6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-02-08 06:32:24 +00:00
Code Issues Projects Releases Wiki Activity
llvm-6502/test/CodeGen/X86/block-placement.ll

143 lines
3.4 KiB
LLVM
Raw Normal View History

Add a very basic test for MachineBlockPlacement. This is essentially the canonical example I used when developing it, and is one of the primary motivating real-world use cases for __builtin_expect (when burried under a macro). I'm working on more test cases here, but I'm trying to make sure both that the pass is doing the right thing with the test cases and that they aren't too brittle to changes elsewhere in the code generation pipeline. Feedback and/or suggestions on how to test this are very welcome. Especially feedback on whether testing the block comments is a good strategy; I couldn't find any good examples to steal from but all the other ideas I had were a lot uglier or more fragile. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@142644 91177308-0d34-0410-b5e6-96231b3b80d8
2011-10-21 08:01:56 +00:00
; RUN: llc -march=x86 -enable-block-placement < %s | FileCheck %s
declare void @error(i32 %i, i32 %a, i32 %b)
Add loop aligning to MachineBlockPlacement based on review discussion so it's a bit more plausible to use this instead of CodePlacementOpt. The code for this was shamelessly stolen from CodePlacementOpt, and then trimmed down a bit. There doesn't seem to be much utility in returning true/false from this pass as we may or may not have rewritten all of the blocks. Also, the statistic of counting how many loops were aligned doesn't seem terribly important so I removed it. If folks would like it to be included, I'm happy to add it back. This was probably the most egregious of the missing features, and now I'm going to start gathering some performance numbers and looking at specific loop structures that have different layout between the two. Test is updated to include both basic loop alignment and nested loop alignment. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@142645 91177308-0d34-0410-b5e6-96231b3b80d8
2011-10-21 08:57:37 +00:00
define i32 @test_ifchains(i32 %i, i32* %a, i32 %b) {
Add a very basic test for MachineBlockPlacement. This is essentially the canonical example I used when developing it, and is one of the primary motivating real-world use cases for __builtin_expect (when burried under a macro). I'm working on more test cases here, but I'm trying to make sure both that the pass is doing the right thing with the test cases and that they aren't too brittle to changes elsewhere in the code generation pipeline. Feedback and/or suggestions on how to test this are very welcome. Especially feedback on whether testing the block comments is a good strategy; I couldn't find any good examples to steal from but all the other ideas I had were a lot uglier or more fragile. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@142644 91177308-0d34-0410-b5e6-96231b3b80d8
2011-10-21 08:01:56 +00:00
; Test a chain of ifs, where the block guarded by the if is error handling code
; that is not expected to run.
Add loop aligning to MachineBlockPlacement based on review discussion so it's a bit more plausible to use this instead of CodePlacementOpt. The code for this was shamelessly stolen from CodePlacementOpt, and then trimmed down a bit. There doesn't seem to be much utility in returning true/false from this pass as we may or may not have rewritten all of the blocks. Also, the statistic of counting how many loops were aligned doesn't seem terribly important so I removed it. If folks would like it to be included, I'm happy to add it back. This was probably the most egregious of the missing features, and now I'm going to start gathering some performance numbers and looking at specific loop structures that have different layout between the two. Test is updated to include both basic loop alignment and nested loop alignment. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@142645 91177308-0d34-0410-b5e6-96231b3b80d8
2011-10-21 08:57:37 +00:00
; CHECK: test_ifchains:
Add a very basic test for MachineBlockPlacement. This is essentially the canonical example I used when developing it, and is one of the primary motivating real-world use cases for __builtin_expect (when burried under a macro). I'm working on more test cases here, but I'm trying to make sure both that the pass is doing the right thing with the test cases and that they aren't too brittle to changes elsewhere in the code generation pipeline. Feedback and/or suggestions on how to test this are very welcome. Especially feedback on whether testing the block comments is a good strategy; I couldn't find any good examples to steal from but all the other ideas I had were a lot uglier or more fragile. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@142644 91177308-0d34-0410-b5e6-96231b3b80d8
2011-10-21 08:01:56 +00:00
; CHECK: %entry
; CHECK: %else1
; CHECK: %else2
; CHECK: %else3
; CHECK: %else4
; CHECK: %exit
; CHECK: %then1
; CHECK: %then2
; CHECK: %then3
; CHECK: %then4
; CHECK: %then5
entry:
%gep1 = getelementptr i32* %a, i32 1
%val1 = load i32* %gep1
%cond1 = icmp ugt i32 %val1, 1
br i1 %cond1, label %then1, label %else1, !prof !0
then1:
call void @error(i32 %i, i32 1, i32 %b)
br label %else1
else1:
%gep2 = getelementptr i32* %a, i32 2
%val2 = load i32* %gep2
%cond2 = icmp ugt i32 %val2, 2
br i1 %cond2, label %then2, label %else2, !prof !0
then2:
call void @error(i32 %i, i32 1, i32 %b)
br label %else2
else2:
%gep3 = getelementptr i32* %a, i32 3
%val3 = load i32* %gep3
%cond3 = icmp ugt i32 %val3, 3
br i1 %cond3, label %then3, label %else3, !prof !0
then3:
call void @error(i32 %i, i32 1, i32 %b)
br label %else3
else3:
%gep4 = getelementptr i32* %a, i32 4
%val4 = load i32* %gep4
%cond4 = icmp ugt i32 %val4, 4
br i1 %cond4, label %then4, label %else4, !prof !0
then4:
call void @error(i32 %i, i32 1, i32 %b)
br label %else4
else4:
%gep5 = getelementptr i32* %a, i32 3
%val5 = load i32* %gep5
%cond5 = icmp ugt i32 %val5, 3
br i1 %cond5, label %then5, label %exit, !prof !0
then5:
call void @error(i32 %i, i32 1, i32 %b)
br label %exit
exit:
ret i32 %b
}
!0 = metadata !{metadata !"branch_weights", i32 4, i32 64}
Add loop aligning to MachineBlockPlacement based on review discussion so it's a bit more plausible to use this instead of CodePlacementOpt. The code for this was shamelessly stolen from CodePlacementOpt, and then trimmed down a bit. There doesn't seem to be much utility in returning true/false from this pass as we may or may not have rewritten all of the blocks. Also, the statistic of counting how many loops were aligned doesn't seem terribly important so I removed it. If folks would like it to be included, I'm happy to add it back. This was probably the most egregious of the missing features, and now I'm going to start gathering some performance numbers and looking at specific loop structures that have different layout between the two. Test is updated to include both basic loop alignment and nested loop alignment. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@142645 91177308-0d34-0410-b5e6-96231b3b80d8
2011-10-21 08:57:37 +00:00
define i32 @test_loop_align(i32 %i, i32* %a) {
; Check that we provide basic loop body alignment with the block placement
; pass.
; CHECK: test_loop_align:
; CHECK: %entry
; CHECK: .align 16,
; CHECK-NEXT: %body
; CHECK: %exit
entry:
br label %body
body:
%iv = phi i32 [ 0, %entry ], [ %next, %body ]
%base = phi i32 [ 0, %entry ], [ %sum, %body ]
%arrayidx = getelementptr inbounds i32* %a, i32 %iv
%0 = load i32* %arrayidx
%sum = add nsw i32 %0, %base
%next = add i32 %iv, 1
%exitcond = icmp eq i32 %next, %i
br i1 %exitcond, label %exit, label %body
exit:
ret i32 %sum
}
define i32 @test_nested_loop_align(i32 %i, i32* %a, i32* %b) {
; Check that we provide nested loop body alignment.
; CHECK: test_nested_loop_align:
; CHECK: %entry
; CHECK: .align 16,
; CHECK-NEXT: %loop.body.1
; CHECK: .align 16,
; CHECK-NEXT: %inner.loop.body
; CHECK-NOT: .align
; CHECK: %loop.body.2
; CHECK: %exit
entry:
br label %loop.body.1
loop.body.1:
%iv = phi i32 [ 0, %entry ], [ %next, %loop.body.2 ]
%arrayidx = getelementptr inbounds i32* %a, i32 %iv
%bidx = load i32* %arrayidx
br label %inner.loop.body
inner.loop.body:
%inner.iv = phi i32 [ 0, %loop.body.1 ], [ %inner.next, %inner.loop.body ]
%base = phi i32 [ 0, %loop.body.1 ], [ %sum, %inner.loop.body ]
%scaled_idx = mul i32 %bidx, %iv
%inner.arrayidx = getelementptr inbounds i32* %b, i32 %scaled_idx
%0 = load i32* %inner.arrayidx
%sum = add nsw i32 %0, %base
%inner.next = add i32 %iv, 1
%inner.exitcond = icmp eq i32 %inner.next, %i
br i1 %inner.exitcond, label %loop.body.2, label %inner.loop.body
loop.body.2:
%next = add i32 %iv, 1
%exitcond = icmp eq i32 %next, %i
br i1 %exitcond, label %exit, label %loop.body.1
exit:
ret i32 %sum
}
Reference in New Issue Copy Permalink