Add method to TargetInfo to get CPU cache line size

Summary:
This patch adds a virtual method `getCPUCacheLineSize()` to `TargetInfo`. Currently, I've only implemented the method in `X86TargetInfo`. It's extremely important that each CPU's cache line size correct (e.g., we can't just define it as `64` across the board) so, it has been a little slow getting to this point.

I'll work on the ARM CPUs next, but that will probably come later in a different patch.

Tags: #clang

Differential Revision: https://reviews.llvm.org/D74918
This commit is contained in:
zoecarver 2020-03-25 09:48:01 -07:00
parent 7520cf03ee
commit b915aec6b5
3 changed files with 119 additions and 0 deletions

View File

@ -1206,6 +1206,10 @@ public:
"cpu_specific Multiversioning not implemented on this target");
}
// Get the cache line size of a given cpu. This method switches over
// the given cpu and returns "None" if the CPU is not found.
virtual Optional<unsigned> getCPUCacheLineSize() const { return None; }
// Returns maximal number of args passed in registers.
unsigned getRegParmMax() const {
assert(RegParmMax < 7 && "RegParmMax value is larger than AST can handle");

View File

@ -1731,6 +1731,119 @@ bool X86TargetInfo::validateAsmConstraint(
}
}
// Below is based on the following information:
// +------------------------------------+-------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------+
// | Processor Name | Cache Line Size (Bytes) | Source |
// +------------------------------------+-------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------+
// | i386 | 64 | https://www.intel.com/content/dam/www/public/us/en/documents/manuals/64-ia-32-architectures-optimization-manual.pdf |
// | i486 | 16 | "four doublewords" (doubleword = 32 bits, 4 bits * 32 bits = 16 bytes) https://en.wikichip.org/w/images/d/d3/i486_MICROPROCESSOR_HARDWARE_REFERENCE_MANUAL_%281990%29.pdf and http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.126.4216&rep=rep1&type=pdf (page 29) |
// | i586/Pentium MMX | 32 | https://www.7-cpu.com/cpu/P-MMX.html |
// | i686/Pentium | 32 | https://www.7-cpu.com/cpu/P6.html |
// | Netburst/Pentium4 | 64 | https://www.7-cpu.com/cpu/P4-180.html |
// | Atom | 64 | https://www.7-cpu.com/cpu/Atom.html |
// | Westmere | 64 | https://en.wikichip.org/wiki/intel/microarchitectures/sandy_bridge_(client) "Cache Architecture" |
// | Sandy Bridge | 64 | https://en.wikipedia.org/wiki/Sandy_Bridge and https://www.7-cpu.com/cpu/SandyBridge.html |
// | Ivy Bridge | 64 | https://blog.stuffedcow.net/2013/01/ivb-cache-replacement/ and https://www.7-cpu.com/cpu/IvyBridge.html |
// | Haswell | 64 | https://www.7-cpu.com/cpu/Haswell.html |
// | Boadwell | 64 | https://www.7-cpu.com/cpu/Broadwell.html |
// | Skylake (including skylake-avx512) | 64 | https://www.nas.nasa.gov/hecc/support/kb/skylake-processors_550.html "Cache Hierarchy" |
// | Cascade Lake | 64 | https://www.nas.nasa.gov/hecc/support/kb/cascade-lake-processors_579.html "Cache Hierarchy" |
// | Skylake | 64 | https://en.wikichip.org/wiki/intel/microarchitectures/kaby_lake "Memory Hierarchy" |
// | Ice Lake | 64 | https://www.7-cpu.com/cpu/Ice_Lake.html |
// | Knights Landing | 64 | https://software.intel.com/en-us/articles/intel-xeon-phi-processor-7200-family-memory-management-optimizations "The Intel® Xeon Phi™ Processor Architecture" |
// | Knights Mill | 64 | https://software.intel.com/sites/default/files/managed/9e/bc/64-ia-32-architectures-optimization-manual.pdf?countrylabel=Colombia "2.5.5.2 L1 DCache " |
// +------------------------------------+-------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------+
Optional<unsigned> X86TargetInfo::getCPUCacheLineSize() const {
switch (CPU) {
// i386
case CK_i386:
// i486
case CK_i486:
case CK_WinChipC6:
case CK_WinChip2:
case CK_C3:
// Lakemont
case CK_Lakemont:
return 16;
// i586
case CK_i586:
case CK_Pentium:
case CK_PentiumMMX:
// i686
case CK_PentiumPro:
case CK_i686:
case CK_Pentium2:
case CK_Pentium3:
case CK_PentiumM:
case CK_C3_2:
// K6
case CK_K6:
case CK_K6_2:
case CK_K6_3:
// Geode
case CK_Geode:
return 32;
// Netburst
case CK_Pentium4:
case CK_Prescott:
case CK_Nocona:
// Atom
case CK_Bonnell:
case CK_Silvermont:
case CK_Goldmont:
case CK_GoldmontPlus:
case CK_Tremont:
case CK_Westmere:
case CK_SandyBridge:
case CK_IvyBridge:
case CK_Haswell:
case CK_Broadwell:
case CK_SkylakeClient:
case CK_SkylakeServer:
case CK_Cascadelake:
case CK_Nehalem:
case CK_Cooperlake:
case CK_Cannonlake:
case CK_Tigerlake:
case CK_IcelakeClient:
case CK_IcelakeServer:
case CK_KNL:
case CK_KNM:
// K7
case CK_Athlon:
case CK_AthlonXP:
// K8
case CK_K8:
case CK_K8SSE3:
case CK_AMDFAM10:
// Bobcat
case CK_BTVER1:
case CK_BTVER2:
// Bulldozer
case CK_BDVER1:
case CK_BDVER2:
case CK_BDVER3:
case CK_BDVER4:
// Zen
case CK_ZNVER1:
case CK_ZNVER2:
// Deprecated
case CK_x86_64:
case CK_Yonah:
case CK_Penryn:
case CK_Core2:
return 64;
// The following currently have unknown cache line sizes (but they are probably all 64):
// Core
case CK_Generic:
return None;
}
}
bool X86TargetInfo::validateOutputSize(const llvm::StringMap<bool> &FeatureMap,
StringRef Constraint,
unsigned Size) const {

View File

@ -182,6 +182,8 @@ public:
StringRef Name,
llvm::SmallVectorImpl<StringRef> &Features) const override;
Optional<unsigned> getCPUCacheLineSize() const override;
bool validateAsmConstraint(const char *&Name,
TargetInfo::ConstraintInfo &info) const override;