diff options
author | Quentin Colombet <qcolombet@apple.com> | 2014-04-26 01:11:26 +0000 |
---|---|---|
committer | Quentin Colombet <qcolombet@apple.com> | 2014-04-26 01:11:26 +0000 |
commit | 9e93e47b7f196893b5779090897210d750aa1c6b (patch) | |
tree | 8fbe5cc6f623d668ef2ec938ca71d2cdf844d56d /test/CodeGen | |
parent | 64e1be4bf19b03b5961ab9dc4c65857b2561126d (diff) | |
download | llvm-9e93e47b7f196893b5779090897210d750aa1c6b.tar.gz llvm-9e93e47b7f196893b5779090897210d750aa1c6b.tar.bz2 llvm-9e93e47b7f196893b5779090897210d750aa1c6b.tar.xz |
[X86] Implement TargetLowering::getScalingFactorCost hook.
Scaling factors are not free on X86 because every "complex" addressing mode
breaks the related instruction into 2 allocations instead of 1.
<rdar://problem/16730541>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207301 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen')
-rw-r--r-- | test/CodeGen/X86/avoid_complex_am.ll | 37 | ||||
-rw-r--r-- | test/CodeGen/X86/masked-iv-safe.ll | 8 |
2 files changed, 41 insertions, 4 deletions
diff --git a/test/CodeGen/X86/avoid_complex_am.ll b/test/CodeGen/X86/avoid_complex_am.ll new file mode 100644 index 0000000000..0b7a13d3c0 --- /dev/null +++ b/test/CodeGen/X86/avoid_complex_am.ll @@ -0,0 +1,37 @@ +; RUN: opt -S -loop-reduce < %s | FileCheck %s +; Complex addressing mode are costly. +; Make loop-reduce prefer unscaled accesses. +; <rdar://problem/16730541> +target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128" +target triple = "x86_64-apple-macosx" + +define void @mulDouble(double* nocapture %a, double* nocapture %b, double* nocapture %c) { +; CHECK: @mulDouble +entry: + br label %for.body + +for.body: ; preds = %for.body, %entry +; CHECK: [[IV:%[^ ]+]] = phi i64 [ [[IVNEXT:%[^,]+]], %for.body ], [ 0, %entry ] +; Only one induction variable should have been generated. +; CHECK-NOT: phi + %indvars.iv = phi i64 [ 1, %entry ], [ %indvars.iv.next, %for.body ] + %tmp = add nsw i64 %indvars.iv, -1 + %arrayidx = getelementptr inbounds double* %b, i64 %tmp + %tmp1 = load double* %arrayidx, align 8 +; The induction variable should carry the scaling factor: 1 * 8 = 8. +; CHECK: [[IVNEXT]] = add nuw nsw i64 [[IV]], 8 + %indvars.iv.next = add i64 %indvars.iv, 1 + %arrayidx2 = getelementptr inbounds double* %c, i64 %indvars.iv.next + %tmp2 = load double* %arrayidx2, align 8 + %mul = fmul double %tmp1, %tmp2 + %arrayidx4 = getelementptr inbounds double* %a, i64 %indvars.iv + store double %mul, double* %arrayidx4, align 8 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 +; Comparison should be 19 * 8 = 152. +; CHECK: icmp eq i32 {{%[^,]+}}, 152 + %exitcond = icmp eq i32 %lftr.wideiv, 20 + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body + ret void +} diff --git a/test/CodeGen/X86/masked-iv-safe.ll b/test/CodeGen/X86/masked-iv-safe.ll index 4a4d178f6e..7f61e10f5f 100644 --- a/test/CodeGen/X86/masked-iv-safe.ll +++ b/test/CodeGen/X86/masked-iv-safe.ll @@ -5,7 +5,7 @@ ; CHECK-LABEL: count_up ; CHECK-NOT: {{and|movz|sar|shl}} -; CHECK: inc +; CHECK: addq $8, ; CHECK-NOT: {{and|movz|sar|shl}} ; CHECK: jne define void @count_up(double* %d, i64 %n) nounwind { @@ -71,7 +71,7 @@ return: ; CHECK-LABEL: count_up_signed ; CHECK-NOT: {{and|movz|sar|shl}} -; CHECK: inc +; CHECK: addq $8, ; CHECK-NOT: {{and|movz|sar|shl}} ; CHECK: jne define void @count_up_signed(double* %d, i64 %n) nounwind { @@ -174,7 +174,7 @@ return: ; CHECK-LABEL: another_count_down ; CHECK-NOT: {{and|movz|sar|shl}} -; CHECK: decq +; CHECK: addq $-8, ; CHECK-NOT: {{and|movz|sar|shl}} ; CHECK: jne define void @another_count_down(double* %d, i64 %n) nounwind { @@ -242,7 +242,7 @@ return: ; CHECK-LABEL: another_count_down_signed ; CHECK-NOT: {{and|movz|sar|shl}} -; CHECK: decq +; CHECK: addq $-8, ; CHECK-NOT: {{and|movz|sar|shl}} ; CHECK: jne define void @another_count_down_signed(double* %d, i64 %n) nounwind { |