SimplifyDemandedBits. The idea is that some operations can be simplified if
not all of the computed elements are needed. Some targets (like x86) have a
large number of intrinsics that operate on a single element, but pass other
elts through unmodified. If those other elements are not needed, the
intrinsics can be simplified to scalar operations, and insertelement ops can
be removed.
This turns (f.e.):
ushort %Convert_sse(float %f) {
%tmp = insertelement <4 x float> undef, float %f, uint 0 ; <<4 x float>> [#uses=1]
%tmp10 = insertelement <4 x float> %tmp, float 0.000000e+00, uint 1 ; <<4 x float>> [#uses=1]
%tmp11 = insertelement <4 x float> %tmp10, float 0.000000e+00, uint 2 ; <<4 x float>> [#uses=1]
%tmp12 = insertelement <4 x float> %tmp11, float 0.000000e+00, uint 3 ; <<4 x float>> [#uses=1]
%tmp28 = tail call <4 x float> %llvm.x86.sse.sub.ss( <4 x float> %tmp12, <4 x float> < float 1.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00 > ) ; <<4 x float>> [#uses=1]
%tmp37 = tail call <4 x float> %llvm.x86.sse.mul.ss( <4 x float> %tmp28, <4 x float> < float 5.000000e-01, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00 > ) ; <<4 x float>> [#uses=1]
%tmp48 = tail call <4 x float> %llvm.x86.sse.min.ss( <4 x float> %tmp37, <4 x float> < float 6.553500e+04, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00 > ) ; <<4 x float>> [#uses=1]
%tmp59 = tail call <4 x float> %llvm.x86.sse.max.ss( <4 x float> %tmp48, <4 x float> zeroinitializer ) ; <<4 x float>> [#uses=1]
%tmp = tail call int %llvm.x86.sse.cvttss2si( <4 x float> %tmp59 ) ; <int> [#uses=1]
%tmp69 = cast int %tmp to ushort ; <ushort> [#uses=1]
ret ushort %tmp69
}
into:
ushort %Convert_sse(float %f) {
entry:
%tmp28 = sub float %f, 1.000000e+00 ; <float> [#uses=1]
%tmp37 = mul float %tmp28, 5.000000e-01 ; <float> [#uses=1]
%tmp375 = insertelement <4 x float> undef, float %tmp37, uint 0 ; <<4 x float>> [#uses=1]
%tmp48 = tail call <4 x float> %llvm.x86.sse.min.ss( <4 x float> %tmp375, <4 x float> < float 6.553500e+04, float undef, float undef, float undef > ) ; <<4 x float>> [#uses=1]
%tmp59 = tail call <4 x float> %llvm.x86.sse.max.ss( <4 x float> %tmp48, <4 x float> < float 0.000000e+00, float undef, float undef, float undef > ) ; <<4 x float>> [#uses=1]
%tmp = tail call int %llvm.x86.sse.cvttss2si( <4 x float> %tmp59 ) ; <int> [#uses=1]
%tmp69 = cast int %tmp to ushort ; <ushort> [#uses=1]
ret ushort %tmp69
}
which improves codegen from:
_Convert_sse:
movss LCPI1_0, %xmm0
movss 4(%esp), %xmm1
subss %xmm0, %xmm1
movss LCPI1_1, %xmm0
mulss %xmm0, %xmm1
movss LCPI1_2, %xmm0
minss %xmm0, %xmm1
xorps %xmm0, %xmm0
maxss %xmm0, %xmm1
cvttss2si %xmm1, %eax
andl $65535, %eax
ret
to:
_Convert_sse:
movss 4(%esp), %xmm0
subss LCPI1_0, %xmm0
mulss LCPI1_1, %xmm0
movss LCPI1_2, %xmm1
minss %xmm1, %xmm0
xorps %xmm1, %xmm1
maxss %xmm1, %xmm0
cvttss2si %xmm0, %eax
andl $65535, %eax
ret
This is just a first step, it can be extended in many ways. Testcase here:
Transforms/InstCombine/vec_demanded_elts.ll
llvm-svn: 30752
Rafael Espindola