Commit Graph

52 Commits

Author SHA1 Message Date
Kai Nacke b38bf9626a Add support for krait cpu in llvm::sys::getHostCPUName()
Recently, support for krait cpu was added. This commit extends getHostCPUName()
to return krait as cpu for the APQ8064 (a Krait 300).

llvm-svn: 197792
2013-12-20 09:24:13 +00:00
Rafael Espindola b75ea019ea Fix Typo.
llvm-svn: 197168
2013-12-12 16:17:40 +00:00
Rafael Espindola 1f58e4dc11 Convert the other getHostByName implementations to StringRef.
llvm-svn: 197166
2013-12-12 16:10:48 +00:00
Rafael Espindola 74f444cde5 Return a StringRef from getHostCPUName.
llvm-svn: 197158
2013-12-12 15:45:32 +00:00
Benjamin Kramer 583b00e60a Make helper function static.
llvm-svn: 195650
2013-11-25 15:40:24 +00:00
Tim Northover 89ccb616bd X86: enable AVX2 under Haswell native compilation
Patch by Adam Strzelecki

llvm-svn: 195632
2013-11-25 09:52:59 +00:00
Benjamin Kramer d114def3d6 X86: Add a description for AMD bdver3 aka Steamroller.
This is just bdver2 + FSGSBase.

llvm-svn: 193984
2013-11-04 10:29:20 +00:00
Richard Sandiford f834ea19db [SystemZ] Automatically detect zEC12 and z196 hosts
As on other hosts, the CPU identification instruction is priveleged,
so we need to look through /proc/cpuinfo.  I copied the PowerPC way of
handling "generic".

Several tests were implicitly assuming z10 and so failed on z196.

llvm-svn: 193742
2013-10-31 12:14:17 +00:00
Preston Gurd 3fe264d625 Adds support for Atom Silvermont (SLM) - -march=slm
Implements Instruction scheduler latencies for Silvermont,
using latencies from the Intel Silvermont Optimization Guide.

Auto detects SLM.

Turns on post RA scheduler when generating code for SLM.

llvm-svn: 190717
2013-09-13 19:23:28 +00:00
Benjamin Kramer 8f429384b5 X86: Add a description of the Intel Atom Silvermont CPU.
Currently this is just the atom model with SSE4.2 enabled.

llvm-svn: 189669
2013-08-30 14:05:32 +00:00
Reid Kleckner bf4f9ebb9f Actually, use GNU inline asm for cpuid with clang
Clang doesn't support the MSVC __cpuid intrinsic yet, and fixing that is
blocked on some fairly complicated issues.

llvm-svn: 188584
2013-08-16 22:42:42 +00:00
Reid Kleckner be85cb9098 Use the MSVC __cpuid intrinsic instead of inline asm
This works around PR16830 in LLVM when self-hosting clang on Windows.

llvm-svn: 188397
2013-08-14 18:21:51 +00:00
Benjamin Kramer fb34989a82 Some Intel Penryn CPUs come with SSE4 disabled. Detect them as core 2.
PR16721.

llvm-svn: 187350
2013-07-29 11:02:08 +00:00
Duncan Sands e2cd13906e Ensure sys::getProcessTriple always uses a normalized triple. Patch by
Thomas B. Jablin, from PR16636.

llvm-svn: 186501
2013-07-17 11:01:05 +00:00
Tobias Grosser bd9e549e21 Make host ARM CPU feature detection independent of the vendor
For ARM on linux we use /proc/cpuinfo to detect the host CPU's features.
Linux derives these values without ever looking at the vendor of the
specific CPU implementation. Hence, it adds little value, if we parse
the output of /proc/cpuinfo only for certain vendors.

This patch enables us to derive the correct feature flags e.g. for Qualcomm
CPUs.

llvm-svn: 183790
2013-06-11 21:45:01 +00:00
Tim Northover fee13d1e11 Allow host triple to be correctly overridden in CMake builds
The intended semantics mirror autoconf, where the user is able to
specify a host triple, but if it's left to the build system then
"config.guess" is invoked for the default.

This also renames the LLVM_HOSTTRIPLE define to LLVM_HOST_TRIPLE to
fit in with the style of the surrounding defines.

llvm-svn: 181112
2013-05-04 07:36:23 +00:00
Benjamin Kramer b44c4275d5 X86: Add target description for btver2; make autodetection logic aware of AVX.
llvm-svn: 181005
2013-05-03 10:20:08 +00:00
Aaron Ballman 31c0adc68c Testing for _XCR_XFEATURE_ENABLED_MASK instead of a specific MSVC version because some MSVC 2010 SP1 installations do not have the _xgetbv intrinsic. Patch thanks to Serge Pavlov!
llvm-svn: 180125
2013-04-23 17:38:44 +00:00
Craig Topper 7af39d7de0 Convert windows line endings to linux/unix line endings.
llvm-svn: 179995
2013-04-22 05:38:01 +00:00
Aaron Ballman 5e6d20524a Ensuring that both bits are set, and not just a combination of one or the other.
llvm-svn: 178674
2013-04-03 18:00:22 +00:00
Aaron Ballman edc03c660c Testing for Visual Studio 2010 SP1 or greater before calling the _xgetbv intrinsic. This also fixes a minor code formatting issue.
llvm-svn: 178666
2013-04-03 16:28:24 +00:00
Aaron Ballman 5f7c680fdc Second pass at addressing PR15351 by explicitly checking for AVX support
when getting the host processor information.  It emits a .byte sequence on GNUC compilers to work around lack of xgetbv support with older assemblers, and resolves a comment typo found in the previous patch.

llvm-svn: 178636
2013-04-03 12:25:06 +00:00
Aaron Ballman 9c0f0af54f Rolling back the AVX support patch due to breaking a gcc 4.6 build bot that doesn't understand the xgetbv instruction for some reason. Will revisit when time permits.
llvm-svn: 178614
2013-04-03 03:11:39 +00:00
Aaron Ballman 56be6ba5e4 Attempting to fix the build on older GCC versions.
llvm-svn: 178604
2013-04-03 01:39:37 +00:00
Aaron Ballman 6bc0dfc7bd This patch addresses PR15351 by explicitly checking for AVX support
when getting the host processor information.

llvm-svn: 178598
2013-04-03 00:33:32 +00:00