1
0
mirror of https://github.com/google/cpu_features.git synced 2025-07-02 05:33:17 +02:00
Commit Graph

124 Commits

Author SHA1 Message Date
108f3d9eca Fix #140 Atom processor detected as X86_UNKNOWN (#160) 2021-06-22 11:12:02 +02:00
bc2846e78f Detect AVX512 on Darwin use GetDarwinSysCtlByName("hw.optional.avx512f") (#153) 2021-05-21 11:14:50 +02:00
d35e2f38eb Detect Intel's Multi-Precision Add-Carry Instruction Extensions (#157) 2021-05-21 10:47:32 +02:00
7ed0b0e50e Detect Zen 3 (K19) cpus (#152)
Co-authored-by: natanbc <natanbc@users.noreply.github.com>
2021-02-25 21:47:39 +01:00
e2f6dea65f Update AArch64 features to Linux 5.10 (#149)
Added feature: MTE.
2020-12-15 13:28:53 +01:00
cdab59af76 [NFC] Simplify build by removing inl files. (#139) 2020-10-13 13:05:04 +02:00
9a8f04b24c [NFC] Generate separate tables via macro (#137)
This is a non functional change, it allows:
 - Getting rid of `unix_features_aggregator`
 - Have a single blob describing the features
 - Fix wrong mocking of `hwcaps`

Downside: abuse of macros makes the code slightly magical and harder to understand.
It think it's still an improvement over the current situation as there's less repetition and less chances to get something wrong.
2020-10-12 09:50:35 +00:00
3cc8f310d9 [NFC] Update copyright from Google Inc. to Google LLC 2020-10-12 08:55:20 +00:00
c0885fec9b docs: fix simple typo, intented -> intended (#138)
There is a small typo in src/utils/list_cpu_features.c.

Should read `intended` rather than `intented`.
2020-10-12 07:20:05 +00:00
e63405f118 Remove need for utsname (#136) 2020-10-09 20:40:06 +00:00
4795373db2 Fix SSE detection on non-AVX CPUs (#135)
Fixes #4. This is based on #115 with a few modifications:
 - Removed use of __builtin_cpu_supports since it relies on cpuid and doesn't improve on the current situation,
 - Added detection for all of sse, sse2, sse3, ssse3, sse4_1 and sse4_2,
 - Added tests for Atom, Nehalem, and P3 processors,

Thx to @gadoofou87 for providing the original PR.
It also removes the need for #92

* Fix SSE detection on non-AVX CPUs
* Fixes typo
* Mock OSX sysctlbyname in tests
* Also update other tests
* FakeCpu is reset between each tests
* Fix conflicting name on Windows
* Disable pre AVX cpu sse detection tests on Windows
* Guard OS specific code with macros
* Fix missing import for tests
* Fix wrong function prototype
* Fix wrong mocking of P3 on Windows
* Completely guard OS specific parts in x86 tests
* Store DWORD instead unsigned long for x86 tests
2020-10-09 15:20:25 +00:00
22a5362e11 [NFC] clang-format codebase (#134)
* [NFC] clang-format codebase

* revert to 80 char columns at the price of uglier table init

* Specifically disabling clang-format for table initialization
2020-09-23 09:52:20 +00:00
17ffb65117 detect AVX-512 FMA count (#125)
* add Ice Lake Server and Sapphire Rapids models

The information contained in this commit was obtained from
"Intel® Architecture Instruction Set Extensions and Future Features Programming Reference" document 319433-040 from
https://software.intel.com/content/www/us/en/develop/download/intel-architecture-instruction-set-extensions-programming-reference.html

Signed-off-by: Jeff Hammond <jeff.r.hammond@intel.com>

* Tiger Lake; Ice Lake NNP-I; SPR string

Signed-off-by: Hammond, Jeff R <jeff.r.hammond@intel.com>

* second FMA features - incomplete and wrong

Signed-off-by: Hammond, Jeff R <jeff.r.hammond@intel.com>

* oops: use T/F not 2/1

Signed-off-by: Jeff Hammond <jeff.r.hammond@intel.com>

* implement SKX lookup

Signed-off-by: Hammond, Jeff R <jeff.r.hammond@intel.com>

* add Intel copyright

* cleanup AVX512 second FMA code

1) remove debug stuff
2) remove ICX - will add details when available

Signed-off-by: Hammond, Jeff R <jeff.r.hammond@intel.com>

* fix CPX detection

Signed-off-by: Hammond, Jeff R <jeff.r.hammond@intel.com>

* remove elses

Signed-off-by: Hammond, Jeff R <jeff.r.hammond@intel.com>

* remove curly braces from single-line conditional bodies

Signed-off-by: Hammond, Jeff R <jeff.r.hammond@intel.com>

* apply clang-format

Signed-off-by: Hammond, Jeff R <jeff.r.hammond@intel.com>

Fixes #120
2020-09-22 07:29:46 +00:00
76dafc7e3b [NFC] Remove unused max_cpuid_leaf variable (#131) 2020-09-21 14:54:13 +02:00
33bd72c1bc detect future Intel AVX/AMX features (#124)
* add Ice Lake Server and Sapphire Rapids models

The information contained in this commit was obtained from
"Intel® Architecture Instruction Set Extensions and Future Features Programming Reference" document 319433-040 from
https://software.intel.com/content/www/us/en/develop/download/intel-architecture-instruction-set-extensions-programming-reference.html

Signed-off-by: Jeff Hammond <jeff.r.hammond@intel.com>

* Tiger Lake; Ice Lake NNP-I; SPR string

Signed-off-by: Hammond, Jeff R <jeff.r.hammond@intel.com>

* add AVX512_BF16 and AVX512_VP2INTERSECT detection

Signed-off-by: Hammond, Jeff R <jeff.r.hammond@intel.com>

* correction for KNM features: s/4VBMI2/4FMAPS/g

Signed-off-by: Hammond, Jeff R <jeff.r.hammond@intel.com>

* add AMX/TMUL bits from 319433-040

Signed-off-by: Hammond, Jeff R <jeff.r.hammond@intel.com>

* add Intel copyright

Fixes #128
2020-09-21 07:56:26 +00:00
e698327713 add future Intel microarchitectures (#123)
* add Ice Lake Server and Sapphire Rapids models

The information contained in this commit was obtained from
"Intel® Architecture Instruction Set Extensions and Future Features Programming Reference" document 319433-040 from
https://software.intel.com/content/www/us/en/develop/download/intel-architecture-instruction-set-extensions-programming-reference.html

Signed-off-by: Jeff Hammond <jeff.r.hammond@intel.com>

* Tiger Lake; Ice Lake NNP-I; SPR string

Signed-off-by: Hammond, Jeff R <jeff.r.hammond@intel.com>

* add Intel copyright

Fix #127
2020-09-21 07:54:58 +00:00
73d10ad25b Update features for AArch64 to Linux 5.8 (#122)
This adds the following features: dcpodp, sve2, sveaes, svepmull,
svebitperm, svesha3, svesm4, flagm2, frint, svei8mm, svef32mm,
svef64mm, svebf16, i8mm, bf16, dgh and rng.

With these, all features used by Linux 5.8 on AArch64 is supported.

Fixes #126
2020-09-21 07:50:38 +00:00
339bfd32be Add OsSupport structure 2020-03-12 10:58:41 +00:00
404e462cd4 Move AMD extra flags to its own function 2020-03-12 10:58:41 +00:00
3262a55118 Support x86 FMA4 and SSE4A features 2020-03-12 10:58:41 +00:00
5d55aa1efe Add cache_info data to X86 for list_cpu_features (#105)
* Add cache_info data to X86 for list_cpu_features
2020-01-29 15:02:48 +01:00
e50d7db3b0 [NFC] Use Designated Initializers 2020-01-29 11:31:10 +01:00
24b8a1de17 Add INTEL_WHL and INTEL_ICL to uarch get name function 2020-01-07 10:18:04 +01:00
3d71a964f5 Use a getter function to avoid manual work for future to-be-added cpu features 2020-01-06 16:24:10 +01:00
73a121b1ae Differentiate between different Lake uarch 2020-01-06 16:23:29 +01:00
8a6fd87074 [NFC] Fixed signed shift
signed shift result (0x80000000) sets the sign bit of the shift expression's type ('int') and becomes negative
2019-11-13 14:39:06 +01:00
99d2363c62 [NFC] fix various errors 2019-11-13 11:22:31 +01:00
be306b7b15 [NFC] fix unused and shadowing variables 2019-11-13 11:15:40 +01:00
9d2de7fb5c Making sure global variable is aligned without using attributes 2019-11-12 17:12:44 +01:00
7298eda2ff Making sure global variable is 8B aligned as well 2019-11-12 16:53:04 +01:00
0f2f60ab00 Address comments in https://github.com/google/cpu_features/pull/94 2019-11-12 16:26:00 +01:00
64b1b9090f [NFC] Use a tree structure in list_cpu_features
This is in preparation to include cache hierarchy in the dumped data.
2019-11-12 14:00:19 +01:00
d835b4958c Update features for AArch64.
Add all missing features up to Linux v5.0.

Features added: evtstrm, atomics, fphp, asimdhp, cpuid, asimdrdm,
jscvt, fcma, lrcpc, dcpop, sha3, sm3, sm4, asimddp, sha512, sve,
asimdfhm, dit, uscat, ilrcpc, flagm, ssbs, sb, paca, pacg.
2019-10-11 11:02:00 +02:00
22c05ed620 Use enum properly to directly access kConfig struct 2019-07-04 21:25:14 +02:00
bdb36d9489 Fix a few compile warnings (#84)
Visual C++ reported a number of warnings:

..\src\filesystem.c(27): warning C4996: '_open': This function or variable may be unsafe. Consider using _sopen_s instead. To disable deprecation, use _CRT_SECURE_NO_WARNINGS. See online help for details.
..\src\filesystem.c(34): warning C4267: 'function': conversion from 'size_t' to 'unsigned int', possible loss of data
..\src\string_view.c(25): warning C4244: 'return': conversion from '__int64' to 'int', possible loss of data
..\src\string_view.c(41): warning C4244: 'return': conversion from '__int64' to 'int', possible loss of data
..\src\utils\list_cpu_features.c(151): warning C4090: 'function': different 'const' qualifiers
..\src\cpuinfo_x86.c(67): warning C4244: 'return': conversion from 'unsigned __int64' to 'uint32_t', possible loss of data
..\test\filesystem_for_testing.cc(48): warning C4267: 'return': conversion from 'size_t' to 'int', possible loss of data
..\test\filesystem_for_testing.cc(57): warning C4267: 'argument': conversion from 'size_t' to 'int', possible loss of data
..\test\bit_utils_test.cc(26): warning C4267: 'argument': conversion from 'size_t' to 'uint32_t', possible loss of data
..\test\bit_utils_test.cc(32): warning C4267: 'argument': conversion from 'size_t' to 'uint32_t', possible loss of data
..\test\bit_utils_test.cc(37): warning C4267: 'argument': conversion from 'size_t' to 'uint32_t', possible loss of data

Most of them, with the exception of _open() -> _sopen_s() are about
questionable implicit casts. Fixing the types and adding explicit casts
to explicitly mark the intention (and silence the warnings in the process)
2019-07-03 14:57:19 +02:00
653d581e03 Add support for leaf2 and leaf4 on Intel's x86 arch (#80)
* Add support for leaf4 on Intel's x86 arch
* Update cpuinfo_x86.h
* Fix typo
* Force compiler to use C99
* Add Intel x86 leaf2 support
* Fixes after review
* Fix review comments
2019-07-02 16:52:25 +02:00
bfd109b687 Completed all missing ARM hwcaps. (#79) 2019-06-26 12:56:52 +02:00
18342789a1 Fix ARMv6 on Linux vs Android (#81) 2019-06-25 17:58:31 +02:00
bfb4cf99cc Add CpuIdEx function to pass inputs in ecx register (required for E.g. leaf4) (#77) 2019-06-21 14:13:29 +02:00
3ee4a9e801 Support x86 DCA and SS features (#76)
* Add dca and ss features
* Remove trailing white spaces
2019-06-19 15:06:05 +02:00
6482bad213 Added RPI zero with its features HALF, THUMB, FASTMULT, EDSP, JAVA and TLS (#75) 2019-06-18 12:53:08 +02:00
367bc42116 Support x86 features: FPU, TSC, CX8, CLFSH, MMX, VAES, HLE, RTM, RDSEED, CLFLUSHOPT, CLWB, SSE, SSE2, SSE3, PCLMULQDQ (#73) 2019-06-13 11:53:39 +02:00
084ec5cd0f Convert XGETBV to equivalent byte form in GetXCR0Eax (#69)
osxcross (https://github.com/tpoechtrager/osxcross) gives the following error, which also happens with regular gcc on OS X (https://github.com/asmjit/asmjit/issues/78):
```
cpu_features/src/cpuinfo_x86.c:44:no such instruction: `XGETBV'
```
2019-03-20 10:04:24 +01:00
d395dfa026 Add x86 missing feature detections for ndk_compat (#58)
One more step towards #47.
2019-01-22 13:19:42 +01:00
5911e96bbd add r6 flag (#57)
Update tests and add support in ndk-compat as well
2019-01-22 11:00:48 +01:00
9917e8481e Fix hwcaps constants for mips. (#60)
fixes #59
2019-01-21 10:39:24 +01:00
4155ee7e36 Guarding header use with architecture (#56) 2019-01-18 13:38:22 +01:00
dfdac6adfc Add partial implementation of ndk_compat (#54)
* First implementation of ndk_compat
* Restrict building of linux_based_hardware_detection to UNIX
* Fix variable declaration and printf formatting
* Restrict ndk compat to UNIX style systems
* Restrict cpu_mask index to 32
* Fix values display in ndk-compat-test
* Addressing comments
2019-01-17 18:00:21 +01:00
918553a21f Export GetArmCpuId function 2019-01-17 15:28:04 +01:00
122b067087 Use Cmake macros to detect getauxval and dlopen 2019-01-15 15:18:08 +01:00