maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/LoopVectorize/iv_outside_user.ll

136 lines
3.8 KiB
LLVM
Raw Normal View History

Recommit [LV] Enable vectorization of loops where the IV has an external use r272715 broke libcxx because it did not correctly handle cases where the last iteration of one IV is the second-to-last iteration of another. Original commit message: Vectorizing loops with "escaping" IVs has been disabled since r190790, due to PR17179. This re-enables it, with support for external use of both "post-increment" (last iteration) and "pre-increment" (second-to-last iteration) IVs. llvm-svn: 272742
2016-06-15 08:35:26 +08:00
; RUN: opt -S -loop-vectorize -force-vector-interleave=1 -force-vector-width=2 < %s | FileCheck %s
; CHECK-LABEL: @postinc
; CHECK-LABEL: scalar.ph:
; CHECK: %bc.resume.val = phi i32 [ %n.vec, %middle.block ], [ 0, %entry ]
; CHECK-LABEL: for.end:
; CHECK: %[[RET:.*]] = phi i32 [ {{.*}}, %for.body ], [ %n.vec, %middle.block ]
; CHECK: ret i32 %[[RET]]
define i32 @postinc(i32 %k) {
entry:
br label %for.body
for.body:
%inc.phi = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%inc = add nsw i32 %inc.phi, 1
%cmp = icmp eq i32 %inc, %k
br i1 %cmp, label %for.end, label %for.body
for.end:
ret i32 %inc
}
; CHECK-LABEL: @preinc
; CHECK-LABEL: middle.block:
[LV] Don't widen trivial induction variables We currently always vectorize induction variables. However, if an induction variable is only used for counting loop iterations or computing addresses with getelementptr instructions, we don't need to do this. Vectorizing these trivial induction variables can create vector code that is difficult to simplify later on. This is especially true when the unroll factor is greater than one, and we create vector arithmetic when computing step vectors. With this patch, we check if an induction variable is only used for counting iterations or computing addresses, and if so, scalarize the arithmetic when computing step vectors instead. This allows for greater simplification. This patch addresses the suboptimal pointer arithmetic sequence seen in PR27881. Reference: https://llvm.org/bugs/show_bug.cgi?id=27881 Differential Revision: http://reviews.llvm.org/D21620 llvm-svn: 274627
2016-07-06 22:26:59 +08:00
; CHECK: %[[v3:.+]] = sub i32 %n.vec, 1
; CHECK: %ind.escape = add i32 0, %[[v3]]
Recommit [LV] Enable vectorization of loops where the IV has an external use r272715 broke libcxx because it did not correctly handle cases where the last iteration of one IV is the second-to-last iteration of another. Original commit message: Vectorizing loops with "escaping" IVs has been disabled since r190790, due to PR17179. This re-enables it, with support for external use of both "post-increment" (last iteration) and "pre-increment" (second-to-last iteration) IVs. llvm-svn: 272742
2016-06-15 08:35:26 +08:00
; CHECK-LABEL: scalar.ph:
; CHECK: %bc.resume.val = phi i32 [ %n.vec, %middle.block ], [ 0, %entry ]
; CHECK-LABEL: for.end:
; CHECK: %[[RET:.*]] = phi i32 [ {{.*}}, %for.body ], [ %ind.escape, %middle.block ]
; CHECK: ret i32 %[[RET]]
define i32 @preinc(i32 %k) {
entry:
br label %for.body
for.body:
%inc.phi = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%inc = add nsw i32 %inc.phi, 1
%cmp = icmp eq i32 %inc, %k
br i1 %cmp, label %for.end, label %for.body
for.end:
ret i32 %inc.phi
}
; CHECK-LABEL: @constpre
; CHECK-LABEL: for.end:
; CHECK: %[[RET:.*]] = phi i32 [ {{.*}}, %for.body ], [ 2, %middle.block ]
; CHECK: ret i32 %[[RET]]
define i32 @constpre() {
entry:
br label %for.body
for.body:
%inc.phi = phi i32 [ 32, %entry ], [ %inc, %for.body ]
%inc = sub nsw i32 %inc.phi, 2
%cmp = icmp eq i32 %inc, 0
br i1 %cmp, label %for.end, label %for.body
for.end:
ret i32 %inc.phi
}
; CHECK-LABEL: @geppre
; CHECK-LABEL: middle.block:
; CHECK: %ind.escape = getelementptr i32, i32* %ptr, i64 124
; CHECK-LABEL: for.end:
; CHECK: %[[RET:.*]] = phi i32* [ {{.*}}, %for.body ], [ %ind.escape, %middle.block ]
; CHECK: ret i32* %[[RET]]
define i32* @geppre(i32* %ptr) {
entry:
br label %for.body
for.body:
%inc.phi = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%ptr.phi = phi i32* [ %ptr, %entry ], [ %inc.ptr, %for.body ]
%inc = add nsw i32 %inc.phi, 1
%inc.ptr = getelementptr i32, i32* %ptr.phi, i32 4
%cmp = icmp eq i32 %inc, 32
br i1 %cmp, label %for.end, label %for.body
for.end:
ret i32* %ptr.phi
}
; CHECK-LABEL: @both
; CHECK-LABEL: middle.block:
; CHECK: %[[END:.*]] = sub i64 %n.vec, 1
; CHECK: %ind.escape = getelementptr i32, i32* %base, i64 %[[END]]
; CHECK-LABEL: for.end:
; CHECK: %[[RET:.*]] = phi i32* [ %inc.lag1, %for.body ], [ %ind.escape, %middle.block ]
; CHECK: ret i32* %[[RET]]
define i32* @both(i32 %k) {
entry:
%base = getelementptr inbounds i32, i32* undef, i64 1
br label %for.body
for.body:
%inc.phi = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%inc.lag1 = phi i32* [ %base, %entry ], [ %tmp, %for.body]
%inc.lag2 = phi i32* [ undef, %entry ], [ %inc.lag1, %for.body]
%tmp = getelementptr inbounds i32, i32* %inc.lag1, i64 1
%inc = add nsw i32 %inc.phi, 1
%cmp = icmp eq i32 %inc, %k
br i1 %cmp, label %for.end, label %for.body
for.end:
ret i32* %inc.lag1
}
[LV] Remove wrong assumption about LCSSA The LCSSA pass itself will not generate several redundant PHI nodes in a single exit block. However, such redundant PHI nodes don't violate LCSSA form, and may be introduced by passes that preserve LCSSA, and/or preserved by the LCSSA pass itself. So, assuming a single PHI node per exit block is not safe. llvm-svn: 275217
2016-07-13 05:24:06 +08:00
; CHECK-LABEL: @multiphi
; CHECK-LABEL: scalar.ph:
; CHECK: %bc.resume.val = phi i32 [ %n.vec, %middle.block ], [ 0, %entry ]
; CHECK-LABEL: for.end:
; CHECK: %phi = phi i32 [ {{.*}}, %for.body ], [ %n.vec, %middle.block ]
; CHECK: %phi2 = phi i32 [ {{.*}}, %for.body ], [ %n.vec, %middle.block ]
; CHECK: store i32 %phi2, i32* %p
; CHECK: ret i32 %phi
define i32 @multiphi(i32 %k, i32* %p) {
entry:
br label %for.body
for.body:
%inc.phi = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%inc = add nsw i32 %inc.phi, 1
%cmp = icmp eq i32 %inc, %k
br i1 %cmp, label %for.end, label %for.body
for.end:
%phi = phi i32 [ %inc, %for.body ]
%phi2 = phi i32 [ %inc, %for.body ]
store i32 %phi2, i32* %p
ret i32 %phi
}