diff options
| author | Chris Lattner <sabre@nondot.org> | 2008-03-02 18:05:14 +0000 |
|---|---|---|
| committer | Chris Lattner <sabre@nondot.org> | 2008-03-02 18:05:14 +0000 |
| commit | 767486b1d5660948643959348f8cb0b1ac7c54bc (patch) | |
| tree | 9977f9d8435ae3077fdb65f9380702c20a2c1252 /lib | |
| parent | 3be4893dcecaec7acc21ea445321e27a03ef99b2 (diff) | |
Evan implemented these.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@47828 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/Target/X86/README-SSE.txt | 26 | ||||
| -rw-r--r-- | lib/Target/X86/README.txt | 27 |
2 files changed, 0 insertions, 53 deletions
diff --git a/lib/Target/X86/README-SSE.txt b/lib/Target/X86/README-SSE.txt index 2ccabca2fc..acfe411623 100644 --- a/lib/Target/X86/README-SSE.txt +++ b/lib/Target/X86/README-SSE.txt @@ -131,32 +131,6 @@ feasible. //===---------------------------------------------------------------------===// -Teach the coalescer to commute 2-addr instructions, allowing us to eliminate -the reg-reg copy in this example: - -float foo(int *x, float *y, unsigned c) { - float res = 0.0; - unsigned i; - for (i = 0; i < c; i++) { - float xx = (float)x[i]; - xx = xx * y[i]; - xx += res; - res = xx; - } - return res; -} - -LBB_foo_3: # no_exit - cvtsi2ss %XMM0, DWORD PTR [%EDX + 4*%ESI] - mulss %XMM0, DWORD PTR [%EAX + 4*%ESI] - addss %XMM0, %XMM1 - inc %ESI - cmp %ESI, %ECX -**** movaps %XMM1, %XMM0 - jb LBB_foo_3 # no_exit - -//===---------------------------------------------------------------------===// - Codegen: if (copysign(1.0, x) == copysign(1.0, y)) into: diff --git a/lib/Target/X86/README.txt b/lib/Target/X86/README.txt index fccddc79f4..65de926a3e 100644 --- a/lib/Target/X86/README.txt +++ b/lib/Target/X86/README.txt @@ -933,33 +933,6 @@ _test: //===---------------------------------------------------------------------===// -This is a "commutable two-address" register coallescing deficiency: - -define <4 x float> @test1(<4 x float> %V) { -entry: - %tmp8 = shufflevector <4 x float> %V, <4 x float> undef, - <4 x i32> < i32 3, i32 2, i32 1, i32 0 > - %add = add <4 x float> %tmp8, %V - ret <4 x float> %add -} - -this codegens to: - -_test1: - pshufd $27, %xmm0, %xmm1 - addps %xmm0, %xmm1 - movaps %xmm1, %xmm0 - ret - -instead of: - -_test1: - pshufd $27, %xmm0, %xmm1 - addps %xmm1, %xmm0 - ret - -//===---------------------------------------------------------------------===// - Leaf functions that require one 4-byte spill slot have a prolog like this: _foo: |