maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

test: LLVM supports now vectors of arbitrary pointers 

This allows Polly to vectorize more code. Fix the relevant test cases.

llvm-svn: 167923
This commit is contained in:
Tobias Grosser 2012-11-14 08:25:52 +00:00
parent c4343f2c45
commit 3344f733fd
3 changed files with 51 additions and 59 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
polly/test/CodeGen/simple_vec_call_2.ll
View File

@ -27,9 +27,6 @@ return:
}
; CHECK: %p_scevgep = getelementptr [1024 x float**]* @B, i64 0, i64 0
; CHECK: %p_scevgep1 = getelementptr [1024 x float**]* @B, i64 0, i64 1
; CHECK: %p_scevgep2 = getelementptr [1024 x float**]* @B, i64 0, i64 2
; CHECK: %p_scevgep3 = getelementptr [1024 x float**]* @B, i64 0, i64 3
; CHECK: %value_p_splat_one = load <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
@ -40,10 +37,12 @@ return:
; CHECK: [[RES2:%[a-zA-Z0-9_]+]] = tail call float** @foo(float %1) nounwind
; CHECK: [[RES3:%[a-zA-Z0-9_]+]] = tail call float** @foo(float %2) nounwind
; CHECK: [[RES4:%[a-zA-Z0-9_]+]] = tail call float** @foo(float %3) nounwind
; CHECK: store float** [[RES1]], float*** %p_scevgep, align 4
; CHECK: store float** [[RES2]], float*** %p_scevgep1, align 4
; CHECK: store float** [[RES3]], float*** %p_scevgep2, align 4
; CHECK: store float** [[RES4]], float*** %p_scevgep3, align 4
; CHECK: %4 = insertelement <4 x float**> undef, float** %p_result, i32 0
; CHECK: %5 = insertelement <4 x float**> %4, float** %p_result4, i32 1
; CHECK: %6 = insertelement <4 x float**> %5, float** %p_result5, i32 2
; CHECK: %7 = insertelement <4 x float**> %6, float** %p_result6, i32 3
; CHECK: %vector_ptr = bitcast float*** %p_scevgep to <4 x float**>*
; CHECK: store <4 x float**> %7, <4 x float**>* %vector_ptr, align 8
; CHECK-SCEV: %value_p_splat_one = load <1 x float>* bitcast ([1024 x float]* @A to <1 x float>*), align 8
; CHECK-SCEV: %value_p_splat = shufflevector <1 x float> %value_p_splat_one, <1 x float> %value_p_splat_one, <4 x i32> zeroinitializer
@ -55,7 +54,8 @@ return:
; CHECK-SCEV: [[RES2:%[a-zA-Z0-9_]+]] = tail call float** @foo(float %1) nounwind
; CHECK-SCEV: [[RES3:%[a-zA-Z0-9_]+]] = tail call float** @foo(float %2) nounwind
; CHECK-SCEV: [[RES4:%[a-zA-Z0-9_]+]] = tail call float** @foo(float %3) nounwind
; CHECK-SCEV: store float** [[RES1]], float*** getelementptr inbounds ([1024 x float**]* @B, i64 0, i64 0), align 4
; CHECK-SCEV: store float** [[RES2]], float*** getelementptr inbounds ([1024 x float**]* @B, i64 0, i64 1), align 4
; CHECK-SCEV: store float** [[RES3]], float*** getelementptr inbounds ([1024 x float**]* @B, i64 0, i64 2), align 4
; CHECK-SCEV: store float** [[RES4]], float*** getelementptr inbounds ([1024 x float**]* @B, i64 0, i64 3), align 4
; CHECK-SCEV: %4 = insertelement <4 x float**> undef, float** %p_result, i32 0
; CHECK-SCEV: %5 = insertelement <4 x float**> %4, float** %p_result1, i32 1
; CHECK-SCEV: %6 = insertelement <4 x float**> %5, float** %p_result2, i32 2
; CHECK-SCEV: %7 = insertelement <4 x float**> %6, float** %p_result3, i32 3
; CHECK-SCEV: store <4 x float**> %7, <4 x float**>* bitcast ([1024 x float**]* @B to <4 x float**>*), align

48
polly/test/CodeGen/simple_vec_impossible.ll
View File

@ -1,48 +0,0 @@
; RUN: opt %loadPolly -basicaa -polly-codegen %vector-opt -S -polly-codegen-scev=false < %s | FileCheck %s
; RUN: opt %loadPolly -basicaa -polly-codegen %vector-opt -S -polly-codegen-scev=true < %s | FileCheck %s -check-prefix=CHECK-SCEV
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"
target triple = "x86_64-unknown-linux-gnu"
@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**]* @B, i64 0, i64 %indvar
%value = load float*** getelementptr inbounds ([1024 x float**]* @A, i64 0, i64 0), align 16
store float** %value, 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: %p_scevgep = getelementptr [1024 x float**]* @B, i64 0, i64 0
; CHECK: %p_scevgep1 = getelementptr [1024 x float**]* @B, i64 0, i64 1
; CHECK: %p_scevgep2 = getelementptr [1024 x float**]* @B, i64 0, i64 2
; CHECK: %p_scevgep3 = getelementptr [1024 x float**]* @B, i64 0, i64 3
; CHECK: %value_p_scalar_ = load float*** getelementptr inbounds ([1024 x float**]* @A, i64 0, i64 0)
; CHECK: %value_p_scalar_4 = load float*** getelementptr inbounds ([1024 x float**]* @A, i64 0, i64 0)
; CHECK: %value_p_scalar_5 = load float*** getelementptr inbounds ([1024 x float**]* @A, i64 0, i64 0)
; CHECK: %value_p_scalar_6 = load float*** getelementptr inbounds ([1024 x float**]* @A, i64 0, i64 0)
; CHECK: store float** %value_p_scalar_, float*** %p_scevgep, align 4
; CHECK: store float** %value_p_scalar_4, float*** %p_scevgep1, align 4
; CHECK: store float** %value_p_scalar_5, float*** %p_scevgep2, align 4
; CHECK: store float** %value_p_scalar_6, float*** %p_scevgep3, align 4
; CHECK-SCEV: %value_p_scalar_ = load float*** getelementptr inbounds ([1024 x float**]* @A, i64 0, i64 0)
; CHECK-SCEV: %value_p_scalar_1 = load float*** getelementptr inbounds ([1024 x float**]* @A, i64 0, i64 0)
; CHECK-SCEV: %value_p_scalar_2 = load float*** getelementptr inbounds ([1024 x float**]* @A, i64 0, i64 0)
; CHECK-SCEV: %value_p_scalar_3 = load float*** getelementptr inbounds ([1024 x float**]* @A, i64 0, i64 0)
; CHECK-SCEV: store float** %value_p_scalar_, float*** getelementptr inbounds ([1024 x float**]* @B, i64 0, i64 0), align 4
; CHECK-SCEV: store float** %value_p_scalar_1, float*** getelementptr inbounds ([1024 x float**]* @B, i64 0, i64 1), align 4
; CHECK-SCEV: store float** %value_p_scalar_2, float*** getelementptr inbounds ([1024 x float**]* @B, i64 0, i64 2), align 4
; CHECK-SCEV: store float** %value_p_scalar_3, float*** getelementptr inbounds ([1024 x float**]* @B, i64 0, i64 3), align 4

40
polly/test/CodeGen/simple_vec_ptr_ptr_ty.ll Normal file
View File

@ -0,0 +1,40 @@
; RUN: opt %loadPolly -basicaa -polly-codegen %vector-opt -S -polly-codegen-scev=false < %s | FileCheck %s
; RUN: opt %loadPolly -basicaa -polly-codegen %vector-opt -S -polly-codegen-scev=true < %s | FileCheck %s -check-prefix=CHECK-SCEV
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"
target triple = "x86_64-unknown-linux-gnu"
@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**]* @B, i64 0, i64 %indvar
%value = load float*** getelementptr inbounds ([1024 x float**]* @A, i64 0, i64 0), align 16
store float** %value, 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: %p_scevgep = getelementptr [1024 x float**]* @B, i64 0, i64 0
; CHECK: %p_scevgep1 = getelementptr [1024 x float**]* @B, i64 0, i64 1
; CHECK: %p_scevgep2 = getelementptr [1024 x float**]* @B, i64 0, i64 2
; CHECK: %p_scevgep3 = getelementptr [1024 x float**]* @B, i64 0, i64 3
; CHECK: %value_p_splat_one = load <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: %vector_ptr = bitcast float*** %p_scevgep to <4 x float**>*
; CHECK: store <4 x float**> %value_p_splat, <4 x float**>* %vector_ptr
; CHECK-SCEV: %value_p_splat_one = load <1 x float**>* bitcast ([1024 x float**]* @A to <1 x float**>*), align 8
; CHECK-SCEV: %value_p_splat = shufflevector <1 x float**> %value_p_splat_one, <1 x float**> %value_p_splat_one, <4 x i32> zeroinitializer
; CHECK-SCEV: store <4 x float**> %value_p_splat, <4 x float**>* bitcast ([1024 x float**]* @B to <4 x float**>*), align 8