aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2006-03-25X86 SSE1 arithmetic and logical operation intrinsics.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27092 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Support for scalar to vector with zero extension.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27091 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Change approach so that we get codegen for free for intrinsics. With this,Chris Lattner
intrinsics that don't take pointer arguments now work. For example, we can compile this: int test3( __m128d *A) { return _mm_movemask_pd(*A); } int test4( __m128 *A) { return _mm_movemask_ps(*A); } to this: _test3: movl 4(%esp), %eax movapd (%eax), %xmm0 movmskpd %xmm0, %eax ret _test4: movl 4(%esp), %eax movaps (%eax), %xmm0 movmskps %xmm0, %eax ret git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27090 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24fix inverted conditionalChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27089 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24D'oh - should be even numbered.Jim Laskey
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27088 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Added LDMXCSREvan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27087 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24ldmxcsr is a SSE instruction.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27086 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Added ldmxcsr intrinsic.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27085 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24fix 80 column violationsChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27084 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24plug the intrinsics into the patterns for movmsk*Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27083 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Parse intrinsics correctly and perform type propagation. This doesn't currentlyChris Lattner
emit the code to select intrinsics, but that is next :) git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27082 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Add dwarf register numbering to register data.Jim Laskey
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27081 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Add support for dwarf register numbering.Jim Laskey
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27080 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Hack no more.Jim Laskey
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27079 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Make sure to initialize the TheDef field!Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27078 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24add another noteChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27077 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24add a noteChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27076 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Move CodeGenIntrinsic implementation to CodeGenTarget.cpp with the rest ofChris Lattner
the CodeGen* implementations. Parse the MVT::ValueType for each operand of the intrinsics. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27075 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Specify the value type for each llvm type. This needs work for pointers.Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27074 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Shuffle some includes aroundChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27073 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Pull in valuetypes.td here, we will use it shortly.Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27072 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Only to vector shuffle for {x,x,y,y} cases when SCALAR_TO_VECTOR is free.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27071 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24expose intrinsic info to the targets.Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27070 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Fix a bad JIT encoding of VPERM. Why is VPERM D,A,B,C but vfmadd is D,A,C,B ??Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27069 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Like the comment says, prefer to use the implicit add done by [r+r] addressingChris Lattner
modes than emitting an explicit add and using a base of r0. This implements Regression/CodeGen/PowerPC/mem-rr-addr-mode.ll git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27068 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24New testcaseChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27067 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Tweak a comment.Jim Laskey
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27066 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Fix indent.Jim Laskey
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27065 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Clean up some commentary.Jim Laskey
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27064 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Rename for truth in advertising.Jim Laskey
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27063 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Fixed some grammer and spelling.Jim Laskey
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27062 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Zero vector testcaseEvan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27061 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Disable the i32->float G5 optimization. It is unsafe, as documented in theChris Lattner
comment. This fixes 177.mesa, and McCat/09-vor with the td scheduler. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27060 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24add support for using vxor to build zero vectors. This implementsChris Lattner
Regression/CodeGen/PowerPC/vec_zero.ll git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27059 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24new testcaseChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27058 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Add a facility for invoking the llvm-config tool when linking a program.Reid Spencer
This facility allows LLVMLIBS to be specified with something like: LLVMLIBS = config --libs jit instead of: LLVMLIBS = JIT with the same effect. However, the llvm-config utility is much more versatile than the single keyword approach. Note that "config" is the keyword after which any arguments to llvm-config are allowed. When llvm-config is tested and working well, we'll start using this and drop support for the JIT keyword. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27057 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Handle BUILD_VECTOR with all zero elements.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27056 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24prefer to generate constant pool loads over splats. This prevents us fromChris Lattner
using a splat for {1.0,1.0,1.0,1.0} git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27055 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Fix a typo, thanks to Gabor GreifChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27054 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24fix spelloChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27053 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Fix spelloChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27052 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24add the actual cost to the debug infoChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27051 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24fix two spellosChris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27050 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Gabor points out that we can't spell. :)Chris Lattner
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27049 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Remove a spurious <table> tag.Reid Spencer
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27045 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24All v2f64 shuffle cases can be handled.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27044 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Fix headersJeff Cohen
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27043 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Minor corrections.Jeff Cohen
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27042 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24Minor corrections.Jeff Cohen
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27041 91177308-0d34-0410-b5e6-96231b3b80d8
2006-03-24More efficient v2f64 shuffle using movlhps, movhlps, unpckhpd, and unpcklpd.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27040 91177308-0d34-0410-b5e6-96231b3b80d8
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-09-22 14:41:49 +0000