diff options
| author | Alexey Bataev <a.bataev@hotmail.com> | 2015-07-15 08:39:35 +0000 |
|---|---|---|
| committer | Alexey Bataev <a.bataev@hotmail.com> | 2015-07-15 08:39:35 +0000 |
| commit | b9288601a3ec46c3b645818110038c9910efcc55 (patch) | |
| tree | 4cdc6d11f707d00ce4e9a9fe705829bed8c01c6c /llvm/test/CodeGen/AArch64 | |
| parent | 5d36b230b5ea88cb6e06f604431f856808703969 (diff) | |
| download | bcm5719-llvm-b9288601a3ec46c3b645818110038c9910efcc55.tar.gz bcm5719-llvm-b9288601a3ec46c3b645818110038c9910efcc55.zip | |
[SDAG] Optimize unordered comparison in soft-float mode (patch by Anton Nadolskiy)
Current implementation handles unordered comparison poorly in soft-float mode.
Consider (a ULE b) which is a <= b. It is lowered to (ledf2(a, b) <= 0 || unorddf2(a, b) != 0) (in general). We can do better job by lowering it to (__gtdf2(a, b) <= 0).
Such replacement is true for other CMP's (ult, ugt, uge). In general, we just call same function as for ordered case but negate comparison against zero.
Differential Revision: http://reviews.llvm.org/D10804
llvm-svn: 242280
Diffstat (limited to 'llvm/test/CodeGen/AArch64')
| -rw-r--r-- | llvm/test/CodeGen/AArch64/arm64-fp128.ll | 31 |
1 files changed, 8 insertions, 23 deletions
diff --git a/llvm/test/CodeGen/AArch64/arm64-fp128.ll b/llvm/test/CodeGen/AArch64/arm64-fp128.ll index aaef39fcf51..097fe2ca6ed 100644 --- a/llvm/test/CodeGen/AArch64/arm64-fp128.ll +++ b/llvm/test/CodeGen/AArch64/arm64-fp128.ll @@ -148,14 +148,9 @@ define i1 @test_setcc2() { ; CHECK: ldr q1, [{{x[0-9]+}}, :lo12:rhs] %val = fcmp ugt fp128 %lhs, %rhs -; CHECK: bl __gttf2 +; CHECK: bl __letf2 ; CHECK: cmp w0, #0 -; CHECK: cset [[GT:w[0-9]+]], gt - -; CHECK: bl __unordtf2 -; CHECK: cmp w0, #0 -; CHECK: cset [[UNORDERED:w[0-9]+]], ne -; CHECK: orr w0, [[UNORDERED]], [[GT]] +; CHECK: cset w0, gt ret i1 %val ; CHECK: ret @@ -169,31 +164,21 @@ define i32 @test_br_cc() { ; CHECK: ldr q0, [{{x[0-9]+}}, :lo12:lhs] ; CHECK: ldr q1, [{{x[0-9]+}}, :lo12:rhs] - ; olt == !uge, which LLVM unfortunately "optimizes" this to. + ; olt == !uge, which LLVM optimizes this to. %cond = fcmp olt fp128 %lhs, %rhs -; CHECK: bl __getf2 -; CHECK: cmp w0, #0 -; CHECK: cset [[OGE:w[0-9]+]], ge - -; CHECK: bl __unordtf2 -; CHECK: cmp w0, #0 -; CHECK: cset [[UNORDERED:w[0-9]+]], ne - -; CHECK: orr [[UGE:w[0-9]+]], [[UNORDERED]], [[OGE]] -; CHECK: cbnz [[UGE]], [[RET29:.LBB[0-9]+_[0-9]+]] +; CHECK: bl __lttf2 +; CHECK-NEXT: cmp w0, #0 +; CHECK-NEXT: b.ge {{.LBB[0-9]+_[0-9]+}} br i1 %cond, label %iftrue, label %iffalse iftrue: ret i32 42 ; CHECK-NEXT: BB# ; CHECK-NEXT: movz w0, #0x2a -; CHECK-NEXT: b [[REALRET:.LBB[0-9]+_[0-9]+]] - +; CHECK: ret iffalse: ret i32 29 -; CHECK: [[RET29]]: -; CHECK-NEXT: movz w0, #0x1d -; CHECK-NEXT: [[REALRET]]: +; CHECK: movz w0, #0x1d ; CHECK: ret } |
