mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-09-06 09:54:49 +00:00
c6d7ad3c7d
stuff now that we don't care about emulating the old broken behavior of the old isel. This eliminates the 'CheckChainCompatible' check (along with IsChainCompatible) which did an incorrect and inefficient scan *up* the chain nodes which happened as the pattern was being formed and does the validation at the end in HandleMergeInputChains when it forms a structural pattern. This scans "down" the graph, which means that it is quickly bounded by nodes already selected. This also handles token factors that get "trapped" in the dag. Removing the CheckChainCompatible nodes also shrinks the generated tables by about 6K for X86 (down to 83K). There are two pieces remaining before I can nuke PreprocessRMW: 1. I xfailed a test because we're now producing worse code in a case that has nothing to do with the change: it turns out that our use of MorphNodeTo will leave dead nodes in the graph which (depending on how the graph is walked) end up causing bogus uses of chains and blocking matches. This is really bad for other reasons, so I'll fix this in a follow-up patch. 2. CheckFoldableChainNode needs to be improved to handle the TF. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97539 91177308-0d34-0410-b5e6-96231b3b80d8
35 lines
2.0 KiB
LLVM
35 lines
2.0 KiB
LLVM
; RUN: llc < %s -march=x86 -x86-asm-syntax=intel | \
|
|
; RUN: grep {and DWORD PTR} | count 2
|
|
|
|
target datalayout = "e-p:32:32"
|
|
%struct.Macroblock = type { i32, i32, i32, i32, i32, [8 x i32], %struct.Macroblock*, %struct.Macroblock*, i32, [2 x [4 x [4 x [2 x i32]]]], [16 x i8], [16 x i8], i32, i64, [4 x i32], [4 x i32], i64, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i16, double, i32, i32, i32, i32, i32, i32, i32, i32, i32 }
|
|
|
|
define internal fastcc i32 @dct_chroma(i32 %uv, i32 %cr_cbp) nounwind {
|
|
entry:
|
|
br i1 true, label %cond_true2732.preheader, label %cond_true129
|
|
cond_true129: ; preds = %entry
|
|
ret i32 0
|
|
cond_true2732.preheader: ; preds = %entry
|
|
%tmp2666 = getelementptr %struct.Macroblock* null, i32 0, i32 13 ; <i64*> [#uses=2]
|
|
%tmp2674 = trunc i32 0 to i8 ; <i8> [#uses=1]
|
|
br i1 true, label %cond_true2732.preheader.split.us, label %cond_true2732.preheader.split
|
|
cond_true2732.preheader.split.us: ; preds = %cond_true2732.preheader
|
|
br i1 true, label %cond_true2732.outer.us.us, label %cond_true2732.outer.us
|
|
cond_true2732.outer.us.us: ; preds = %cond_true2732.preheader.split.us
|
|
%tmp2667.us.us = load i64* %tmp2666 ; <i64> [#uses=1]
|
|
%tmp2670.us.us = load i64* null ; <i64> [#uses=1]
|
|
%shift.upgrd.1 = zext i8 %tmp2674 to i64 ; <i64> [#uses=1]
|
|
%tmp2675.us.us = shl i64 %tmp2670.us.us, %shift.upgrd.1 ; <i64> [#uses=1]
|
|
%tmp2675not.us.us = xor i64 %tmp2675.us.us, -1 ; <i64> [#uses=1]
|
|
%tmp2676.us.us = and i64 %tmp2667.us.us, %tmp2675not.us.us ; <i64> [#uses=1]
|
|
store i64 %tmp2676.us.us, i64* %tmp2666
|
|
ret i32 0
|
|
cond_true2732.outer.us: ; preds = %cond_true2732.preheader.split.us
|
|
ret i32 0
|
|
cond_true2732.preheader.split: ; preds = %cond_true2732.preheader
|
|
ret i32 0
|
|
cond_next2752: ; No predecessors!
|
|
ret i32 0
|
|
}
|
|
|