Displaying 3 results from an estimated 3 matches for "next21248".
2012 Jan 17
0
[LLVMdev] [llvm-commits] [PATCH] BasicBlock Autovectorization Pass
Hi,
On Fri, Dec 30, 2011 at 3:09 AM, Tobias Grosser <tobias at grosser.es> wrote:
> As it seems my intuition is wrong, I am very eager to see and understand
> an example where a search limit of 4000 is really needed.
>
To make the ball roll again, I attached a testcase that can be tuned
to understand the impact on compile time for different sizes of a
basic block. One can also
2011 Dec 30
3
[LLVMdev] [llvm-commits] [PATCH] BasicBlock Autovectorization Pass
On 12/29/2011 06:32 PM, Hal Finkel wrote:
> On Thu, 2011-12-29 at 15:00 +0100, Tobias Grosser wrote:
>> On 12/14/2011 01:25 AM, Hal Finkel wrote:
>> One thing that I would still like to have is a test case where
>> bb-vectorize-search-limit is needed to avoid exponential compile time
>> growth and another test case that is not optimized, if
>>
2012 Jan 24
4
[LLVMdev] [llvm-commits] [PATCH] BasicBlock Autovectorization Pass
...ounwind uwtable readnone {
entry:
%A = alloca [100 x i32], align 16
%B = alloca [100 x i32], align 16
%C = alloca [100 x i32], align 16
br label %for.body
for.body: ; preds = %for.body, %entry
%indvars.iv21247 = phi i64 [ 0, %entry ], [ %indvars.iv.next21248, %for.body ]
%arrayidx = getelementptr inbounds [100 x i32]* %A, i64 0, i64 %indvars.iv21247
%0 = trunc i64 %indvars.iv21247 to i32
store i32 %0, i32* %arrayidx, align 4, !tbaa !0
%1 = add nsw i64 %indvars.iv21247, 42
%arrayidx2 = getelementptr inbounds [100 x i32]* %B, i64 0, i64 %indvar...