Chandler Carruth 050d187bc8 [x86] Begin a significant overhaul of how vector lowering is done in the ... x86 backend. This sketches out a new code path for vector lowering, hidden behind an off-by-default flag while it is under development. The fundamental idea behind the new code path is to aggressively break down the problem space in ways that ease selecting the odd set of instructions available on x86, and carefully avoid scalarizing code even when forced to use older ISAs. Notably, this starts off restricting itself to SSE2 and implements the complete vector shuffle and blend space for 128-bit vectors in SSE2 without scalarizing. The plan is to layer on top of this ISA extensions where we can bail out of the complex SSE2 lowering and opt for a cheaper, specialized instruction (or set of instructions). It also needs to be generalized to AVX and AVX512 vector widths. Currently, this does a decent but not perfect job for SSE2. There are some specific shortcomings that I plan to address: - We need a peephole combine to fold together shuffles where possible. There are cases where a previous shuffle could be modified slightly to arrange for elements to be in the correct position and a later shuffle eliminated. Doing this eagerly added quite a bit of complexity, and so my plan is to combine away these redundancies afterward. - There are a lot more clever ways to use unpck and pack that need to be added. This is essential for real world shuffles as it turns out... Once SSE2 is polished a bit I should be able to get interesting numbers on performance improvements on benchmarks conducive to vectorization. All of this will be off by default until it is functionally equivalent of course. Differential Revision: http://reviews.llvm.org/D4225 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211888 91177308-0d34-0410-b5e6-96231b3b80d8		2014-06-27 11:23:44 +00:00
..
Analysis	Revert "Introduce a string_ostream string builder facilty"	2014-06-26 22:52:05 +00:00
AsmParser	ParseIR: don't take ownership of the MemoryBuffer	2014-06-27 04:33:58 +00:00
Bitcode	IRReader: don't mark MemoryBuffers const	2014-06-27 09:19:14 +00:00
CodeGen	Revert "Revert "Revert "PR20038: DebugInfo: Inlined call sites where the caller has debug info but the call itself has no debug location."""	2014-06-27 05:34:05 +00:00
DebugInfo	Revert "Introduce a string_ostream string builder facilty"	2014-06-26 22:52:05 +00:00
ExecutionEngine	[RuntimeDyld, PowerPC] Fix/improve handling of TOC relocations	2014-06-27 10:32:14 +00:00
IR	Revert "Revert "Revert "PR20038: DebugInfo: Inlined call sites where the caller has debug info but the call itself has no debug location."""	2014-06-27 05:34:05 +00:00
IRReader	IRReader: don't mark MemoryBuffers const	2014-06-27 09:19:14 +00:00
LineEditor
Linker	Replace some assert(0)'s with llvm_unreachable.	2014-06-18 05:05:13 +00:00
LTO	Revert "Introduce a string_ostream string builder facilty"	2014-06-26 22:52:05 +00:00
MC	Revert "Introduce a string_ostream string builder facilty"	2014-06-26 22:52:05 +00:00
Object	Revert "Introduce a string_ostream string builder facilty"	2014-06-26 22:52:05 +00:00
Option	Revert "Introduce a string_ostream string builder facilty"	2014-06-26 22:52:05 +00:00
ProfileData	Renaming SwapByteOrder() to getSwappedBytes()	2014-06-14 11:36:01 +00:00
Support	Revert "Introduce a string_ostream string builder facilty"	2014-06-26 22:52:05 +00:00
TableGen	Revert "Introduce a string_ostream string builder facilty"	2014-06-26 22:52:05 +00:00
Target	[x86] Begin a significant overhaul of how vector lowering is done in the	2014-06-27 11:23:44 +00:00
Transforms	Added instruction combine to transform few more negative values addition to subtraction (Part 3)	2014-06-27 07:47:35 +00:00
CMakeLists.txt
LLVMBuild.txt
Makefile