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

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

62 lines
2.2 KiB
LLVM
Raw Normal View History

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: opt %loadPolly -polly-ast -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -polly-codegen -S < %s | FileCheck %s -check-prefix=CODEGEN
; RUN: opt %loadPolly -polly-codegen -loops -analyze < %s | FileCheck %s -check-prefix=LOOPS
isl-codegen: Support '<' and '>' Previously isl always generated '<=' or '>='. However, in many cases '<' or '>' leads to simpler code. This commit updates isl and adds the relevant code generation support to Polly. llvm-svn: 166020
2012-10-16 15:29:13 +08:00
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"
@A = common global [1024 x i32] zeroinitializer
define void @bar(i64 %n) {
start:
%n_plus_one = add i64 %n, 1
fence seq_cst
br label %loop.header
loop.header:
%i = phi i64 [ 0, %start ], [ %i.next, %loop.backedge ]
Update Polly tests to handle explicitly typed gep changes in LLVM llvm-svn: 230784
2015-02-28 03:20:19 +08:00
%scevgep = getelementptr [1024 x i32], [1024 x i32]* @A, i64 0, i64 %i
isl-codegen: Support '<' and '>' Previously isl always generated '<=' or '>='. However, in many cases '<' or '>' leads to simpler code. This commit updates isl and adds the relevant code generation support to Polly. llvm-svn: 166020
2012-10-16 15:29:13 +08:00
%exitcond = icmp ne i64 %i, %n_plus_one
br i1 %exitcond, label %loop.body, label %ret
loop.body:
store i32 1, i32* %scevgep
br label %loop.backedge
loop.backedge:
%i.next = add nsw i64 %i, 1
br label %loop.header
ret:
fence seq_cst
ret void
}
Drop all constant scheduling dimensions Schedule dimensions that have the same constant value accross all statements do not carry any information, but due to the increased dimensionality of the schedule cost compile time. To not pay this cost, we remove constant dimensions if possible. llvm-svn: 225067
2015-01-02 07:01:11 +08:00
; CHECK: for (int c0 = 0; c0 <= n; c0 += 1)
; CHECK: Stmt_loop_body(c0)
isl-codegen: Support '<' and '>' Previously isl always generated '<=' or '>='. However, in many cases '<' or '>' leads to simpler code. This commit updates isl and adds the relevant code generation support to Polly. llvm-svn: 166020
2012-10-16 15:29:13 +08:00
; CODEGEN: polly.start:
LoopGenerators: Construct loops such that they are already loop rotated BeforeBB | v GuardBB / \ __ PreHeaderBB \ / \ / | latch HeaderBB | \ / \ / < \ / \ / ExitBB This does not only remove the need for an explicit loop rotate pass, but it also gives us the possibility to skip the construction of the guard condition in case the loop is known to be executed at least once. We do not yet exploit this, but by implementing this analysis in the isl code generator we should be able to remove more guards than the generic loop rotate pass can. Another point is that loop rotation can introduce additional PHI nodes, which may hide that a loop can be executed in parallel. This change avoids this complication and will make it easier to move the openmp code generation into a separate pass. llvm-svn: 181986
2013-05-16 14:40:06 +08:00
; CODEGEN: br label %polly.loop_if
isl-codegen: Support '<' and '>' Previously isl always generated '<=' or '>='. However, in many cases '<' or '>' leads to simpler code. This commit updates isl and adds the relevant code generation support to Polly. llvm-svn: 166020
2012-10-16 15:29:13 +08:00
LoopGenerators: Construct loops such that they are already loop rotated BeforeBB | v GuardBB / \ __ PreHeaderBB \ / \ / | latch HeaderBB | \ / \ / < \ / \ / ExitBB This does not only remove the need for an explicit loop rotate pass, but it also gives us the possibility to skip the construction of the guard condition in case the loop is known to be executed at least once. We do not yet exploit this, but by implementing this analysis in the isl code generator we should be able to remove more guards than the generic loop rotate pass can. Another point is that loop rotation can introduce additional PHI nodes, which may hide that a loop can be executed in parallel. This change avoids this complication and will make it easier to move the openmp code generation into a separate pass. llvm-svn: 181986
2013-05-16 14:40:06 +08:00
; CODEGEN: polly.loop_exit:
isl-codegen: Support '<' and '>' Previously isl always generated '<=' or '>='. However, in many cases '<' or '>' leads to simpler code. This commit updates isl and adds the relevant code generation support to Polly. llvm-svn: 166020
2012-10-16 15:29:13 +08:00
; CODEGEN: br label %polly.merge_new_and_old
LoopGenerators: Construct loops such that they are already loop rotated BeforeBB | v GuardBB / \ __ PreHeaderBB \ / \ / | latch HeaderBB | \ / \ / < \ / \ / ExitBB This does not only remove the need for an explicit loop rotate pass, but it also gives us the possibility to skip the construction of the guard condition in case the loop is known to be executed at least once. We do not yet exploit this, but by implementing this analysis in the isl code generator we should be able to remove more guards than the generic loop rotate pass can. Another point is that loop rotation can introduce additional PHI nodes, which may hide that a loop can be executed in parallel. This change avoids this complication and will make it easier to move the openmp code generation into a separate pass. llvm-svn: 181986
2013-05-16 14:40:06 +08:00
; CODEGEN: polly.loop_if:
; CODEGEN: %polly.loop_guard = icmp sle i64 0, %n
; CODEGEN: br i1 %polly.loop_guard, label %polly.loop_preheader, label %polly.loop_exit
isl-codegen: Support '<' and '>' Previously isl always generated '<=' or '>='. However, in many cases '<' or '>' leads to simpler code. This commit updates isl and adds the relevant code generation support to Polly. llvm-svn: 166020
2012-10-16 15:29:13 +08:00
LoopGenerators: Construct loops such that they are already loop rotated BeforeBB | v GuardBB / \ __ PreHeaderBB \ / \ / | latch HeaderBB | \ / \ / < \ / \ / ExitBB This does not only remove the need for an explicit loop rotate pass, but it also gives us the possibility to skip the construction of the guard condition in case the loop is known to be executed at least once. We do not yet exploit this, but by implementing this analysis in the isl code generator we should be able to remove more guards than the generic loop rotate pass can. Another point is that loop rotation can introduce additional PHI nodes, which may hide that a loop can be executed in parallel. This change avoids this complication and will make it easier to move the openmp code generation into a separate pass. llvm-svn: 181986
2013-05-16 14:40:06 +08:00
; CODEGEN: polly.loop_header:
; CODEGEN: %polly.indvar = phi i64 [ 0, %polly.loop_preheader ], [ %polly.indvar_next, %polly.stmt.loop.body ]
isl-codegen: Support '<' and '>' Previously isl always generated '<=' or '>='. However, in many cases '<' or '>' leads to simpler code. This commit updates isl and adds the relevant code generation support to Polly. llvm-svn: 166020
2012-10-16 15:29:13 +08:00
; CODEGEN: br label %polly.stmt.loop.body
; CODEGEN: polly.stmt.loop.body:
Update Polly tests to handle explicitly typed gep changes in LLVM llvm-svn: 230784
2015-02-28 03:20:19 +08:00
; CODEGEN: [[PTR:%[a-zA-Z0-9_\.]+]] = getelementptr [1024 x i32], [1024 x i32]* @A, i64 0, i64 %polly.indvar
Modify test cases to work with SCEV based code generation This patch includes tests where we actually need to adjust the CHECK lines for SCEV based code generation. Besides these adjustments we add explicit calls to -polly-codegen-scev=[true|false] and make sure we test both cases. llvm-svn: 222112
2014-11-17 06:43:21 +08:00
; CODEGEN: store i32 1, i32* [[PTR]]
LoopGenerators: Construct loops such that they are already loop rotated BeforeBB | v GuardBB / \ __ PreHeaderBB \ / \ / | latch HeaderBB | \ / \ / < \ / \ / ExitBB This does not only remove the need for an explicit loop rotate pass, but it also gives us the possibility to skip the construction of the guard condition in case the loop is known to be executed at least once. We do not yet exploit this, but by implementing this analysis in the isl code generator we should be able to remove more guards than the generic loop rotate pass can. Another point is that loop rotation can introduce additional PHI nodes, which may hide that a loop can be executed in parallel. This change avoids this complication and will make it easier to move the openmp code generation into a separate pass. llvm-svn: 181986
2013-05-16 14:40:06 +08:00
; CODEGEN: %polly.indvar_next = add nsw i64 %polly.indvar, 1
[Polly] Generate more 'canonical' induction variable Today Polly generates induction variable in this way: polly.indvar = phi 0, polly.indvar.next ... polly.indvar.next = polly.indvar + stide polly.loop_cond = predicate polly.indvar, (UB - stride) Instead of: polly.indvar = phi 0, polly.indvar.next ... polly.indvar.next = polly.indvar + stide polly.loop_cond = predicate polly.indvar.next, UB The way Polly generate induction variable cause some problem in the indvar simplify pass. This patch make polly generate the later form, by assuming the induction variable never overflow Differential Revision: https://reviews.llvm.org/D33089 llvm-svn: 302866
2017-05-12 10:17:15 +08:00
; CODEGEN: %polly.loop_cond = icmp sle i64 %polly.indvar_next, %n
LoopGenerators: Construct loops such that they are already loop rotated BeforeBB | v GuardBB / \ __ PreHeaderBB \ / \ / | latch HeaderBB | \ / \ / < \ / \ / ExitBB This does not only remove the need for an explicit loop rotate pass, but it also gives us the possibility to skip the construction of the guard condition in case the loop is known to be executed at least once. We do not yet exploit this, but by implementing this analysis in the isl code generator we should be able to remove more guards than the generic loop rotate pass can. Another point is that loop rotation can introduce additional PHI nodes, which may hide that a loop can be executed in parallel. This change avoids this complication and will make it easier to move the openmp code generation into a separate pass. llvm-svn: 181986
2013-05-16 14:40:06 +08:00
; CODEGEN: br i1 %polly.loop_cond, label %polly.loop_header, label %polly.loop_exit
; CODEGEN: polly.loop_preheader:
isl-codegen: Support '<' and '>' Previously isl always generated '<=' or '>='. However, in many cases '<' or '>' leads to simpler code. This commit updates isl and adds the relevant code generation support to Polly. llvm-svn: 166020
2012-10-16 15:29:13 +08:00
; CODEGEN: br label %polly.loop_header
Update LoopInfo correctly When the Polly code generation was written we did not correctly update the LoopInfo data, but still claimed that the loop information is correct. This does not only lead to missed optimizations, but it can also cause miscompilations in case passes such as LoopSimplify are run after Polly. Reported-by: Sergei Larin <slarin@codeaurora.org> llvm-svn: 181987
2013-05-16 14:40:24 +08:00
[IslAst] Untangle IslAst lit-testcases from specifics of the legacy-PM Summary: This consists instances of two changes: - Accept any order of checks for a specific loop form, that appear in different order in the new vs legacy-PM. - Remove checks for specific regions. Reviewers: grosser Reviewed By: grosser Subscribers: pollydev, llvm-commits Tags: #polly Differential Revision: https://reviews.llvm.org/D35837 llvm-svn: 308976
2017-07-25 23:07:42 +08:00
; LOOPS-DAG: Loop at depth 1 containing: %loop.header<header><exiting>,%loop.body,%loop.backedge<latch>
; LOOPS-DAG: Loop at depth 1 containing: %polly.loop_header<header>,%polly.stmt.loop.body<latch><exiting>