diff options
| author | Nadav Rotem <nrotem@apple.com> | 2012-11-03 00:39:56 +0000 |
|---|---|---|
| committer | Nadav Rotem <nrotem@apple.com> | 2012-11-03 00:39:56 +0000 |
| commit | b4b04c3fa0a5da15424de7818e9f72811495c65b (patch) | |
| tree | 4819e241823db653ae482ef043ec8d1e23e8d1b9 /test/Analysis | |
| parent | 3c9c1ab7b7549dfaf22456d89bd241a5e8dfc0a4 (diff) | |
| download | external_llvm-b4b04c3fa0a5da15424de7818e9f72811495c65b.zip external_llvm-b4b04c3fa0a5da15424de7818e9f72811495c65b.tar.gz external_llvm-b4b04c3fa0a5da15424de7818e9f72811495c65b.tar.bz2 | |
X86 CostModel: Add support for a some of the common arithmetic instructions for SSE4, AVX and AVX2.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167347 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Analysis')
| -rw-r--r-- | test/Analysis/CostModel/X86/arith.ll | 40 | ||||
| -rw-r--r-- | test/Analysis/CostModel/X86/vectorized-loop.ll | 2 |
2 files changed, 42 insertions, 0 deletions
diff --git a/test/Analysis/CostModel/X86/arith.ll b/test/Analysis/CostModel/X86/arith.ll new file mode 100644 index 0000000..58b4a7c --- /dev/null +++ b/test/Analysis/CostModel/X86/arith.ll @@ -0,0 +1,40 @@ +; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s + +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-macosx10.8.0" + +define i32 @add(i32 %arg) { + ;CHECK: cost of 1 {{.*}} add + %A = add <4 x i32> undef, undef + ;CHECK: cost of 4 {{.*}} add + %B = add <8 x i32> undef, undef + ;CHECK: cost of 1 {{.*}} add + %C = add <2 x i64> undef, undef + ;CHECK: cost of 4 {{.*}} add + %D = add <4 x i64> undef, undef + ;CHECK: cost of 1 {{.*}} ret + ret i32 undef +} + + +define i32 @xor(i32 %arg) { + ;CHECK: cost of 1 {{.*}} xor + %A = xor <4 x i32> undef, undef + ;CHECK: cost of 1 {{.*}} xor + %B = xor <8 x i32> undef, undef + ;CHECK: cost of 1 {{.*}} xor + %C = xor <2 x i64> undef, undef + ;CHECK: cost of 1 {{.*}} xor + %D = xor <4 x i64> undef, undef + ;CHECK: cost of 1 {{.*}} ret + ret i32 undef +} + + +define i32 @fmul(i32 %arg) { + ;CHECK: cost of 1 {{.*}} fmul + %A = fmul <4 x float> undef, undef + ;CHECK: cost of 1 {{.*}} fmul + %B = fmul <8 x float> undef, undef + ret i32 undef +} diff --git a/test/Analysis/CostModel/X86/vectorized-loop.ll b/test/Analysis/CostModel/X86/vectorized-loop.ll index fbf20de..7919a9c 100644 --- a/test/Analysis/CostModel/X86/vectorized-loop.ll +++ b/test/Analysis/CostModel/X86/vectorized-loop.ll @@ -30,10 +30,12 @@ vector.body: ; preds = %for.body.lr.ph, %ve %5 = bitcast i32* %4 to <8 x i32>* ;CHECK: cost of 1 {{.*}} load %6 = load <8 x i32>* %5, align 4 + ;CHECK: cost of 4 {{.*}} mul %7 = mul nsw <8 x i32> %6, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5> %8 = getelementptr inbounds i32* %A, i64 %index %9 = bitcast i32* %8 to <8 x i32>* %10 = load <8 x i32>* %9, align 4 + ;CHECK: cost of 4 {{.*}} add %11 = add nsw <8 x i32> %10, %7 ;CHECK: cost of 1 {{.*}} store store <8 x i32> %11, <8 x i32>* %9, align 4 |