maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/polly/test/ScopDetect/non-affine-float-compare.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

48 lines
1.6 KiB
LLVM
Raw Normal View History

Do not detect Scops with only one loop. If a region does not have more than one loop, we do not identify it as a Scop in ScopDetection. The main optimizations Polly is currently performing (tiling, preparation for outer-loop vectorization and loop fusion) are unlikely to have a positive impact on individual loops. In some cases, Polly's run-time alias checks or conditional hoisting may still have a positive impact, but those are mostly enabling transformations which LLVM already performs for individual loops. As we do not focus on individual loops, we leave them untouched to not introduce compile time regressions and execution time noise. This results in good compile time reduction (oourafft: -73.99%, smg2000: -56.25%). Contributed-by: Pratik Bhatu <cs12b1010@iith.ac.in> Reviewers: grosser Differential Revision: http://reviews.llvm.org/D12268 llvm-svn: 246161
2015-08-28 00:55:18 +08:00
; RUN: opt %loadPolly -polly-detect -polly-allow-nonaffine-branches \
tests: Drop -polly-detect-unprofitable and -polly-no-early-exit These flags are now always passed to all tests and need to be disabled if not needed. Disabling these flags, rather than passing them to almost all tests, significantly simplfies our RUN: lines. llvm-svn: 249422
2015-10-06 23:36:44 +08:00
; RUN: -analyze < %s | FileCheck %s
Allow non-affine control flow -- SCoP Detection With this patch we allow the SCoP detection to detect regions as SCoPs which have non-affine control flow inside. All non-affine regions are tracked and later accessible to the ScopInfo. As there is no real difference, non-affine branches as well as floating point branches are covered (and both called non-affine control flow). However, the detection is restricted to overapproximate only loop free regions. llvm-svn: 230325
2015-02-24 19:45:21 +08:00
;
; void f(float *A) {
; for (int i = 0; i < 1024; i++)
; if (A[i] == A[i - 1])
; A[i]++;
; }
;
; CHECK: Valid Region for Scop: bb1 => bb14
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
define void @f(float* %A) {
bb:
br label %bb1
bb1: ; preds = %bb13, %bb
%indvars.iv = phi i64 [ %indvars.iv.next, %bb13 ], [ 0, %bb ]
%exitcond = icmp ne i64 %indvars.iv, 1024
br i1 %exitcond, label %bb2, label %bb14
bb2: ; preds = %bb1
Update Polly tests to handle explicitly typed gep changes in LLVM llvm-svn: 230784
2015-02-28 03:20:19 +08:00
%tmp = getelementptr inbounds float, float* %A, i64 %indvars.iv
Update Polly tests to handle explicitly typed load changes in LLVM. llvm-svn: 230796
2015-02-28 05:22:50 +08:00
%tmp3 = load float, float* %tmp, align 4
Allow non-affine control flow -- SCoP Detection With this patch we allow the SCoP detection to detect regions as SCoPs which have non-affine control flow inside. All non-affine regions are tracked and later accessible to the ScopInfo. As there is no real difference, non-affine branches as well as floating point branches are covered (and both called non-affine control flow). However, the detection is restricted to overapproximate only loop free regions. llvm-svn: 230325
2015-02-24 19:45:21 +08:00
%tmp4 = add nsw i64 %indvars.iv, -1
Update Polly tests to handle explicitly typed gep changes in LLVM llvm-svn: 230784
2015-02-28 03:20:19 +08:00
%tmp5 = getelementptr inbounds float, float* %A, i64 %tmp4
Update Polly tests to handle explicitly typed load changes in LLVM. llvm-svn: 230796
2015-02-28 05:22:50 +08:00
%tmp6 = load float, float* %tmp5, align 4
Allow non-affine control flow -- SCoP Detection With this patch we allow the SCoP detection to detect regions as SCoPs which have non-affine control flow inside. All non-affine regions are tracked and later accessible to the ScopInfo. As there is no real difference, non-affine branches as well as floating point branches are covered (and both called non-affine control flow). However, the detection is restricted to overapproximate only loop free regions. llvm-svn: 230325
2015-02-24 19:45:21 +08:00
%tmp7 = fcmp oeq float %tmp3, %tmp6
br i1 %tmp7, label %bb8, label %bb12
bb8: ; preds = %bb2
Update Polly tests to handle explicitly typed gep changes in LLVM llvm-svn: 230784
2015-02-28 03:20:19 +08:00
%tmp9 = getelementptr inbounds float, float* %A, i64 %indvars.iv
Update Polly tests to handle explicitly typed load changes in LLVM. llvm-svn: 230796
2015-02-28 05:22:50 +08:00
%tmp10 = load float, float* %tmp9, align 4
Allow non-affine control flow -- SCoP Detection With this patch we allow the SCoP detection to detect regions as SCoPs which have non-affine control flow inside. All non-affine regions are tracked and later accessible to the ScopInfo. As there is no real difference, non-affine branches as well as floating point branches are covered (and both called non-affine control flow). However, the detection is restricted to overapproximate only loop free regions. llvm-svn: 230325
2015-02-24 19:45:21 +08:00
%tmp11 = fadd float %tmp10, 1.000000e+00
store float %tmp11, float* %tmp9, align 4
br label %bb12
bb12: ; preds = %bb8, %bb2
br label %bb13
bb13: ; preds = %bb12
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
br label %bb1
bb14: ; preds = %bb1
ret void
}