llvm-6502/test
Chandler Carruth bd357588a1 [x86] Teach the x86 vector shuffle lowering to detect mergable 128-bit
lanes.

By special casing these we can often either reduce the total number of
shuffles significantly or reduce the number of (high latency on Haswell)
AVX2 shuffles that potentially cross 128-bit lanes. Even when these
don't actually cross lanes, they have much higher latency to support
that. Doing two of them and a blend is worse than doing a single insert
across the 128-bit lanes to blend and then doing a single interleaved
shuffle.

While this seems like a narrow case, it kept cropping up on me and the
difference is *huge* as you can see in many of the test cases. I first
hit this trying to perfectly fix the interleaving shuffle patterns used
by Halide for AVX2.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@222533 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-21 13:56:05 +00:00
..
Analysis Revert r222039 because of bot failure. 2014-11-19 00:13:26 +00:00
Assembler Use FileCheck in a few tests. 2014-11-06 15:05:51 +00:00
Bindings
Bitcode
BugPoint
CodeGen [x86] Teach the x86 vector shuffle lowering to detect mergable 128-bit 2014-11-21 13:56:05 +00:00
DebugInfo Remove triple in testing case to recover an arm bot. 2014-11-18 16:45:34 +00:00
ExecutionEngine MCJIT tests passing on ARM after r222414 fixed the relocation 2014-11-20 13:32:16 +00:00
Feature
FileCheck
Instrumentation [asan] Add new hidden compile-time flag asan-instrument-allocas to sanitize variable-sized dynamic allocas. Patch by Max Ostapenko. 2014-11-21 10:29:50 +00:00
Integer
JitListener
Linker IR: Simplify uniquing for MDNode 2014-11-17 23:28:21 +00:00
LTO Add Forward Control-Flow Integrity. 2014-11-11 21:08:02 +00:00
MC [ELF] Prevent ARM ELF object writer from generating deprecated relocation code R_ARM_PLT32 2014-11-20 05:58:11 +00:00
Object Object, support both mach-o archive t.o.c file names 2014-11-12 01:37:45 +00:00
Other
SymbolRewriter Transform: add SymbolRewriter pass 2014-11-07 21:32:08 +00:00
TableGen
tools [ELF] Prevent ARM ELF object writer from generating deprecated relocation code R_ARM_PLT32 2014-11-20 05:58:11 +00:00
Transforms SROA: The alloca type isn't a candidate promotion type for vectors 2014-11-21 02:34:55 +00:00
Unit
Verifier
YAMLParser
.clang-format
CMakeLists.txt
lit.cfg Only run the gold plugin tests if gold supports the targets we test with. 2014-11-11 05:27:12 +00:00
lit.site.cfg.in
Makefile OCAMLFLAGS can contain =, don't use = with sed 2014-11-13 09:29:30 +00:00
Makefile.tests
TestRunner.sh