Evan Cheng 82e8360cf3 LLVM sdisel normalize bit extraction of the form: ... ((x & 0xff00) >> 8) << 2 to (x >> 6) & 0x3fc This is general goodness since it folds a left shift into the mask. However, the trailing zeros in the mask prevents the ARM backend from using the bit extraction instructions. And worse since the mask materialization may require an addition instruction. This comes up fairly frequently when the result of the bit twiddling is used as memory address. e.g. = ptr[(x & 0xFF0000) >> 16] We want to generate: ubfx r3, r1, #16, #8 ldr.w r3, [r0, r3, lsl #2] vs. mov.w r9, #1020 and.w r2, r9, r1, lsr #14 ldr r2, [r0, r2] Add a late ARM specific isel optimization to ARMDAGToDAGISel::PreprocessISelDAG(). It folds the left shift to the 'base + offset' address computation; change the mask to one which doesn't have trailing zeros and enable the use of ubfx. Note the optimization has to be done late since it's target specific and we don't want to change the DAG normalization. It's also fairly restrictive as shifter operands are not always free. It's only done for lsh 1 / 2. It's known to be free on some cpus and they are most common for address computation. This is a slight win for blowfish, rijndael, etc. rdar://12870177 llvm-svn: 170581		2012-12-19 20:16:09 +00:00
..
Analysis	Reverse order of checking SSE level when calculating compare cost, so we check	2012-12-18 22:57:56 +00:00
Archive
Assembler	Fast-math test case for bitcode and textual reading/writing	2012-11-27 00:45:08 +00:00
Bindings/Ocaml	Move TargetData to DataLayout.	2012-10-08 16:39:34 +00:00
Bitcode	Change encoding of instruction operands in bitcode binaries to be relative	2012-10-11 20:20:40 +00:00
BugPoint	Fix unexpected passes. These test do work with LTO on linux. I tested both	2012-10-26 02:19:02 +00:00
CodeGen	LLVM sdisel normalize bit extraction of the form:	2012-12-19 20:16:09 +00:00
DebugInfo	Add support for passing -main-file-name all the way through to	2012-12-18 00:31:01 +00:00
ExecutionEngine	llvm/test/ExecutionEngine/MCJIT/lit.local.cfg: ppc32-elf is not ready.	2012-11-20 10:49:01 +00:00
Feature	Remove the dependent libraries feature.	2012-11-27 09:55:56 +00:00
FileCheck	Fix a bug in FileCheck that wouldn't let define variables as follows:	2012-12-02 16:02:41 +00:00
Instrumentation	[msan] Heuristically instrument unknown intrinsics.	2012-12-19 11:22:04 +00:00
Integer	Remove the dependent libraries feature.	2012-11-27 09:55:56 +00:00
JitListener	Use the 'count' attribute to calculate the upper bound of an array.	2012-12-04 21:34:03 +00:00
Linker	Remove the dependent libraries feature.	2012-11-27 09:55:56 +00:00
MC	Remove edis - the enhanced disassembler. Fixes PR14654.	2012-12-19 19:55:47 +00:00
Object	Teach MachO which sections contain code	2012-12-17 17:59:32 +00:00
Other	Using "not grep" is brittle as the test passes if llvm-as fails.	2012-11-21 14:17:23 +00:00
Scripts	Added program header emission	2012-11-16 20:51:32 +00:00
TableGen	Fix typo, which prevent test from being check.	2012-12-12 21:10:56 +00:00
tools	PR10867: Analogue of r169441 for when using external 'sh'. And actually run the test!	2012-12-05 23:15:33 +00:00
Transforms	Transform (x&C)>V into (x&C)!=0 where possible	2012-12-19 19:47:13 +00:00
Unit
Verifier
YAMLParser
CMakeLists.txt	Adding tests for the Intel JIT event listener's MCJIT support.	2012-11-21 20:38:26 +00:00
lit.cfg	Adding tests for the Intel JIT event listener's MCJIT support.	2012-11-21 20:38:26 +00:00
lit.site.cfg.in	Adding tests for the Intel JIT event listener's MCJIT support.	2012-11-21 20:38:26 +00:00
Makefile	Drop the address space limit for tests in the makefile build.	2012-12-09 10:34:22 +00:00
Makefile.tests
TestRunner.sh