From f74e9bf650d7c40d595d3bb60e3c901e2bccec4b Mon Sep 17 00:00:00 2001 From: Michael Liao Date: Wed, 20 Mar 2013 22:01:10 +0000 Subject: Correct cost model for vector shift on AVX2 - After moving logic recognizing vector shift with scalar amount from DAG combining into DAG lowering, we declare to customize all vector shifts even vector shift on AVX is legal. As a result, the cost model needs special tuning to identify these legal cases. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177586 91177308-0d34-0410-b5e6-96231b3b80d8 --- test/Analysis/CostModel/X86/arith.ll | 54 ++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) (limited to 'test/Analysis/CostModel/X86/arith.ll') diff --git a/test/Analysis/CostModel/X86/arith.ll b/test/Analysis/CostModel/X86/arith.ll index f0521bae48..5f9444157a 100644 --- a/test/Analysis/CostModel/X86/arith.ll +++ b/test/Analysis/CostModel/X86/arith.ll @@ -72,3 +72,57 @@ define i32 @fmul(i32 %arg) { %B = fmul <8 x float> undef, undef ret i32 undef } + +; AVX: shift +; AVX2: shift +define void @shift() { + ; AVX: cost of 2 {{.*}} shl + ; AVX2: cost of 1 {{.*}} shl + %A0 = shl <4 x i32> undef, undef + ; AVX: cost of 2 {{.*}} shl + ; AVX2: cost of 1 {{.*}} shl + %A1 = shl <2 x i64> undef, undef + + ; AVX: cost of 2 {{.*}} lshr + ; AVX2: cost of 1 {{.*}} lshr + %B0 = lshr <4 x i32> undef, undef + ; AVX: cost of 2 {{.*}} lshr + ; AVX2: cost of 1 {{.*}} lshr + %B1 = lshr <2 x i64> undef, undef + + ; AVX: cost of 2 {{.*}} ashr + ; AVX2: cost of 1 {{.*}} ashr + %C0 = ashr <4 x i32> undef, undef + ; AVX: cost of 6 {{.*}} ashr + ; AVX2: cost of 6 {{.*}} ashr + %C1 = ashr <2 x i64> undef, undef + + ret void +} + +; AVX: avx2shift +; AVX2: avx2shift +define void @avx2shift() { + ; AVX: cost of 2 {{.*}} shl + ; AVX2: cost of 1 {{.*}} shl + %A0 = shl <8 x i32> undef, undef + ; AVX: cost of 2 {{.*}} shl + ; AVX2: cost of 1 {{.*}} shl + %A1 = shl <4 x i64> undef, undef + + ; AVX: cost of 2 {{.*}} lshr + ; AVX2: cost of 1 {{.*}} lshr + %B0 = lshr <8 x i32> undef, undef + ; AVX: cost of 2 {{.*}} lshr + ; AVX2: cost of 1 {{.*}} lshr + %B1 = lshr <4 x i64> undef, undef + + ; AVX: cost of 2 {{.*}} ashr + ; AVX2: cost of 1 {{.*}} ashr + %C0 = ashr <8 x i32> undef, undef + ; AVX: cost of 12 {{.*}} ashr + ; AVX2: cost of 12 {{.*}} ashr + %C1 = ashr <4 x i64> undef, undef + + ret void +} -- cgit v1.2.3-18-g5258