6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-02-21 21:29:41 +00:00
Code Issues Projects Releases Wiki Activity

Add a test case for new unrolling heuristics.

Browse Source 
THe heuristics were added in r228265 and r228434.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@228713 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Michael Zolotukhin 2015-02-10 17:54:54 +00:00
parent 11179629b5
commit 261a3a361b
1 changed files with 59 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
test/Transforms/LoopUnroll/full-unroll-heuristics.ll Normal file
View File

@ -0,0 +1,59 @@
; In this test we check how heuristics for complete unrolling work. We have
; three knobs:
; 1) -unroll-threshold
; 2) -unroll-absolute-threshold and
; 3) -unroll-percent-of-optimized-for-complete-unroll
;
; They control loop-unrolling according to the following rules:
; * If size of unrolled loop exceeds the absoulte threshold, we don't unroll
; this loop under any circumstances.
; * If size of unrolled loop is below the '-unroll-threshold', then we'll
; consider this loop as a very small one, and completely unroll it.
; * If a loop size is between these two tresholds, we only do complete unroll
; it if estimated number of potentially optimized instructions is high (we
; specify the minimal percent of such instructions).
; In this particular test-case, complete unrolling will allow later
; optimizations to remove ~55% of the instructions, the loop body size is 9,
; and unrolled size is 65.
; RUN: opt < %s -S -loop-unroll -unroll-absolute-threshold=10 -unroll-threshold=10 -unroll-percent-of-optimized-for-complete-unroll=30 | FileCheck %s -check-prefix=TEST1
; RUN: opt < %s -S -loop-unroll -unroll-absolute-threshold=100 -unroll-threshold=10 -unroll-percent-of-optimized-for-complete-unroll=30 | FileCheck %s -check-prefix=TEST2
; RUN: opt < %s -S -loop-unroll -unroll-absolute-threshold=100 -unroll-threshold=10 -unroll-percent-of-optimized-for-complete-unroll=80 | FileCheck %s -check-prefix=TEST3
; RUN: opt < %s -S -loop-unroll -unroll-absolute-threshold=100 -unroll-threshold=100 -unroll-percent-of-optimized-for-complete-unroll=80 | FileCheck %s -check-prefix=TEST4
; If the absolute threshold is too low, or if we can't optimize away requested
; percent of instructions, we shouldn't unroll:
; TEST1: %array_const_idx = getelementptr inbounds [9 x i32]* @known_constant, i64 0, i64 %iv
; TEST3: %array_const_idx = getelementptr inbounds [9 x i32]* @known_constant, i64 0, i64 %iv
; Otherwise, we should:
; TEST2-NOT: %array_const_idx = getelementptr inbounds [9 x i32]* @known_constant, i64 0, i64 %iv
; Also, we should unroll if the 'unroll-threshold' is big enough:
; TEST4-NOT: %array_const_idx = getelementptr inbounds [9 x i32]* @known_constant, i64 0, i64 %iv
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
@known_constant = internal unnamed_addr constant [9 x i32] [i32 0, i32 -1, i32 0, i32 -1, i32 5, i32 -1, i32 0, i32 -1, i32 0], align 16
define i32 @foo(i32* noalias nocapture readonly %src) {
entry:
br label %loop
loop: ; preds = %loop, %entry
%iv = phi i64 [ 0, %entry ], [ %inc, %loop ]
%r = phi i32 [ 0, %entry ], [ %add, %loop ]
%arrayidx = getelementptr inbounds i32* %src, i64 %iv
%src_element = load i32* %arrayidx, align 4
%array_const_idx = getelementptr inbounds [9 x i32]* @known_constant, i64 0, i64 %iv
%const_array_element = load i32* %array_const_idx, align 4
%mul = mul nsw i32 %src_element, %const_array_element
%add = add nsw i32 %mul, %r
%inc = add nuw nsw i64 %iv, 1
%exitcond86.i = icmp eq i64 %inc, 9
br i1 %exitcond86.i, label %loop.end, label %loop
loop.end: ; preds = %loop
%r.lcssa = phi i32 [ %r, %loop ]
ret i32 %r.lcssa
}