aboutsummaryrefslogtreecommitdiff
path: root/lib/Target/PowerPC
AgeCommit message (Collapse)Author
2006-05-09Split SwitchSection into SwitchTo{Text|Data}Section methods.Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28184 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-08Yet more readme updatingNate Begeman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28172 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-08New note about something bad happening in target independent optimizersNate Begeman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28170 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-08Proving once again that I am not as smart as the compilerNate Begeman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28169 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-08Fold more shifts into inserts, and update the READMENate Begeman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28168 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-08Update some stuff now that the new rlwimi code has gone inNate Begeman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28162 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-07New rlwimi implementation, which is superior to the old one. There areNate Begeman
still a couple missed optimizations, but we now generate all the possible rlwimis for multiple inserts into the same bitfield. More regression tests to come. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28156 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-05Print a grouping around inline asm blocks so that we can tell when we areChris Lattner
using them. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28134 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-05New note, Nate, please check to see if I'm full of it :)Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28118 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-04Rename MO_VirtualRegister -> MO_Register. Clean up immediate handling.Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28104 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-04Move some methods out of MachineInstr into MachineOperandChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28102 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-04There shalt be only one "immediate" operand type!Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28099 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-04Revert Nate's CR patch from last night, which caused many regressions (e.g. ↵Chris Lattner
fhourstones). Loading and storing off R0 isn't what we wanted. Also, taking some CR's out of CRRC seems to cause failures as well. Further investigation is required. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28097 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-04Remove a bunch more SparcV9 specific stuffChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28093 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-04Remove some more unused stuff from MachineInstr that was leftover from V9.Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28091 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-03Change from using MachineRelocation ctors to using static methodsChris Lattner
in MachineRelocation to create Relocations. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28088 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-03Suck block address tracking out of targets into the JIT Emitter. ThisChris Lattner
simplifies the MachineCodeEmitter interface just a little bit and makes BasicBlocks work like constant pools and jump tables. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28082 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-03Refactor TargetMachine, pushing handling of TargetData into the ↵Owen Anderson
target-specific subclasses. This has one caller-visible change: getTargetData() now returns a pointer instead of a reference. This fixes PR 759. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28074 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-03Change the BasicBlockAddrs map to be a vector, indexed by MBB number.Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28069 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-02Several related changes:Chris Lattner
1. Change several methods in the MachineCodeEmitter class to be pure virtual. 2. Suck emitConstantPool/initJumpTableInfo into startFunction, removing them from the MachineCodeEmitter interface, and reducing the amount of target- specific code. 3. Change the JITEmitter so that it allocates constantpools and jump tables *right* next to the functions that they belong to, instead of in a separate pool of memory. This makes all memory for a function be contiguous, and means the JITEmitter only tracks one block of memory now. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28065 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-02Fix a purely hypothetical problem (for now): emitWord emits in the hostChris Lattner
byte format. This doesn't work when using the code emitter in a cross target environment. Since the code emitter is only really used by the JIT, this isn't a current problem, but if we ever start emitting .o files, it would be. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28060 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-02Refactor the machine code emitter interface to pull the pointers for the currentChris Lattner
code emission location into the base class, instead of being in the derived classes. This change means that low-level methods like emitByte/emitWord now are no longer virtual (yaay for speed), and we now have a framework to support growable code segments. This implements feature request #1 of PR469. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28059 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-02Since we don't handle callee-save CRs right yet, don't allocate them. AlsoNate Begeman
don't step on R11 in the middle of a function when saving and restoring CRs git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28058 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-02Hooray, everyone now uses the same printBasicBlockLabel implementationNate Begeman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28056 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-02Extend printBasicBlockLabel a bit so that it can be used to print allNate Begeman
basic block labels, consolidating the code to do so in one place for each target. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28050 91177308-0d34-0410-b5e6-96231b3b80d8
2006-05-02Update the PPC compilation callback code to not need weird abi-violatingNate Begeman
prologs and epilogs, keep all the asm in one place, and remove use of compiler builtin functions. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28049 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-28Fix CodeGen/Generic/2006-04-28-Sign-extend-bool.llChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28017 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-28Add a noteChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27999 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-25No functionality changes, but cleaner code with correct comments.Nate Begeman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27966 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-22JumpTable support! What this represents is working asm and jit support forNate Begeman
x86 and ppc for 100% dense switch statements when relocations are non-PIC. This support will be extended and enhanced in the coming days to support PIC, and less dense forms of jump tables. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27947 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-22Teach the JIT how to relocate LI, this fixes the JIT on Prolangs-C/TimberWolfMCChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27943 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-21Fix the commentNate Begeman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27938 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-21Change the PPC JIT to use a Static relocation modelNate Begeman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27937 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-20Fix the CodeGen/PowerPC/buildvec_canonicalize.ll regression last night.Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27908 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-20Make sure that the new instructions selected have the right type. This fixesChris Lattner
CodeGen/PowerPC/2006-04-19-vmaddfp-crash.ll git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27868 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-19add a noteChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27832 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-19add a noteChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27828 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-18These are correctly encoded by the JIT. I checked :)Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27810 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-18add a noteChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27809 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-18Fix a crash on:Chris Lattner
void foo2(vector float *A, vector float *B) { vector float C = (vector float)vec_cmpeq(*A, *B); if (!vec_any_eq(*A, *B)) *B = (vector float){0,0,0,0}; *A = C; } git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27808 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-18pretty print node nameChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27806 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-18Implement an important entry from README_ALTIVEC:Chris Lattner
If an altivec predicate compare is used immediately by a branch, don't use a (serializing) MFCR instruction to read the CR6 register, which requires a compare to get it back to CR's. Instead, just branch on CR6 directly. :) For example, for: void foo2(vector float *A, vector float *B) { if (!vec_any_eq(*A, *B)) *B = (vector float){0,0,0,0}; } We now generate: _foo2: mfspr r2, 256 oris r5, r2, 12288 mtspr 256, r5 lvx v2, 0, r4 lvx v3, 0, r3 vcmpeqfp. v2, v3, v2 bne cr6, LBB1_2 ; UnifiedReturnBlock LBB1_1: ; cond_true vxor v2, v2, v2 stvx v2, 0, r4 mtspr 256, r2 blr LBB1_2: ; UnifiedReturnBlock mtspr 256, r2 blr instead of: _foo2: mfspr r2, 256 oris r5, r2, 12288 mtspr 256, r5 lvx v2, 0, r4 lvx v3, 0, r3 vcmpeqfp. v2, v3, v2 mfcr r3, 2 rlwinm r3, r3, 27, 31, 31 cmpwi cr0, r3, 0 beq cr0, LBB1_2 ; UnifiedReturnBlock LBB1_1: ; cond_true vxor v2, v2, v2 stvx v2, 0, r4 mtspr 256, r2 blr LBB1_2: ; UnifiedReturnBlock mtspr 256, r2 blr This implements CodeGen/PowerPC/vec_br_cmp.ll. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27804 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-18move some stuff around, clean things upChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27802 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-18Use vmladduhm to do v8i16 multiplies which is faster and simpler than doingChris Lattner
even/odd halves. Thanks to Nate telling me what's what. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27793 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-18Implement v16i8 multiply with this code:Chris Lattner
vmuloub v5, v3, v2 vmuleub v2, v3, v2 vperm v2, v2, v5, v4 This implements CodeGen/PowerPC/vec_mul.ll. With this, v16i8 multiplies are 6.79x faster than before. Overall, UnitTests/Vector/multiplies.c is now 2.45x faster with LLVM than with GCC. Remove the 'integer multiplies' todo from the README file. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27792 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-18Lower v8i16 multiply into this code:Chris Lattner
li r5, lo16(LCPI1_0) lis r6, ha16(LCPI1_0) lvx v4, r6, r5 vmulouh v5, v3, v2 vmuleuh v2, v3, v2 vperm v2, v2, v5, v4 where v4 is: LCPI1_0: ; <16 x ubyte> .byte 2 .byte 3 .byte 18 .byte 19 .byte 6 .byte 7 .byte 22 .byte 23 .byte 10 .byte 11 .byte 26 .byte 27 .byte 14 .byte 15 .byte 30 .byte 31 This is 5.07x faster on the G5 (measured) than lowering to scalar code + loads/stores. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27789 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-18Custom lower v4i32 multiplies into a cute sequence, instead of having legalizeChris Lattner
scalarize the sequence into 4 mullw's and a bunch of load/store traffic. This speeds up v4i32 multiplies 4.1x (measured) on a G5. This implements PowerPC/vec_mul.ll git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27788 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-17remove done itemChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27778 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-17Don't diddle VRSAVE if no registers need to be added/removed from it. ThisChris Lattner
allows us to codegen functions as: _test_rol: vspltisw v2, -12 vrlw v2, v2, v2 blr instead of: _test_rol: mfvrsave r2, 256 mr r3, r2 mtvrsave r3 vspltisw v2, -12 vrlw v2, v2, v2 mtvrsave r2 blr Testcase here: CodeGen/PowerPC/vec_vrsave.ll git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27777 91177308-0d34-0410-b5e6-96231b3b80d8
2006-04-17Vectors that are known live-in and live-out are clearly already marked inChris Lattner
the vrsave register for the caller. This allows us to codegen a function as: _test_rol: mfspr r2, 256 mr r3, r2 mtspr 256, r3 vspltisw v2, -12 vrlw v2, v2, v2 mtspr 256, r2 blr instead of: _test_rol: mfspr r2, 256 oris r3, r2, 40960 mtspr 256, r3 vspltisw v0, -12 vrlw v2, v0, v0 mtspr 256, r2 blr git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27772 91177308-0d34-0410-b5e6-96231b3b80d8
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-09-15 14:38:31 +0000