Safe CFLAGS

This article provides a summary of 'safe' settings for CPU flags on Gentoo Linux.

Automatic CPU detection by tools

cpuid2cpuflags

The app-portage/cpuid2cpuflags package can attempt to automatically detect all supported CPU flags for the currently running processor. After installing the package, issue the following command for output:

user $cpuid2cpuflags

resolve-march-native

Alternatively, another tool that exists to automagically determine -march=native resolution values is app-misc/resolve-march-native. After installing it, issue:

user $resolve-march-native

Automatic CPU detection by the compiler

A recommended default choice for CFLAGS or CXXFLAGS is to use -march=native. This enables auto-detection of the CPU's architecture. A possible entry might look like:

FILE /etc/portage/make.conf

COMMON_FLAGS="-O2 -pipe -march=native"
CFLAGS="${COMMON_FLAGS}"
CXXFLAGS="${COMMON_FLAGS}"

Warning
Do not use -march=native or -mtune=native in the CFLAGS or CXXFLAGS variables of make.conf when compiling with distcc. Consult the distcc page about how to set up CFLAGS/CXXFLAGS correctly.

Note
To see what GCC detects "native" to be for certain system in particular, the following command can be run:

user $gcc -v -E -x c /dev/null -o /dev/null -march=native 2>&1 | grep /cc1 | grep mtune

The internal translation of -march=native will be visible in the output. In some cases, if the CPU is unknown to GCC's detection model, a suboptimal -mtune=generic (or even no -mtune will be visible). In this case, select relevant -mtune= from manual. In some other cases there are same to detected -march= or common -mtune=intel for (too) modern Intel CPUs.

Also possible suboptimal -march=native detection - full l2-cache-size to single CPU thread on multi-core CPUs. Currently it used only for prefetching, but sometimes good choice to fallback to default --param=l2-cache-size=512 or own calculated value - to reduce cache concurrency on high SMP load. But this is in theory and not for all tasks - do nothing if unsure.

Tip
Additional information can be found at the GCC optimization page.

Manual

Finding the CPU

To identify the model of the CPU, take a look inside /proc/cpuinfo for the "cpu family" and "model" numbers like so:

user $grep -m1 -A3 "vendor_id" /proc/cpuinfo

Once this information is found match the CPU to one listed on this page in order to find out the suggested "safe" CFLAGS.

Below is a list of CFLAGS which are to be considered "safe" for the given processors. These are the settings that should be used, especially when unsure which CFLAGS the processor needs.

x86/amd64

Generic psABI levels

If you have a distcc farm with slightly different CPUs, it might make more sense to generate code that is just old enough to work for all of them, without bogging down to the really generic code. The psABI microarchitecture levels aims to provide just that for common eras of amd64 CPUs. See Wikipedia:x86-64#Microarchitecture_levels for a description of the levels.

Intel

Alder Lake

Core i3/i5/i7 12th Gen vendor_id : GenuineIntel cpu family : 6 model : 154 model name : 12th Gen Intel(R) Core(TM) i7-1260P

FILE /etc/portage/make.conf COMMON_FLAGS="-march=alderlake -O2 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

Skylake, Kaby Lake, Kaby Lake R, Coffee Lake, Comet Lake

Core i3/i5/i7 and Xeon E3/E5 *V5 vendor_id : GenuineIntel cpu family : 6 model : 94 model name : Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz ... model : 165 model name : Intel(R) Core(TM) i5-10400F CPU @ 2.90GHz

FILE /etc/portage/make.conf COMMON_FLAGS="-march=skylake -O2 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}" Warning Even though they fit the family and model, this set of CFLAGS does NOT work for Skylake Pentium CPUs (e. g. G4400, or J5005) producing invalid code, which may break the system. Use -march=native for these systems instead.

Haswell

Core i3/i5/i7 and Xeon E3/E5/E7 *V3 vendor_id : GenuineIntel cpu family : 6 model : 60 model name : Intel(R) Xeon(R) CPU E3-1271 v3 @ 3.60GHz … model : 60 model name : Intel(R) Core(TM) i7-4770 CPU @ 3.40GHz

FILE /etc/portage/make.conf COMMON_FLAGS="-march=haswell -O2 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

Ivy Bridge

Core i3/i5/i7 and Xeon E3/E5/E7 *V2 vendor_id : GenuineIntel cpu family : 6 model : 58 model name : Intel(R) Core(TM) i7-3610QM CPU @ 2.30GHz

FILE /etc/portage/make.conf COMMON_FLAGS="-march=ivybridge -O2 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

Pentium vendor_id : GenuineIntel cpu family : 6 model : 58 model name : Intel(R) Pentium(R) CPU G2020 @ 2.90GHz

FILE /etc/portage/make.conf COMMON_FLAGS="-march=ivybridge -mno-avx -mno-aes -mno-rdrnd -O2 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

Sandy Bridge

Core i3/i5/i7 and Xeon E3/E5/E7 vendor_id : GenuineIntel cpu family : 6 … model : 42 model name : Intel(R) Core(TM) i5-2400 CPU @ 3.10GHz … model : 45 model name : Intel(R) Core(TM) i7-3930K CPU @ 3.20GHz … model : 42 model name : Intel(R) Xeon(R) CPU E31245 @ 3.30GHz … model : 45 model name : Intel(R) Xeon(R) CPU E5-2407 0 @ 2.20GHz

FILE /etc/portage/make.conf COMMON_FLAGS="-march=sandybridge -O2 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

Pentium vendor_id : GenuineIntel cpu family : 6 model : 42 model name : Intel(R) Pentium(R) CPU B960 @ 2.20GHz

FILE /etc/portage/make.conf COMMON_FLAGS="-march=sandybridge -mno-avx -mno-aes -mno-rdrnd -O2 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

Nehalem

Core i3/i5/i7 vendor_id : GenuineIntel cpu family : 6 model : 30 model name : Intel(R) Core(TM) i5-750 CPU @ 2.66GHz

FILE /etc/portage/make.conf COMMON_FLAGS="-march=nehalem -O2 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

Westmere

Core i3/i5/i7 vendor_id : GenuineIntel cpu family : 6 model : 37 model name : Intel(R) Core(TM) i5-650 CPU @ 3.20GHz

FILE /etc/portage/make.conf COMMON_FLAGS="-march=westmere -O2 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

Note
You might need to add -mno-aes -mno-pclmul, especially for i3 (enabled by default). No output means not supported:

user $grep -m1 -e aes -e pclmulqdq /proc/cpuinfo

Intel Core

vendor_id : GenuineIntel cpu family : 6 … model : 15 model name : Intel(R) Core(TM)2 Duo CPU T7500 @ 2.20GHz … model : 15 model name : Intel(R) Xeon(R) CPU 3040 @ 1.86GHz

FILE /etc/portage/make.conf COMMON_FLAGS="-march=core2 -O2 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

Older microarchitecture

Pentium M (Dothan) vendor_id : GenuineIntel cpu family : 6 model : 13 model name : Intel(R) Pentium(R) M processor 2.13GHz

FILE /etc/portage/make.conf COMMON_FLAGS="-O2 -march=pentium-m -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

Pentium 4 (Prescott) 64-bit capable models: 505, 505J, 506, 511, 516, 517, 519K, 521, 524, 531, 541, 551, 561, 571, 6xx and the 3.73(3)GHz Pentium 4 Extreme Edition. Note Check the /proc/cpuinfo for the lm flag to detect 64-bit CPUs: user $grep lm /proc/cpuinfo The cpuid model (4 vs 3) is not an indicator of 64-bit compatibility; there are 32-bit family15/model4 CPUs! vendor_id : GenuineIntel cpu family : 15 model : 4 model name : Intel(R) Pentium(R) 4 CPU XXXGHz

FILE /etc/portage/make.conf COMMON_FLAGS="-O2 -march=nocona -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

All other Prescotts vendor_id : GenuineIntel cpu family : 15 model : 3 model name : Intel(R) Pentium(R) 4 CPU XXXGHz

FILE /etc/portage/make.conf COMMON_FLAGS="-O2 -march=prescott -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

AMD

Ryzen (Zen family)

1000 and 2000 series vendor_id : AuthenticAMD cpu family : 23 model : 1 model name : AMD Ryzen 7 1800X Eight-Core Processor … cpu family : 23 model : 8 model name : AMD Ryzen 7 2700X Eight-Core Processor

FILE /etc/portage/make.conf COMMON_FLAGS="-O2 -march=znver1 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

3000, 4000, 5000, and EPYC 7xx2 series vendor_id : AuthenticAMD cpu family : 23 model : 113 model name : AMD Ryzen 9 3900X 12-Core Processor ... cpu family : 23 model : 49 model name : AMD EPYC 7542 32-Core Processor

FILE /etc/portage/make.conf COMMON_FLAGS="-O2 -march=znver2 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

5000 and EPYC 7xx3 series vendor_id : AuthenticAMD cpu family : 25 model : 80 model name : AMD Ryzen 7 PRO 5850U with Radeon Graphics

FILE /etc/portage/make.conf COMMON_FLAGS="-O2 -march=znver3 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

A6/A8/A9/A10/A12-8XXX/9XXX (Excavator)

Carrizo, Bristol Ridge, and Stoney Ridge vendor_id : AuthenticAMD cpu family : 21 model : 96 or 101 or 112 model name : AMD A12-9800 RADEON R7, 12 COMPUTE CORES 4C+8G

FILE /etc/portage/make.conf COMMON_FLAGS="-O2 -march=bdver4 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

A4/A6/A8/A10-7XXX/8XXX (Steamroller)

Kaveri and Godavari vendor_id : AuthenticAMD cpu family : 21 model : 48 or 56 model name : AMD A10-7850K Radeon R7, 12 Compute Cores 4C+8G Important Various lowpower AMD APUs branded as AX-7XXX (eg. A4-7210) don't belong to cpu family 21!

FILE /etc/portage/make.conf COMMON_FLAGS="-O2 -march=bdver3 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

E1/E2-XXXX, A4/A6/A8/A10-XXXX (Jaguar, Puma)

Kabini, Temash, Beema, Mullins, and Carrizo-L vendor_id : AuthenticAMD cpu family : 22 model : 0 or 48 model name : AMD A4-5000 APU with Radeon(TM) HD Graphics Important Majority of AMD APUs branded as A4/A6/A8-XXXX (eg. A4-5300, A4-4000 or A6-5345M) don't belong to cpu family 22! They should use settings listed for AMD APU model given by the cpu family and model.

FILE /etc/portage/make.conf COMMON_FLAGS="-O2 -march=btver2 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

A4/A6/A8/A10-4XXX/5XXX/6XXX (Piledriver)

Trinity and Richland vendor_id : AuthenticAMD cpu family : 21 model : 16 or 19 model name : AMD A8-4500M APU with Radeon(tm) HD Graphics Important Various low power AMD APUs branded as AX-5XXX/6XXX (eg. A4-5000, A4-5100 or A6-6310) don't belong to CPU family 21!

FILE /etc/portage/make.conf COMMON_FLAGS="-O2 -march=bdver2 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

FX-XXXX

Bulldozer and Piledriver vendor_id : AuthenticAMD cpu family : 21 model : 1 or 2 model name : AMD FX(tm)-8150 Eight-Core Processor Important Make sure and check the number listed by model on the system, the -march flag should be bdverX where X is the model number. Important Various AMD APUs branded as FX don't match model 1 or 2! They should use settings listed for AMD APU model given by the cpu family and model.

FILE /etc/portage/make.conf COMMON_FLAGS="-O2 -march=bdver1 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

Z-XX, C-X0, E-XX0, E1/E2-1X00, E2-2000 (Bobcat)

Ontario, Hondo, Desna, and Zacate vendor_id : AuthenticAMD cpu family : 20 model : 1 or 2 model name : AMD E-350 Processor

FILE /etc/portage/make.conf COMMON_FLAGS="-O2 -march=btver1 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

A4/A6/A8-3XXX/3XXXM (12h)

Llano vendor_id : AuthenticAMD cpu family : 18 model : 1 model name : AMD A8-3500M APU with Radeon(tm) HD Graphics

FILE /etc/portage/make.conf COMMON_FLAGS="-O2 -march=amdfam10 -mcx16 -mpopcnt -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

Phenom/Phenom II, Athlon II, Sempron (10h)

Agena, Deneb, Thuban, and derivatives vendor_id : AuthenticAMD cpu family : 16 model : X model name : AMD Phenom(tm) II X6 1090T Processor

FILE /etc/portage/make.conf COMMON_FLAGS="-O2 -march=amdfam10 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

Older microarchitectures

Important
Various AMD CPUs branded as Sempron (eg. Sempron 2200+ or Sempron 3000+) don't belong to cpu family 15!

E+ revisions - Athlon 64, Athlon 64 X2/FX, Sempron (0Fh) vendor_id : AuthenticAMD cpu family : 15 model : >= 39 model name : AMD Athlon(tm) 64 X2 Dual Core Processor 4200+

FILE /etc/portage/make.conf COMMON_FLAGS="-O2 -march=opteron-sse3 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

Geode LX vendor_id : AuthenticAMD cpu family : 5 model : 10 model name : Geode(TM) Integrated Processor by AMD PCS

FILE /etc/portage/make.conf CHOST="i486-pc-linux-gnu" COMMON_FLAGS="-Os -pipe -march=geode -mmmx -m3dnow -fomit-frame-pointer" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

Pre-E revisions - Athlon 64, Athlon 64 FX, Sempron (0Fh) vendor_id : AuthenticAMD cpu family : 15 model : < 39 model name : AMD Athlon(tm) 64 Processor 3200+

FILE /etc/portage/make.conf COMMON_FLAGS="-O2 -march=opteron -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

ARM

Note
To identify the respective ARM core of the SoC on your board, List of ARM microarchitectures and List of applications of ARM cores on Wikipedia may help.

Cortex-A

ARMv7-A/Cortex-A9 MPCore

with optional VFPv3 FPU processor : 0 model name : ARMv7 Processor rev 0 (v7l) BogoMIPS : 2.00 Features : half thumb fastmult vfp edsp vfpv3 vfpv3d16 tls CPU implementer : 0x41 CPU architecture: 7 CPU variant : 0x1 CPU part : 0xc09 CPU revision : 0 processor : 1 model name : ARMv7 Processor rev 0 (v7l) BogoMIPS : 2.00 Features : half thumb fastmult vfp edsp vfpv3 vfpv3d16 tls CPU implementer : 0x41 CPU architecture: 7 CPU variant : 0x1 CPU part : 0xc09 CPU revision : 0 Hardware : NVIDIA Tegra SoC (Flattened Device Tree) Revision : 0000 Serial : 0000000000000000 Note This ARM core (equipped with the optional vfpv3d16 FPU but missing the NEON extension) is used in the Toshiba AC100/Dynabook AZ/Compal Paz00 Board.

FILE /etc/portage/make.conf CHOST="armv7a-hardfloat-linux-gnueabi" COMMON_FLAGS="-O2 -march=cortex-a9 -mfpu=vfpv3-d16 -mfloat-abi=hard -pipe -fomit-frame-pointer" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

ARMv8-A/BCM2837

Note
This is the Broadcom chip used in the Raspberry Pi 3 Model B.

AArch32 with neon FPU processor : 0-3 model name : ARMv7 Processor rev 4 (v7l) BogoMIPS : 38.40 Features : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae evtstrm crc32 CPU implementer : 0x41 CPU architecture: 7 CPU variant : 0x0 CPU part : 0xd03 CPU revision : 4 Hardware : BCM2709 Revision : 0000 Serial : 0000000000000000

FILE /etc/portage/make.conf CHOST="armv7a-hardfloat-linux-gnueabi" COMMON_FLAGS="-O2 -pipe -march=armv7-a -mfpu=neon-vfpv4 -mfloat-abi=hard" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

AArch64 processor : 0-3 BogoMIPS : 38.40 Features : fp asimd evtstrm crc32 CPU implementer : 0x41 CPU architecture: 8 CPU variant : 0x0 CPU part : 0xd03 CPU revision : 4

FILE /etc/portage/make.conf COMMON_FLAGS="-march=armv8-a+crc -mtune=cortex-a53 -O2 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

ARM11

ARMv6/ARM1176JZF-S

Note This ARM core is used in the first generation of the Raspberry Pi. processor : 0 model name : ARMv6-compatible processor rev 7 (v6l) BogoMIPS : 697.95 Features : half thumb fastmult vfp edsp java tls CPU implementer : 0x41 CPU architecture: 7 CPU variant : 0x0 CPU part : 0xb76 CPU revision : 7 Hardware : BCM2835 Revision : 0000 Serial : 000000000XXXXXXX

FILE /etc/portage/make.conf CHOST="armv6j-hardfloat-linux-gnueabi" COMMON_FLAGS="-O2 -pipe -mcpu=arm1176jzf-s -mfpu=vfp -mfloat-abi=hard" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

ARMv6/ARM1136JF-S

Processor : ARMv6-compatible processor rev 5 (v6l) BogoMIPS : 791.34 Features : swp half thumb fastmult vfp edsp java CPU implementer : 0x41 CPU architecture: 6TEJ CPU variant : 0x1 CPU part : 0xb36 CPU revision : 5 Hardware : IMAPX200 Revision : 0000 Serial : 0000000000000000

FILE /etc/portage/make.conf CHOST="armv6j-hardfloat-linux-gnueabi" COMMON_FLAGS="-Os -mcpu=arm1136jf-s -mfpu=vfp -mfloat-abi=hard -pipe -fomit-frame-pointer" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

ppc/ppc64

Important
-march= is not supported on the PowerPC (and RS/6000) instruction set architecture (ISA). Use -mcpu= and -mtune= instead.

Note
Using -mcpu=native (and/or -mtune=native) should work on PowerPC but is not recommended due to distcc.

POWER8

processor : 0 cpu : POWER8E (raw), altivec supported clock : 3026.000000MHz revision : 2.1 (pvr 004b 0201) timebase : 512000000 platform : pSeries model : IBM pSeries (emulated by qemu) machine : CHRP IBM pSeries (emulated by qemu)

FILE /etc/portage/make.conf COMMON_FLAGS="-mcpu=power8 -O2 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

Cell

processor : 0 cpu : Cell Broadband Engine, altivec supported clock : 3192.000000MHz revision : 5.1 (pvr 0070 0501) processor : 1 cpu : Cell Broadband Engine, altivec supported clock : 3192.000000MHz revision : 5.1 (pvr 0070 0501) timebase : 79800000 platform : PS3 model : SonyPS3

FILE /etc/portage/make.conf COMMON_FLAGS="-mcpu=cell -O2 -pipe -mabi=altivec -maltivec" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}" Note GCC's -mspe and -mabi=spe options are not targetting PS3 systems and IBM Cell. Instead, those options are dedicated to IBM e500. More info: https://lists.debian.org/debian-devel/2011/06/msg00592.html https://wiki.debian.org/PowerPCSPEPort

PPC 970 (G5)

Compatible processors are IBM PPC970, PPC970FX, PPC970MP and PPC970GX.

cpu : PPC970, altivec supported clock : 1800MHz revision : 2.2 (pvr 0039 0202) bogomips : 1127.21 machine : PowerMac7,2 motherboard : PowerMac7,2 MacRISC4 Power Macintosh board revision : 00000001 detected as : 336 (PowerMac G5) pmac flags : 00000000 L2 cache : 512K unified pmac-generation : NewWorld

FILE /etc/portage/make.conf COMMON_FLAGS="-mcpu=970 -O2 -maltivec -mabi=altivec -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

G4 (PPC 74xx)

PPC 7450 family

Compatible processors are Motorola/Freescale MPC7450, MPC7440, MPC7451, MPC7441, MPC7455, MPC7445, MPC7457, MPC7447, MPC7447/A, and MPC7448.

processor : 0 cpu : 7447A, altivec supported clock : 1666.666000MHz revision : 1.5 (pvr 8003 0105) bogomips : 33.28 timebase : 8320000 platform : PowerMac model : PowerBook5,9 machine : PowerBook5,9 motherboard : PowerBook5,9 MacRISC3 Power Macintosh detected as : 287 (PowerBook G4 17") pmac flags : 00000018 L2 cache : 512K unified pmac-generation : NewWorld

FILE /etc/portage/make.conf COMMON_FLAGS="-mcpu=7450 -O2 -maltivec -mabi=altivec -fno-strict-aliasing -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

PPC 7400 family

Compatible processors are Motorola MPC7400 and MPC7410. Note: IBM manufactured the MPC7400 as 06K5319 and 10K8298 when Motorola was not able to fulfill Apple's demands.

processor : 0 cpu : 7400, altivec supported clock : 400.000000MHz revision : 2.9 (pvr 000c 0209) bogomips : 49.66 timebase : 24908583 platform : PowerMac machine : PowerMac3,1 motherboard : PowerMac3,1 MacRISC Power Macintosh detected as : 65 (PowerMac G4 AGP Graphics) pmac flags : 00000004 L2 cache : 1024K unified pmac-generation : NewWorld

FILE /etc/portage/make.conf COMMON_FLAGS="-mcpu=7400 -O2 -maltivec -mabi=altivec -fno-strict-aliasing -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

G3 (PPC 7XX)

Compatible processors are Motorola/Freescale MPC750, MPC740, MPC755 and MPC745 as well as IBM PPC750, PPC740, PPC750L, PPC740L, PPC750CX, PPC750CXe, PPCDBK ("Gekko"), PPC750FX, PPC750GX, PPC750CXr, PPC750CL ("Broadway"), PPC750GL and PPC750FL. The BAE Systems RAD750 is a radiation hardened variant of the PPC750. The "Espresso" (following the "Gekko" and "Broadway") is also based on the PPC750.

For CPUs for embedded systems such as the Gekko (PPCDBK, used in the Nintendo GameCube) additional CFLAGS (like -meabi) will be required.

processor : 0 cpu : 740/750 clock : 400.000000MHz revision : 131.0 (pvr 0008 8300) bogomips : 49.93 timebase : 24966218 platform : PowerMac model : PowerBook3,1 machine : PowerBook3,1 motherboard : PowerBook3,1 MacRISC2 MacRISC Power Macintosh detected as : 70 (PowerBook Pismo) pmac flags : 0000001f L2 cache : 1024K unified pmac-generation : NewWorld

FILE /etc/portage/make.conf COMMON_FLAGS="-mcpu=750 -Os -pipe -fno-strict-aliasing" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

RISC-V

processor     : 0 hart         : 1 isa         : rv64imafdc mmu         : sv39 uarch         : sifive,u74-mc

FILE /etc/portage/make.conf COMMON_FLAGS="-march=rv64imafdc_zicsr_zba_zbb -mcpu=sifive-u74 -mtune=sifive-7-series -O2 -pipe" CFLAGS="${COMMON_FLAGS}" CXXFLAGS="${COMMON_FLAGS}"

See also

• GCC optimization — an introduction to optimizing compiled code using safe, sane CFLAGS and CXXFLAGS.
• Gentoo documentation page on backtraces
• CFLAGS_and_CXXFLAGS (AMD64 Handbook)

External resources

• GCC Online Documentation on GNU.org
• GCC x86 performance hints from Intel
• List of AMD Microarchitectures with extended info
• List of Intel Microarchitectures with extended info