mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-19 11:02:59 +02:00
0d99339102
One of several parallel first steps to remove the target type of pointers, replacing them with a single opaque pointer type. This adds an explicit type parameter to the gep instruction so that when the first parameter becomes an opaque pointer type, the type to gep through is still available to the instructions. * This doesn't modify gep operators, only instructions (operators will be handled separately) * Textual IR changes only. Bitcode (including upgrade) and changing the in-memory representation will be in separate changes. * geps of vectors are transformed as: getelementptr <4 x float*> %x, ... ->getelementptr float, <4 x float*> %x, ... Then, once the opaque pointer type is introduced, this will ultimately look like: getelementptr float, <4 x ptr> %x with the unambiguous interpretation that it is a vector of pointers to float. * address spaces remain on the pointer, not the type: getelementptr float addrspace(1)* %x ->getelementptr float, float addrspace(1)* %x Then, eventually: getelementptr float, ptr addrspace(1) %x Importantly, the massive amount of test case churn has been automated by same crappy python code. I had to manually update a few test cases that wouldn't fit the script's model (r228970,r229196,r229197,r229198). The python script just massages stdin and writes the result to stdout, I then wrapped that in a shell script to handle replacing files, then using the usual find+xargs to migrate all the files. update.py: import fileinput import sys import re ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") def conv(match, line): if not match: return line line = match.groups()[0] if len(match.groups()[5]) == 0: line += match.groups()[2] line += match.groups()[3] line += ", " line += match.groups()[1] line += "\n" return line for line in sys.stdin: if line.find("getelementptr ") == line.find("getelementptr inbounds"): if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("): line = conv(re.match(ibrep, line), line) elif line.find("getelementptr ") != line.find("getelementptr ("): line = conv(re.match(normrep, line), line) sys.stdout.write(line) apply.sh: for name in "$@" do python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name" rm -f "$name.tmp" done The actual commands: From llvm/src: find test/ -name *.ll | xargs ./apply.sh From llvm/src/tools/clang: find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}" From llvm/src/tools/polly: find test/ -name *.ll | xargs ./apply.sh After that, check-all (with llvm, clang, clang-tools-extra, lld, compiler-rt, and polly all checked out). The extra 'rm' in the apply.sh script is due to a few files in clang's test suite using interesting unicode stuff that my python script was throwing exceptions on. None of those files needed to be migrated, so it seemed sufficient to ignore those cases. Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7636 llvm-svn: 230786
260 lines
8.6 KiB
LLVM
260 lines
8.6 KiB
LLVM
; RUN: opt < %s -loop-unroll -pragma-unroll-threshold=1024 -S | FileCheck %s
|
|
; RUN: opt < %s -loop-unroll -loop-unroll -pragma-unroll-threshold=1024 -S | FileCheck %s
|
|
;
|
|
; Run loop unrolling twice to verify that loop unrolling metadata is properly
|
|
; removed and further unrolling is disabled after the pass is run once.
|
|
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-linux-gnu"
|
|
|
|
; loop4 contains a small loop which should be completely unrolled by
|
|
; the default unrolling heuristics. It serves as a control for the
|
|
; unroll(disable) pragma test loop4_with_disable.
|
|
;
|
|
; CHECK-LABEL: @loop4(
|
|
; CHECK-NOT: br i1
|
|
define void @loop4(i32* nocapture %a) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
|
|
%0 = load i32* %arrayidx, align 4
|
|
%inc = add nsw i32 %0, 1
|
|
store i32 %inc, i32* %arrayidx, align 4
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp eq i64 %indvars.iv.next, 4
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
; #pragma clang loop unroll(disable)
|
|
;
|
|
; CHECK-LABEL: @loop4_with_disable(
|
|
; CHECK: store i32
|
|
; CHECK-NOT: store i32
|
|
; CHECK: br i1
|
|
define void @loop4_with_disable(i32* nocapture %a) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
|
|
%0 = load i32* %arrayidx, align 4
|
|
%inc = add nsw i32 %0, 1
|
|
store i32 %inc, i32* %arrayidx, align 4
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp eq i64 %indvars.iv.next, 4
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !1
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
!1 = !{!1, !2}
|
|
!2 = !{!"llvm.loop.unroll.disable"}
|
|
|
|
; loop64 has a high enough count that it should *not* be unrolled by
|
|
; the default unrolling heuristic. It serves as the control for the
|
|
; unroll(full) pragma test loop64_with_.* tests below.
|
|
;
|
|
; CHECK-LABEL: @loop64(
|
|
; CHECK: store i32
|
|
; CHECK-NOT: store i32
|
|
; CHECK: br i1
|
|
define void @loop64(i32* nocapture %a) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
|
|
%0 = load i32* %arrayidx, align 4
|
|
%inc = add nsw i32 %0, 1
|
|
store i32 %inc, i32* %arrayidx, align 4
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp eq i64 %indvars.iv.next, 64
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
; #pragma clang loop unroll(full)
|
|
; Loop should be fully unrolled.
|
|
;
|
|
; CHECK-LABEL: @loop64_with_enable(
|
|
; CHECK-NOT: br i1
|
|
define void @loop64_with_enable(i32* nocapture %a) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
|
|
%0 = load i32* %arrayidx, align 4
|
|
%inc = add nsw i32 %0, 1
|
|
store i32 %inc, i32* %arrayidx, align 4
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp eq i64 %indvars.iv.next, 64
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !3
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
!3 = !{!3, !4}
|
|
!4 = !{!"llvm.loop.unroll.full"}
|
|
|
|
; #pragma clang loop unroll_count(4)
|
|
; Loop should be unrolled 4 times.
|
|
;
|
|
; CHECK-LABEL: @loop64_with_count4(
|
|
; CHECK: store i32
|
|
; CHECK: store i32
|
|
; CHECK: store i32
|
|
; CHECK: store i32
|
|
; CHECK-NOT: store i32
|
|
; CHECK: br i1
|
|
define void @loop64_with_count4(i32* nocapture %a) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
|
|
%0 = load i32* %arrayidx, align 4
|
|
%inc = add nsw i32 %0, 1
|
|
store i32 %inc, i32* %arrayidx, align 4
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp eq i64 %indvars.iv.next, 64
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !5
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
!5 = !{!5, !6}
|
|
!6 = !{!"llvm.loop.unroll.count", i32 4}
|
|
|
|
; #pragma clang loop unroll(full)
|
|
; Full unrolling is requested, but loop has a dynamic trip count so
|
|
; no unrolling should occur.
|
|
;
|
|
; CHECK-LABEL: @dynamic_loop_with_enable(
|
|
; CHECK: store i32
|
|
; CHECK-NOT: store i32
|
|
; CHECK: br i1
|
|
define void @dynamic_loop_with_enable(i32* nocapture %a, i32 %b) {
|
|
entry:
|
|
%cmp3 = icmp sgt i32 %b, 0
|
|
br i1 %cmp3, label %for.body, label %for.end, !llvm.loop !8
|
|
|
|
for.body: ; preds = %entry, %for.body
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
|
|
%0 = load i32* %arrayidx, align 4
|
|
%inc = add nsw i32 %0, 1
|
|
store i32 %inc, i32* %arrayidx, align 4
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, %b
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !8
|
|
|
|
for.end: ; preds = %for.body, %entry
|
|
ret void
|
|
}
|
|
!8 = !{!8, !4}
|
|
|
|
; #pragma clang loop unroll_count(4)
|
|
; Loop has a dynamic trip count. Unrolling should occur, but no
|
|
; conditional branches can be removed.
|
|
;
|
|
; CHECK-LABEL: @dynamic_loop_with_count4(
|
|
; CHECK-NOT: store
|
|
; CHECK: br i1
|
|
; CHECK: store
|
|
; CHECK: br i1
|
|
; CHECK: store
|
|
; CHECK: br i1
|
|
; CHECK: store
|
|
; CHECK: br i1
|
|
; CHECK: store
|
|
; CHECK: br i1
|
|
; CHECK-NOT: br i1
|
|
define void @dynamic_loop_with_count4(i32* nocapture %a, i32 %b) {
|
|
entry:
|
|
%cmp3 = icmp sgt i32 %b, 0
|
|
br i1 %cmp3, label %for.body, label %for.end, !llvm.loop !9
|
|
|
|
for.body: ; preds = %entry, %for.body
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
|
|
%0 = load i32* %arrayidx, align 4
|
|
%inc = add nsw i32 %0, 1
|
|
store i32 %inc, i32* %arrayidx, align 4
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, %b
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !9
|
|
|
|
for.end: ; preds = %for.body, %entry
|
|
ret void
|
|
}
|
|
!9 = !{!9, !6}
|
|
|
|
; #pragma clang loop unroll_count(1)
|
|
; Loop should not be unrolled
|
|
;
|
|
; CHECK-LABEL: @unroll_1(
|
|
; CHECK: store i32
|
|
; CHECK-NOT: store i32
|
|
; CHECK: br i1
|
|
define void @unroll_1(i32* nocapture %a, i32 %b) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
|
|
%0 = load i32* %arrayidx, align 4
|
|
%inc = add nsw i32 %0, 1
|
|
store i32 %inc, i32* %arrayidx, align 4
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp eq i64 %indvars.iv.next, 4
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !10
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
!10 = !{!10, !11}
|
|
!11 = !{!"llvm.loop.unroll.count", i32 1}
|
|
|
|
; #pragma clang loop unroll(full)
|
|
; Loop has very high loop count (1 million) and full unrolling was requested.
|
|
; Loop should unrolled up to the pragma threshold, but not completely.
|
|
;
|
|
; CHECK-LABEL: @unroll_1M(
|
|
; CHECK: store i32
|
|
; CHECK: store i32
|
|
; CHECK: br i1
|
|
define void @unroll_1M(i32* nocapture %a, i32 %b) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
|
|
%0 = load i32* %arrayidx, align 4
|
|
%inc = add nsw i32 %0, 1
|
|
store i32 %inc, i32* %arrayidx, align 4
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp eq i64 %indvars.iv.next, 1000000
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !12
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
!12 = !{!12, !4}
|