maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/polly/test/ScopInfo/reduction_invalid_different...

51 lines
1.5 KiB
LLVM
Raw Normal View History

Allow multiple reductions per statement Iterate over all store memory accesses and check for valid binary reduction candidate loads by following the operands of the stored value. For each candidate pair we check if they have the same base address and there are no other accesses which may overlap with them. This ensures that no intermediate value can escape into other memory locations or is overwritten at some point. + 17 test cases for reduction detection and reduction dependency modeling llvm-svn: 211957
2014-06-28 04:31:28 +08:00
; RUN: opt %loadPolly -basicaa -polly-scops -analyze < %s | FileCheck %s
;
; int f() {
; int i, sum = 0, sth = 0;
; for (i = 0; i < 1024; i++) {
; sum += 5;
; sth = sth + sth * sth + sth;
; sum *= 5;
; }
; return sum + sth;
; }
;
Introduce reduction types This change is particularly useful in the code generation as we need to know which binary operator/identity element we need to combine/initialize the privatization locations. + Print the reduction type for each memory access + Adjusted the test cases to comply with the new output format and to test for the right reduction type llvm-svn: 212126
2014-07-02 04:52:51 +08:00
; CHECK-NOT: Reduction Type: ADD
; CHECK-NOT: Reduction Type: MUL
Allow multiple reductions per statement Iterate over all store memory accesses and check for valid binary reduction candidate loads by following the operands of the stored value. For each candidate pair we check if they have the same base address and there are no other accesses which may overlap with them. This ensures that no intermediate value can escape into other memory locations or is overwritten at some point. + 17 test cases for reduction detection and reduction dependency modeling llvm-svn: 211957
2014-06-28 04:31:28 +08:00
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-n32-S64"
define i32 @f() {
entry:
%sum.0 = alloca i32
%sth.0 = alloca i32
br label %entry.split
entry.split: ; preds = %entry
store i32 0, i32* %sum.0
store i32 0, i32* %sth.0
br label %for.cond
for.cond: ; preds = %for.cond, %entry.split
%i.0 = phi i32 [ 0, %entry.split ], [ %inc, %for.cond ]
%sth.0.reload = load i32* %sth.0
%sum.0.reload = load i32* %sum.0
%exitcond = icmp ne i32 %i.0, 1024
%mul = mul nsw i32 %sth.0.reload, %sth.0.reload
%add1 = add nsw i32 %sth.0.reload, %mul
%tmp = mul i32 %sum.0.reload, 5
store i32 %tmp, i32* %sum.0
%sum.1.reload = load i32* %sum.0
%mul3 = add i32 %sum.1.reload, 25
%add2 = add nsw i32 %add1, %sth.0.reload
%inc = add nsw i32 %i.0, 1
store i32 %mul3, i32* %sum.0
store i32 %add2, i32* %sth.0
br i1 %exitcond, label %for.cond, label %for.end
for.end: ; preds = %for.cond
%sum.0.reload.2 = load i32* %sum.0
%sth.0.reload.2 = load i32* %sth.0
%add4 = add nsw i32 %sum.0.reload.2, %sth.0.reload.2
ret i32 %add4
}