point values in higher
+ # precision than what's specified in the source and doing so
+ # is more efficient than constantly rounding up to 64-bit or
+ # 32-bit precision as specified in the source, the compiler,
+ # especially in the optimized mode, tries very hard to keep
+ # values in x87 floating-point stack (in 80-bit precision)
+ # as long as possible. This has important side effects, that
+ # the real value used in computation may change depending on
+ # how the compiler did the optimization - that is, the value
+ # kept in 80-bit is different than the value rounded down to
+ # 64-bit or 32-bit. There are possible compiler options to
+ # make this behavior consistent (e.g. -ffloat-store would keep
+ # all floating-values in the memory, thus force them to be
+ # rounded to its original precision) but they have significant
+ # runtime performance penalty.
+ #
+ # -mfpmath=sse -msse2 makes the compiler use SSE instructions
+ # which keep floating-point values in SSE registers in its
+ # native precision (32-bit for single precision, and 64-bit
+ # for double precision values). This means the floating-point
+ # value used during computation does not change depending on
+ # how the compiler optimized the code, since the value is
+ # always kept in its specified precision.
+ #
+ # Refer to http://crbug.com/348761 for rationale behind SSE2
+ # being a minimum requirement for 32-bit Linux builds and
+ # http://crbug.com/313032 for an example where this has "bit"
+ # us in the past.
+ 'cflags': [
+ '-msse2',
+ '-mfpmath=sse',
+ '-mmmx', # Allows mmintrin.h for MMX intrinsics.
+ ],
+ }],
+ ['(OS=="linux" or OS=="freebsd" or OS=="openbsd" or OS=="solaris" \
+ or OS=="netbsd" or OS=="mac" or OS=="android" or OS=="qnx") and \
(v8_target_arch=="arm" or v8_target_arch=="ia32" or \
v8_target_arch=="x87" or v8_target_arch=="mips" or \
v8_target_arch=="mipsel" or v8_target_arch=="ppc")', {
--
--
v8-dev mailing list
[email protected]
http://groups.google.com/group/v8-dev
---
You received this message because you are subscribed to the Google Groups "v8-dev" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/d/optout.
