llvm-6502/test/CodeGen/X86/misched-fusion.ll
David Blaikie 198d8baafb [opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
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

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230786 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-27 19:29:02 +00:00

109 lines
3.1 KiB
LLVM

; RUN: llc < %s -march=x86-64 -mcpu=corei7-avx -disable-lsr -pre-RA-sched=source -enable-misched -verify-machineinstrs | FileCheck %s
; Verify that TEST+JE are scheduled together.
; CHECK: test_je
; CHECK: %loop
; CHECK: test
; CHECK-NEXT: je
define void @test_je() {
entry:
br label %loop
loop:
%var = phi i32* [ null, %entry ], [ %next.load, %loop1 ], [ %var, %loop2 ]
%next.ptr = phi i32** [ null, %entry ], [ %next.ptr, %loop1 ], [ %gep, %loop2 ]
br label %loop1
loop1:
%cond = icmp eq i32* %var, null
%next.load = load i32** %next.ptr
br i1 %cond, label %loop, label %loop2
loop2: ; preds = %loop1
%gep = getelementptr inbounds i32*, i32** %next.ptr, i32 1
store i32* %next.load, i32** undef
br label %loop
}
; Verify that DEC+JE are scheduled together.
; CHECK: dec_je
; CHECK: %loop1
; CHECK: dec
; CHECK-NEXT: je
define void @dec_je() {
entry:
br label %loop
loop:
%var = phi i32 [ 0, %entry ], [ %next.var, %loop1 ], [ %var2, %loop2 ]
%next.ptr = phi i32** [ null, %entry ], [ %next.ptr, %loop1 ], [ %gep, %loop2 ]
br label %loop1
loop1:
%var2 = sub i32 %var, 1
%cond = icmp eq i32 %var2, 0
%next.load = load i32** %next.ptr
%next.var = load i32* %next.load
br i1 %cond, label %loop, label %loop2
loop2:
%gep = getelementptr inbounds i32*, i32** %next.ptr, i32 1
store i32* %next.load, i32** undef
br label %loop
}
; DEC+JS should *not* be scheduled together.
; CHECK: dec_js
; CHECK: %loop1
; CHECK: dec
; CHECK: mov
; CHECK: js
define void @dec_js() {
entry:
br label %loop2a
loop2a: ; preds = %loop1, %body, %entry
%var = phi i32 [ 0, %entry ], [ %next.var, %loop1 ], [ %var2, %loop2b ]
%next.ptr = phi i32** [ null, %entry ], [ %next.ptr, %loop1 ], [ %gep, %loop2b ]
br label %loop1
loop1: ; preds = %loop2a, %loop2b
%var2 = sub i32 %var, 1
%cond = icmp slt i32 %var2, 0
%next.load = load i32** %next.ptr
%next.var = load i32* %next.load
br i1 %cond, label %loop2a, label %loop2b
loop2b: ; preds = %loop1
%gep = getelementptr inbounds i32*, i32** %next.ptr, i32 1
store i32* %next.load, i32** undef
br label %loop2a
}
; Verify that CMP+JB are scheduled together.
; CHECK: cmp_jb
; CHECK: %loop1
; CHECK: cmp
; CHECK-NEXT: jb
define void @cmp_jb(i32 %n) {
entry:
br label %loop2a
loop2a: ; preds = %loop1, %body, %entry
%var = phi i32 [ 0, %entry ], [ %next.var, %loop1 ], [ %var2, %loop2b ]
%next.ptr = phi i32** [ null, %entry ], [ %next.ptr, %loop1 ], [ %gep, %loop2b ]
br label %loop1
loop1: ; preds = %loop2a, %loop2b
%var2 = sub i32 %var, 1
%cond = icmp ult i32 %var2, %n
%next.load = load i32** %next.ptr
%next.var = load i32* %next.load
br i1 %cond, label %loop2a, label %loop2b
loop2b: ; preds = %loop1
%gep = getelementptr inbounds i32*, i32** %next.ptr, i32 1
store i32* %next.load, i32** undef
br label %loop2a
}