09d3069740
Besides class, function and file names, we also change the command line option from -polly-codegen-isl to just -polly-codegen. The isl postfix is a leftover from the times when we still had the CLooG based -polly-codegen. Today it is just redundant and we drop it. llvm-svn: 237099
43 lines
2.2 KiB
LLVM
43 lines
2.2 KiB
LLVM
; RUN: opt %loadPolly -polly-detect-unprofitable -basicaa -polly-codegen -polly-vectorizer=polly -dce -S < %s | 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"
|
|
|
|
@A = common global [1024 x float] zeroinitializer, align 16
|
|
@B = common global [1024 x float**] zeroinitializer, align 16
|
|
|
|
declare float** @foo(float) readnone
|
|
|
|
define void @simple_vec_call() nounwind {
|
|
entry:
|
|
br label %body
|
|
|
|
body:
|
|
%indvar = phi i64 [ 0, %entry ], [ %indvar_next, %body ]
|
|
%scevgep = getelementptr [1024 x float**], [1024 x float**]* @B, i64 0, i64 %indvar
|
|
%value = load float, float* getelementptr inbounds ([1024 x float], [1024 x float]* @A, i64 0, i64 0), align 16
|
|
%result = tail call float** @foo(float %value) nounwind
|
|
store float** %result, float*** %scevgep, align 4
|
|
%indvar_next = add i64 %indvar, 1
|
|
%exitcond = icmp eq i64 %indvar_next, 4
|
|
br i1 %exitcond, label %return, label %body
|
|
|
|
return:
|
|
ret void
|
|
}
|
|
|
|
; CHECK: %value_p_splat_one = load <1 x float>, <1 x float>* bitcast ([1024 x float]* @A to <1 x float>*), align 8
|
|
; CHECK: %value_p_splat = shufflevector <1 x float> %value_p_splat_one, <1 x float> %value_p_splat_one, <4 x i32> zeroinitializer
|
|
; CHECK: %0 = extractelement <4 x float> %value_p_splat, i32 0
|
|
; CHECK: %1 = extractelement <4 x float> %value_p_splat, i32 1
|
|
; CHECK: %2 = extractelement <4 x float> %value_p_splat, i32 2
|
|
; CHECK: %3 = extractelement <4 x float> %value_p_splat, i32 3
|
|
; CHECK: [[RES1:%[a-zA-Z0-9_]+]] = tail call float** @foo(float %0) [[NUW:#[0-9]+]]
|
|
; CHECK: [[RES2:%[a-zA-Z0-9_]+]] = tail call float** @foo(float %1) [[NUW]]
|
|
; CHECK: [[RES3:%[a-zA-Z0-9_]+]] = tail call float** @foo(float %2) [[NUW]]
|
|
; CHECK: [[RES4:%[a-zA-Z0-9_]+]] = tail call float** @foo(float %3) [[NUW]]
|
|
; CHECK: %4 = insertelement <4 x float**> undef, float** %p_result, i32 0
|
|
; CHECK: %5 = insertelement <4 x float**> %4, float** %p_result1, i32 1
|
|
; CHECK: %6 = insertelement <4 x float**> %5, float** %p_result2, i32 2
|
|
; CHECK: %7 = insertelement <4 x float**> %6, float** %p_result3, i32 3
|
|
; CHECK: store <4 x float**> %7, <4 x float**>* bitcast ([1024 x float**]* @B to <4 x float**>*), align
|
|
; CHECK: attributes [[NUW]] = { nounwind }
|