6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-02-08 06:32:24 +00:00
Code Issues Projects Releases Wiki Activity
llvm-6502/test/Transforms/LoopVectorize/X86/small-size.ll

196 lines
7.3 KiB
LLVM
Raw Normal View History

Rename getMaximumUnrollFactor -> getMaxInterleaveFactor; also rename option names controlling this variable. "Unroll" is not the appropriate name for this variable. Clang already uses the term "interleave" in pragmas and metadata for this. Differential Revision: http://reviews.llvm.org/D5066 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217528 91177308-0d34-0410-b5e6-96231b3b80d8
2014-09-10 17:58:16 +00:00
; RUN: opt < %s -basicaa -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -loop-vectorize-with-block-frequency -dce -instcombine -S | FileCheck %s
LoopVectorizer: Use the "optsize" attribute to decide if we are allowed to increase the function size. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170004 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-12 19:29:45 +00:00
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-S128"
target triple = "x86_64-apple-macosx10.8.0"
@b = common global [2048 x i32] zeroinitializer, align 16
@c = common global [2048 x i32] zeroinitializer, align 16
@a = common global [2048 x i32] zeroinitializer, align 16
@G = common global [32 x [1024 x i32]] zeroinitializer, align 16
@ub = common global [1024 x i32] zeroinitializer, align 16
@uc = common global [1024 x i32] zeroinitializer, align 16
@d = common global [2048 x i32] zeroinitializer, align 16
@fa = common global [1024 x float] zeroinitializer, align 16
@fb = common global [1024 x float] zeroinitializer, align 16
@ic = common global [1024 x i32] zeroinitializer, align 16
@da = common global [1024 x float] zeroinitializer, align 16
@db = common global [1024 x float] zeroinitializer, align 16
@dc = common global [1024 x float] zeroinitializer, align 16
@dd = common global [1024 x float] zeroinitializer, align 16
@dj = common global [1024 x i32] zeroinitializer, align 16
; We can optimize this test without a tail.
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186268 91177308-0d34-0410-b5e6-96231b3b80d8
2013-07-14 01:42:54 +00:00
;CHECK-LABEL: @example1(
LoopVectorizer: Use the "optsize" attribute to decide if we are allowed to increase the function size. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170004 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-12 19:29:45 +00:00
;CHECK: load <4 x i32>
;CHECK: add nsw <4 x i32>
;CHECK: store <4 x i32>
;CHECK: ret void
define void @example1() optsize {
br label %1
; <label>:1 ; preds = %1, %0
%indvars.iv = phi i64 [ 0, %0 ], [ %indvars.iv.next, %1 ]
%2 = getelementptr inbounds [2048 x i32]* @b, i64 0, i64 %indvars.iv
%3 = load i32* %2, align 4
%4 = getelementptr inbounds [2048 x i32]* @c, i64 0, i64 %indvars.iv
%5 = load i32* %4, align 4
%6 = add nsw i32 %5, %3
%7 = getelementptr inbounds [2048 x i32]* @a, i64 0, i64 %indvars.iv
store i32 %6, i32* %7, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, 256
br i1 %exitcond, label %8, label %1
; <label>:8 ; preds = %1
ret void
}
; Can't vectorize in 'optsize' mode because we need a tail.
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186268 91177308-0d34-0410-b5e6-96231b3b80d8
2013-07-14 01:42:54 +00:00
;CHECK-LABEL: @example2(
LoopVectorizer: Use the "optsize" attribute to decide if we are allowed to increase the function size. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170004 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-12 19:29:45 +00:00
;CHECK-NOT: store <4 x i32>
;CHECK: ret void
define void @example2(i32 %n, i32 %x) optsize {
%1 = icmp sgt i32 %n, 0
br i1 %1, label %.lr.ph5, label %.preheader
..preheader_crit_edge: ; preds = %.lr.ph5
%phitmp = sext i32 %n to i64
br label %.preheader
.preheader: ; preds = %..preheader_crit_edge, %0
%i.0.lcssa = phi i64 [ %phitmp, %..preheader_crit_edge ], [ 0, %0 ]
%2 = icmp eq i32 %n, 0
br i1 %2, label %._crit_edge, label %.lr.ph
.lr.ph5: ; preds = %0, %.lr.ph5
%indvars.iv6 = phi i64 [ %indvars.iv.next7, %.lr.ph5 ], [ 0, %0 ]
%3 = getelementptr inbounds [2048 x i32]* @b, i64 0, i64 %indvars.iv6
store i32 %x, i32* %3, align 4
%indvars.iv.next7 = add i64 %indvars.iv6, 1
%lftr.wideiv = trunc i64 %indvars.iv.next7 to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %..preheader_crit_edge, label %.lr.ph5
.lr.ph: ; preds = %.preheader, %.lr.ph
%indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ %i.0.lcssa, %.preheader ]
%.02 = phi i32 [ %4, %.lr.ph ], [ %n, %.preheader ]
%4 = add nsw i32 %.02, -1
%5 = getelementptr inbounds [2048 x i32]* @b, i64 0, i64 %indvars.iv
%6 = load i32* %5, align 4
%7 = getelementptr inbounds [2048 x i32]* @c, i64 0, i64 %indvars.iv
%8 = load i32* %7, align 4
%9 = and i32 %8, %6
%10 = getelementptr inbounds [2048 x i32]* @a, i64 0, i64 %indvars.iv
store i32 %9, i32* %10, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%11 = icmp eq i32 %4, 0
br i1 %11, label %._crit_edge, label %.lr.ph
._crit_edge: ; preds = %.lr.ph, %.preheader
ret void
}
; N is unknown, we need a tail. Can't vectorize.
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186268 91177308-0d34-0410-b5e6-96231b3b80d8
2013-07-14 01:42:54 +00:00
;CHECK-LABEL: @example3(
LoopVectorizer: Use the "optsize" attribute to decide if we are allowed to increase the function size. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170004 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-12 19:29:45 +00:00
;CHECK-NOT: <4 x i32>
;CHECK: ret void
define void @example3(i32 %n, i32* noalias nocapture %p, i32* noalias nocapture %q) optsize {
%1 = icmp eq i32 %n, 0
br i1 %1, label %._crit_edge, label %.lr.ph
.lr.ph: ; preds = %0, %.lr.ph
%.05 = phi i32 [ %2, %.lr.ph ], [ %n, %0 ]
%.014 = phi i32* [ %5, %.lr.ph ], [ %p, %0 ]
%.023 = phi i32* [ %3, %.lr.ph ], [ %q, %0 ]
%2 = add nsw i32 %.05, -1
%3 = getelementptr inbounds i32* %.023, i64 1
%4 = load i32* %.023, align 16
%5 = getelementptr inbounds i32* %.014, i64 1
store i32 %4, i32* %.014, align 16
%6 = icmp eq i32 %2, 0
br i1 %6, label %._crit_edge, label %.lr.ph
._crit_edge: ; preds = %.lr.ph, %0
ret void
}
[vectorize] Initial version of respecting PGO in the vectorizer: treat cold loops as-if they were being optimized for size. Nothing fancy here. Simply test case included. The nice thing is that we can now incrementally build on top of this to drive other heuristics. All of the infrastructure work is done to get the profile information into this layer. The remaining work necessary to make this a fully general purpose loop unroller for very hot loops is to make it a fully general purpose loop unroller. Things I know of but am not going to have time to benchmark and fix in the immediate future: 1) Don't disable the entire pass when the target is lacking vector registers. This really doesn't make any sense any more. 2) Teach the unroller at least and the vectorizer potentially to handle non-if-converted loops. This is trivial for the unroller but hard for the vectorizer. 3) Compute the relative hotness of the loop and thread that down to the various places that make cost tradeoffs (very likely only the unroller makes sense here, and then only when dealing with loops that are small enough for unrolling to not completely blow out the LSD). I'm still dubious how useful hotness information will be. So far, my experiments show that if we can get the correct logic for determining when unrolling actually helps performance, the code size impact is completely unimportant and we can unroll in all cases. But at least we'll no longer burn code size on cold code. One somewhat unrelated idea that I've had forever but not had time to implement: mark all functions which are only reachable via the global constructors rigging in the module as optsize. This would also decrease the impact of any more aggressive heuristics here on code size. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200219 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-27 13:11:50 +00:00
; N is unknown, we need a tail. Can't vectorize because the loop is cold.
;CHECK-LABEL: @example4(
;CHECK-NOT: <4 x i32>
;CHECK: ret void
define void @example4(i32 %n, i32* noalias nocapture %p, i32* noalias nocapture %q) {
%1 = icmp eq i32 %n, 0
br i1 %1, label %._crit_edge, label %.lr.ph, !prof !0
.lr.ph: ; preds = %0, %.lr.ph
%.05 = phi i32 [ %2, %.lr.ph ], [ %n, %0 ]
%.014 = phi i32* [ %5, %.lr.ph ], [ %p, %0 ]
%.023 = phi i32* [ %3, %.lr.ph ], [ %q, %0 ]
%2 = add nsw i32 %.05, -1
%3 = getelementptr inbounds i32* %.023, i64 1
%4 = load i32* %.023, align 16
%5 = getelementptr inbounds i32* %.014, i64 1
store i32 %4, i32* %.014, align 16
%6 = icmp eq i32 %2, 0
br i1 %6, label %._crit_edge, label %.lr.ph
._crit_edge: ; preds = %.lr.ph, %0
ret void
}
IR: Make metadata typeless in assembly Now that `Metadata` is typeless, reflect that in the assembly. These are the matching assembly changes for the metadata/value split in r223802. - Only use the `metadata` type when referencing metadata from a call intrinsic -- i.e., only when it's used as a `Value`. - Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode` when referencing it from call intrinsics. So, assembly like this: define @foo(i32 %v) { call void @llvm.foo(metadata !{i32 %v}, metadata !0) call void @llvm.foo(metadata !{i32 7}, metadata !0) call void @llvm.foo(metadata !1, metadata !0) call void @llvm.foo(metadata !3, metadata !0) call void @llvm.foo(metadata !{metadata !3}, metadata !0) ret void, !bar !2 } !0 = metadata !{metadata !2} !1 = metadata !{i32* @global} !2 = metadata !{metadata !3} !3 = metadata !{} turns into this: define @foo(i32 %v) { call void @llvm.foo(metadata i32 %v, metadata !0) call void @llvm.foo(metadata i32 7, metadata !0) call void @llvm.foo(metadata i32* @global, metadata !0) call void @llvm.foo(metadata !3, metadata !0) call void @llvm.foo(metadata !{!3}, metadata !0) ret void, !bar !2 } !0 = !{!2} !1 = !{i32* @global} !2 = !{!3} !3 = !{} I wrote an upgrade script that handled almost all of the tests in llvm and many of the tests in cfe (even handling many `CHECK` lines). I've attached it (or will attach it in a moment if you're speedy) to PR21532 to help everyone update their out-of-tree testcases. This is part of PR21532. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@224257 91177308-0d34-0410-b5e6-96231b3b80d8
2014-12-15 19:07:53 +00:00
!0 = !{!"branch_weights", i32 64, i32 4}
LoopVectorizer: Use the "optsize" attribute to decide if we are allowed to increase the function size. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170004 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-12 19:29:45 +00:00
; We can't vectorize this one because we need a runtime ptr check.
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186268 91177308-0d34-0410-b5e6-96231b3b80d8
2013-07-14 01:42:54 +00:00
;CHECK-LABEL: @example23(
LoopVectorizer: Use the "optsize" attribute to decide if we are allowed to increase the function size. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170004 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-12 19:29:45 +00:00
;CHECK-NOT: <4 x i32>
;CHECK: ret void
define void @example23(i16* nocapture %src, i32* nocapture %dst) optsize {
br label %1
; <label>:1 ; preds = %1, %0
%.04 = phi i16* [ %src, %0 ], [ %2, %1 ]
%.013 = phi i32* [ %dst, %0 ], [ %6, %1 ]
%i.02 = phi i32 [ 0, %0 ], [ %7, %1 ]
%2 = getelementptr inbounds i16* %.04, i64 1
%3 = load i16* %.04, align 2
%4 = zext i16 %3 to i32
%5 = shl nuw nsw i32 %4, 7
%6 = getelementptr inbounds i32* %.013, i64 1
store i32 %5, i32* %.013, align 4
%7 = add nsw i32 %i.02, 1
%exitcond = icmp eq i32 %7, 256
br i1 %exitcond, label %8, label %1
; <label>:8 ; preds = %1
ret void
}
; We CAN vectorize this example because the pointers are marked as noalias.
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186268 91177308-0d34-0410-b5e6-96231b3b80d8
2013-07-14 01:42:54 +00:00
;CHECK-LABEL: @example23b(
LoopVectorizer: Use the "optsize" attribute to decide if we are allowed to increase the function size. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170004 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-12 19:29:45 +00:00
;CHECK: <4 x i32>
;CHECK: ret void
define void @example23b(i16* noalias nocapture %src, i32* noalias nocapture %dst) optsize {
br label %1
; <label>:1 ; preds = %1, %0
%.04 = phi i16* [ %src, %0 ], [ %2, %1 ]
%.013 = phi i32* [ %dst, %0 ], [ %6, %1 ]
%i.02 = phi i32 [ 0, %0 ], [ %7, %1 ]
%2 = getelementptr inbounds i16* %.04, i64 1
%3 = load i16* %.04, align 2
%4 = zext i16 %3 to i32
%5 = shl nuw nsw i32 %4, 7
%6 = getelementptr inbounds i32* %.013, i64 1
store i32 %5, i32* %.013, align 4
%7 = add nsw i32 %i.02, 1
%exitcond = icmp eq i32 %7, 256
br i1 %exitcond, label %8, label %1
; <label>:8 ; preds = %1
ret void
}
Reference in New Issue Copy Permalink