From cada03eedbd70793e13a08a5d8f6c77e0b052de2 Mon Sep 17 00:00:00 2001 From: Hein-Pieter van Braam Date: Wed, 9 Jan 2019 01:09:56 +0100 Subject: [PATCH] Don't use -ffast-math or other unsafe math optimizations Godot supports many different compilers and for production releases we have to support 3 currently: GCC8, Clang6, and MSVC2017. These compilers all do slightly different things with -ffast-math and it is causing issues now. See #24841, #24540, #10758, #10070. And probably other complaints about physics differences between release and release_debug builds. I've done some performance comparisons on Linux x86_64. All tests are ran 20 times. Bunnymark: (higher is better) (bunnies) min max stdev average fast-math 7332 7597 71 7432 this pr 7379 7779 108 7621 (102%) FPBench (gdscript port http://fpbench.org/) (lower is better) (ms) fast-math 15441 16127 192 15764 this pr 15671 16855 326 16001 (99%) Float_add (adding floats in a tight loop) (lower is better) (sec) fast-math 5.49 5.78 0.07 5.65 this pr 5.65 5.90 0.06 5.76 (98%) Float_div (dividing floats in a tight loop) (lower is better) (sec) fast-math 11.70 12.36 0.18 11.99 this pr 11.92 12.32 0.12 12.12 (99%) Float_mul (multiplying floats in a tight loop) (lower is better) (sec) fast-math 11.72 12.17 0.12 11.93 this pr 12.01 12.62 0.17 12.26 (97%) I have also looked at FPS numbers for tps-demo, 3d platformer, 2d platformer, and sponza and could not find any measurable difference. I believe that given the issues and oft-reported (physics) glitches on release builds I believe that the couple of percent of tight-loop floating point performance regression is well worth it. This fixes #24540 and fixes #24841 (cherry picked from commit e5b335d367103f4052fc5fd435a54ad635ec447c) --- modules/etc/SCsub | 4 ---- platform/android/detect.py | 2 +- platform/haiku/detect.py | 4 ++-- platform/iphone/detect.py | 2 +- platform/osx/detect.py | 2 +- platform/server/detect.py | 4 ++-- platform/x11/detect.py | 6 ++---- 7 files changed, 9 insertions(+), 15 deletions(-) diff --git a/modules/etc/SCsub b/modules/etc/SCsub index 31d8f00ef30..4a3ce41f4d5 100644 --- a/modules/etc/SCsub +++ b/modules/etc/SCsub @@ -36,7 +36,3 @@ env_etc.add_source_files(env.modules_sources, "*.cpp") # upstream uses c++11 if (not env_etc.msvc): env_etc.Append(CCFLAGS="-std=c++11") -# -ffast-math seems to be incompatible with ec2comp on recent versions of -# GCC and Clang -if '-ffast-math' in env_etc['CCFLAGS']: - env_etc['CCFLAGS'].remove('-ffast-math') diff --git a/platform/android/detect.py b/platform/android/detect.py index 72ae6b47c66..9558597a8f9 100644 --- a/platform/android/detect.py +++ b/platform/android/detect.py @@ -150,7 +150,7 @@ def configure(env): if (env["target"].startswith("release")): env.Append(LINKFLAGS=['-O2']) - env.Append(CPPFLAGS=['-O2', '-DNDEBUG', '-ffast-math', '-funsafe-math-optimizations', '-fomit-frame-pointer']) + env.Append(CPPFLAGS=['-O2', '-DNDEBUG', '-fomit-frame-pointer']) if (can_vectorize): env.Append(CPPFLAGS=['-ftree-vectorize']) if (env["target"] == "release_debug"): diff --git a/platform/haiku/detect.py b/platform/haiku/detect.py index 7c62654ef61..b290a2ab277 100644 --- a/platform/haiku/detect.py +++ b/platform/haiku/detect.py @@ -37,14 +37,14 @@ def configure(env): ## Build type if (env["target"] == "release"): - env.Prepend(CCFLAGS=['-O3', '-ffast-math']) + env.Prepend(CCFLAGS=['-O3']) if (env["debug_symbols"] == "yes"): env.Prepend(CCFLAGS=['-g1']) if (env["debug_symbols"] == "full"): env.Prepend(CCFLAGS=['-g2']) elif (env["target"] == "release_debug"): - env.Prepend(CCFLAGS=['-O2', '-ffast-math', '-DDEBUG_ENABLED']) + env.Prepend(CCFLAGS=['-O2', '-DDEBUG_ENABLED']) if (env["debug_symbols"] == "yes"): env.Prepend(CCFLAGS=['-g1']) if (env["debug_symbols"] == "full"): diff --git a/platform/iphone/detect.py b/platform/iphone/detect.py index 772ad91f195..ac9ec4d3c96 100644 --- a/platform/iphone/detect.py +++ b/platform/iphone/detect.py @@ -47,7 +47,7 @@ def configure(env): if (env["target"].startswith("release")): env.Append(CPPFLAGS=['-DNDEBUG', '-DNS_BLOCK_ASSERTIONS=1']) - env.Append(CPPFLAGS=['-O2', '-ftree-vectorize', '-fomit-frame-pointer', '-ffast-math', '-funsafe-math-optimizations']) + env.Append(CPPFLAGS=['-O2', '-ftree-vectorize', '-fomit-frame-pointer']) env.Append(LINKFLAGS=['-O2']) if env["target"] == "release_debug": diff --git a/platform/osx/detect.py b/platform/osx/detect.py index 7676840f977..52f04b7048f 100644 --- a/platform/osx/detect.py +++ b/platform/osx/detect.py @@ -39,7 +39,7 @@ def configure(env): ## Build type if (env["target"] == "release"): - env.Prepend(CCFLAGS=['-O3', '-ffast-math', '-fomit-frame-pointer', '-ftree-vectorize', '-msse2']) + env.Prepend(CCFLAGS=['-O3', '-fomit-frame-pointer', '-ftree-vectorize', '-msse2']) if (env["debug_symbols"] == "yes"): env.Prepend(CCFLAGS=['-g1']) if (env["debug_symbols"] == "full"): diff --git a/platform/server/detect.py b/platform/server/detect.py index b09b3b8bbda..6bb96a6fa86 100644 --- a/platform/server/detect.py +++ b/platform/server/detect.py @@ -39,10 +39,10 @@ def configure(env): ## Build type if (env["target"] == "release"): - env.Append(CCFLAGS=['-O2', '-ffast-math', '-fomit-frame-pointer']) + env.Append(CCFLAGS=['-O2', '-fomit-frame-pointer']) elif (env["target"] == "release_debug"): - env.Append(CCFLAGS=['-O2', '-ffast-math', '-DDEBUG_ENABLED']) + env.Append(CCFLAGS=['-O2', '-DDEBUG_ENABLED']) elif (env["target"] == "debug"): env.Append(CCFLAGS=['-g2', '-DDEBUG_ENABLED', '-DDEBUG_MEMORY_ENABLED']) diff --git a/platform/x11/detect.py b/platform/x11/detect.py index a565b5e11ff..ae89677e131 100644 --- a/platform/x11/detect.py +++ b/platform/x11/detect.py @@ -70,16 +70,14 @@ def configure(env): ## Build type if (env["target"] == "release"): - # -O3 -ffast-math is identical to -Ofast. We need to split it out so we can selectively disable - # -ffast-math in code for which it generates wrong results. - env.Prepend(CCFLAGS=['-O3', '-ffast-math']) + env.Prepend(CCFLAGS=['-O3']) if (env["debug_symbols"] == "yes"): env.Prepend(CCFLAGS=['-g1']) if (env["debug_symbols"] == "full"): env.Prepend(CCFLAGS=['-g2']) elif (env["target"] == "release_debug"): - env.Prepend(CCFLAGS=['-O2', '-ffast-math', '-DDEBUG_ENABLED']) + env.Prepend(CCFLAGS=['-O2', '-DDEBUG_ENABLED']) if (env["debug_symbols"] == "yes"): env.Prepend(CCFLAGS=['-g1']) if (env["debug_symbols"] == "full"):