external_llvm.git - Unnamed repository; edit this file 'description' to name the repository.

	Commit message (Expand)	Author	Age	Files	Lines
*	s/CSR_Ghc/CSR_NoRegs/	Jakob Stoklund Olesen	2012-05-08	2	-3/+3
*	Remove 256-bit AVX non-temporal store intrinsics. Similar was previously done...	Craig Topper	2012-05-08	1	-7/+0
*	Add an MF argument to TRI::getPointerRegClass() and TII::getRegClass().	Jakob Stoklund Olesen	2012-05-07	3	-8/+10
*	Fix a regression from r147481. This combine should only happen if there is a	Chad Rosier	2012-05-07	1	-10/+12
*	X86: optimization for -(x != 0)	Manman Ren	2012-05-07	2	-0/+22
*	Fix some issues in the f16c instructions.	Craig Topper	2012-05-07	1	-11/+9
*	Add SSE4A MOVNTSS/MOVNTSD instructions.	Craig Topper	2012-05-07	1	-0/+14
*	Use MVT instead of EVT as the argument to all the shuffle decode functions. S...	Craig Topper	2012-05-06	3	-35/+33
*	Add VPERMQ/VPERMPD to the list of target specific shuffles that can be looked...	Craig Topper	2012-05-06	1	-0/+6
*	Add shuffle decode support for VPERMQ/VPERMPD.	Craig Topper	2012-05-06	3	-0/+22
*	Nuke a few dead remnants of the CBE.	Jim Grosbach	2012-05-05	1	-17/+0
*	Add a new target hook "predictableSelectIsExpensive".	Benjamin Kramer	2012-05-05	1	-0/+3
*	Adds Intel Atom scheduling latencies to X86InstrSystem.td.	Preston Gurd	2012-05-04	3	-139/+272
*	Fix some loops to match coding standards. No functional change intended.	Craig Topper	2012-05-04	1	-6/+8
*	Fix up some spacing. No functional change.	Craig Topper	2012-05-04	1	-6/+6
*	Simplify broadcast lowering code. No functional change intended.	Craig Topper	2012-05-04	1	-17/+7
*	Allow v16i16 and v32i8 shuffles to be rewritten as narrower shuffles.	Craig Topper	2012-05-04	1	-5/+8
*	Simplify shuffle narrowing code a bit. No functional change intended.	Craig Topper	2012-05-04	1	-22/+16
*	Remove the SubRegClasses field from RegisterClass descriptions.	Jakob Stoklund Olesen	2012-05-04	1	-78/+19
*	Use 'unsigned' instead of 'int' in a few places dealing with counts of vector...	Craig Topper	2012-05-03	1	-3/+3
*	Fix 256-bit vpshuflw and vpshufhw immediate encoding to handle undefs in the ...	Craig Topper	2012-05-03	2	-21/+36
*	For Intel Atom, use ILP scheduling always, instead of ILP for 64 bit	Preston Gurd	2012-05-02	1	-4/+4
*	Change the Intel Atom detection code to recognize	Preston Gurd	2012-05-02	1	-1/+2
*	This patch continues the work of adding instruction latencies for X86 Atom,	Preston Gurd	2012-05-02	4	-68/+171
*	Revert r155853	Manman Ren	2012-05-02	1	-16/+0
*	Add support for selecting AVX2 vpshuflw and vpshufhw. Add decoding support fo...	Craig Topper	2012-05-02	4	-36/+90
*	Remove unneeded break.	Jakub Staszak	2012-05-01	1	-1/+0
*	Remove trailing spaces.	Jakub Staszak	2012-05-01	1	-43/+43
*	This patch marks the X86 floating point stack registers ST0-ST7 as reserved	Preston Gurd	2012-05-01	1	-0/+10
*	X86: optimization for max-like struct	Manman Ren	2012-05-01	1	-0/+40
*	X86: Use StackRegister instead of FrameRegister in getFrameIndexReference (to...	Alexey Samsonov	2012-05-01	2	-0/+14
*	Change the PassManager from a reference to a pointer.	Bill Wendling	2012-05-01	1	-6/+6
*	Allow BMI, AES, F16C, POPCNT, FMA3, and CLMUL to be detected on AMD processors.	Craig Topper	2012-05-01	1	-9/+9
*	Make XOP and FMA4 require SSE4A to match GCC behavior. Use this to simplify B...	Craig Topper	2012-05-01	1	-9/+8
*	Attempt to handle MRMInitReg in emitVEXOpcodePrefix. Hopefully fixes PR12711.	Craig Topper	2012-05-01	1	-1/+12
*	Make XOP imply AVX as its needed to legalize the registers types.	Craig Topper	2012-05-01	1	-1/+2
*	Remove HasSSE2 from AES and CLMUL predicates. It's now implied by the HasAES ...	Craig Topper	2012-05-01	1	-3/+3
*	Make CLMUL and AES imply SSE2 since its needed to legalize the type.	Craig Topper	2012-05-01	1	-2/+4
*	Enable AVX and FMA4 for AMD Bulldozer processors.	Craig Topper	2012-05-01	1	-5/+5
*	X86: optimization for -(x != 0)	Manman Ren	2012-04-30	1	-0/+16
*	Tidy up. No functional change intended.	Chad Rosier	2012-04-30	1	-8/+7
*	Fix fastcc structure return with fast-isel on x86-32	Derek Schuff	2012-04-30	1	-0/+2
*	No need to normalize index before calling Extract128BitVector	Craig Topper	2012-04-30	1	-12/+11
*	Copied all the VEX prefix encoding code from X86MCCodeEmitter to the x86 JIT ...	Pete Cooper	2012-04-30	2	-97/+534
*	Remove unneeded casts. No functionality change.	Jakub Staszak	2012-04-29	1	-11/+11
*	Simplify code a bit. No functional change intended.	Craig Topper	2012-04-29	1	-4/+3
*	Revert r155745	Derek Schuff	2012-04-27	1	-2/+0
*	Fix fastcc structure return with fast-isel on x86-32	Derek Schuff	2012-04-27	1	-0/+2
*	Use 'unsigned' instead of 'int' in several places when retrieving number of v...	Craig Topper	2012-04-27	1	-12/+12
*	Add x86-specific DAG combine to simplify:	Chad Rosier	2012-04-27	1	-0/+28