aboutsummaryrefslogtreecommitdiff
path: root/lib/Target
AgeCommit message (Collapse)Author
2005-07-30Change the fp to integer code to not perform 2-byte stores followed byChris Lattner
1 byte loads and other operations. This is bad for store-forwarding on common CPUs. We now do this: fnstcw WORD PTR [%ESP] mov %AX, WORD PTR [%ESP] instead of: fnstcw WORD PTR [%ESP] mov %AL, BYTE PTR [%ESP + 1] git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22559 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-30Use a custom expander for all FP to int conversions, as the X86 only hasChris Lattner
FP-to-int-in-memory: this exposes the load from the stored slot to the selection dag, allowing it to be folded into other operaions. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22556 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-29turn off GOT on archs that didn't use it (not that it appeard to harm them ↵Andrew Lenharth
much with it on) git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22553 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-29Implement a FIXME: move a bunch of cruft for handling FP_TO_*INT operationsChris Lattner
that the X86 does not support to the legalizer. This allows it to be better optimized, etc, and will help with SSE support. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22551 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-29Don't forget to diddle with the control word when performing an FISTP64.Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22550 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-29Use a custom expander to compile this:Chris Lattner
long %test4(double %X) { %tmp.1 = cast double %X to long ; <long> [#uses=1] ret long %tmp.1 } to this: _test4: sub %ESP, 12 fld QWORD PTR [%ESP + 16] fistp QWORD PTR [%ESP] mov %EDX, DWORD PTR [%ESP + 4] mov %EAX, DWORD PTR [%ESP] add %ESP, 12 ret instead of this: _test4: sub %ESP, 28 fld QWORD PTR [%ESP + 32] fstp QWORD PTR [%ESP] call ___fixdfdi add %ESP, 28 ret git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22549 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-28support bsr, and more .td simplificationAndrew Lenharth
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22543 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-28get lazy JITing working. Some of shootout runs nowAndrew Lenharth
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22538 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-28Eliminate an extra copy from R1 that Nate noticed on function calls thatChris Lattner
have to write arguments to the stack git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22536 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-28Specify the correct number of operandsChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22535 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-28Fold constant adds into loads and stores to frame indices.Nate Begeman
For the following code: double %ext(int %A.0__, long %A.1__) { %A_addr = alloca %typedef.DComplex ; <%typedef.DComplex*> [#uses=2] %tmp.1 = cast %typedef.DComplex* %A_addr to int* ; <int*> [#uses=1] store int %A.0__, int* %tmp.1 %tmp.2 = getelementptr %typedef.DComplex* %A_addr, int 0, uint 1 ; <double*> [#uses=2] %tmp.3 = cast double* %tmp.2 to long* ; <long*> [#uses=1] store long %A.1__, long* %tmp.3 %tmp.5 = load double* %tmp.2 ; <double> [#uses=1] ret double %tmp.5 } We now generate: _ext: .LBB_ext_0: ; stw r3, -12(r1) stw r4, -8(r1) stw r5, -4(r1) lfd f1, -8(r1) blr Instead of: _ext: .LBB_ext_0: ; stw r3, -12(r1) addi r2, r1, -12 stw r4, 4(r2) stw r5, 8(r2) lfd f1, 4(r2) blr This also fires hundreds of times on MultiSource. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22533 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-27Fix some commentsNate Begeman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22530 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-27Eliminate all remaining tabs and trailing spaces.Jeff Cohen
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22523 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-27Implement the optimization for the Red Zone on Darwin. This removes theNate Begeman
unnecessary SP manipulation in leaf routines that don't need it. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22522 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-27fix some warnings when compiled with 32-bit hostsChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22521 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-27Eliminate tabs and trailing spaces.Jeff Cohen
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22520 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-26add a note about the red zoneChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22518 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-26Wrap some long lines, fix emission of weak global variablesChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22517 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-26Update the PPC readmeNate Begeman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22516 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-25Fix an optimization put in for accessing static globals. This obviatesNate Begeman
the need to build PIC. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22512 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-23fix compile errorAndrew Lenharth
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22508 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-22PowerPC no-pic code is not quite ready for prime-timeChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22507 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-22Handle more imm forms, and load small negative i32 constants without hitting ↵Andrew Lenharth
memory (should do the same for arbitrary zero extended small negative constants) git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22505 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-22finally found the gcc defined constantsAndrew Lenharth
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22502 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-22Alpha JIT (beta)Andrew Lenharth
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22500 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-22simpilfy instruction encoding (and make the lines way shorter, aka Misha ↵Andrew Lenharth
happification) git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22499 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-22update interfaceAndrew Lenharth
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22498 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-21Support building non-PICNate Begeman
Remove the LoadHiAddr pseudo-instruction. Optimization of stores to and loads from statics. Force JIT to use new non-PIC codepaths. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22494 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-21revert to using 4-byte alignment for doubles, as specified by the ABIChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22493 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-21Support assembling fsqrt on darwin. This will be implemented better whenNate Begeman
PowerPC gets subtarget support up. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22489 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-20Generate mfocrf when targeting g5. Generate fsqrt/fsqrts when targetin g5.Nate Begeman
8-byte align doubles. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22486 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-19Integrate SelectFPExpr into SelectExpr. This gets PPC32 closer to beingNate Begeman
automatically generated from a target description. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22470 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-19For: memory operations -> storesReid Spencer
This is the first incremental patch to implement this feature. It adds no functionality to LLVM but setup up the information needed from targets in order to implement the optimization correctly. Each target needs to specify the maximum number of store operations for conversion of the llvm.memset, llvm.memcpy, and llvm.memmove intrinsics into a sequence of store operations. The limit needs to be chosen at the threshold of performance for such an optimization (generally smallish). The target also needs to specify whether the target can support unaligned stores for multi-byte store operations. This helps ensure the optimization doesn't generate code that will trap on an alignment errors. More patches to follow. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22468 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-16Teach the legalizer how to promote SINT_TO_FP to a wider SINT_TO_FP thatNate Begeman
the target natively supports. This eliminates some special-case code from the x86 backend and generates better code as well. For an i8 to f64 conversion, before & after: _x87 before: subl $2, %esp movb 6(%esp), %al movsbw %al, %ax movw %ax, (%esp) filds (%esp) addl $2, %esp ret _x87 after: subl $2, %esp movsbw 6(%esp), %ax movw %ax, (%esp) filds (%esp) addl $2, %esp ret _sse before: subl $12, %esp movb 16(%esp), %al movsbl %al, %eax cvtsi2sd %eax, %xmm0 addl $12, %esp ret _sse after: subl $12, %esp movsbl 16(%esp), %eax cvtsi2sd %eax, %xmm0 addl $12, %esp ret git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22452 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-16Teach the register allocator that movaps is also a move instructionNate Begeman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22451 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-16A couple more darwinismsNate Begeman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22450 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-16Remove all knowledge of UINT_TO_FP from the X86 backend, relying on theChris Lattner
legalizer to eliminate them. With this comes the expected code quality improvements, such as, for this: double foo(unsigned short X) { return X; } we now generate this: _foo: subl $4, %esp movzwl 8(%esp), %eax movl %eax, (%esp) fildl (%esp) addl $4, %esp ret instead of this: _foo: subl $4, %esp movw 8(%esp), %ax movzwl %ax, %eax ;; Load not folded into this. movl %eax, (%esp) fildl (%esp) addl $4, %esp ret -Chris git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22449 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-15Get closer to fully working scalar FP in SSE regs. This gets singlesourceNate Begeman
working, and Olden/power. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22441 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-14Add support for printing the sse scalar comparison instruction mnemonics.Nate Begeman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22440 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-14Fixed PR#596:John Criswell
Add parenthesis around the value being negated; that way, if the value begins with a minus sign (e.g. negative integer), we won't generate a C predecrement operator by mistake. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22437 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-12Check in the last of the darwin-specific code necessary to get shootoutNate Begeman
working before modifying the asm printer to use the subtarget info. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22408 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-12Remove some code that moved to the generic asm printer a long time ago.Nate Begeman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22407 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-12Fix povray and minor cleanupsAndrew Lenharth
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22397 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-12I don't know how this ever compiled with gcc, but VC++ correctly rejects it.Jeff Cohen
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22394 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-12Clean up the TargetSubtarget class a bit, removing an unnecessary argumentNate Begeman
to the constructor. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22392 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-12Minor changes to improve comments and fix the build on _WIN32 systems.Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22391 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-12Add a noteChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22390 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-12Implement Subtarget supportNate Begeman
Implement the X86 Subtarget. This consolidates the checks for target triple, and setting options based on target triple into one place. This allows us to convert the asm printer and isel over from being littered with "forDarwin", "forCygwin", etc. into just having the appropriate flags for each subtarget feature controlling the code for that feature. This patch also implements indirect external and weak references in the X86 pattern isel, for darwin. Next up is to convert over the asm printers to use this new interface. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22389 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-12Commit some pending darwin changes before subtarget support.Nate Begeman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22388 91177308-0d34-0410-b5e6-96231b3b80d8
2005-07-11fix a warningChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22385 91177308-0d34-0410-b5e6-96231b3b80d8
generated by cgit v1.2.3-18-g5258 (git 2.32.0) at 2025-08-04 03:27:33 +0000