maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/SystemZ/memcpy-01.ll

236 lines
7.5 KiB
LLVM
Raw Normal View History

[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
; Test memcpy using MVC.
;
; RUN: llc < %s -mtriple=s390x-linux-gnu | FileCheck %s
declare void @llvm.memcpy.p0i8.p0i8.i32(i8 *nocapture, i8 *nocapture, i32, i32, i1) nounwind
declare void @llvm.memcpy.p0i8.p0i8.i64(i8 *nocapture, i8 *nocapture, i64, i32, i1) nounwind
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
declare void @foo(i8 *, i8 *)
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
; Test a no-op move, i32 version.
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
define void @f1(i8 *%dest, i8 *%src) {
Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change and all updated tests passed locally. This update was done with the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc.*debug" $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 sed -i '' "s/;\(.*\)-LABEL-LABEL:/;\1-LABEL:/" $TEMP sed -i '' "s/;\(.*\)-NEXT-LABEL:/;\1-NEXT:/" $TEMP sed -i '' "s/;\(.*\)-NOT-LABEL:/;\1-NOT:/" $TEMP sed -i '' "s/;\(.*\)-DAG-LABEL:/;\1-DAG:/" $TEMP mv $TEMP $NAME fi done llvm-svn: 186280
2013-07-14 14:24:09 +08:00
; CHECK-LABEL: f1:
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
; CHECK-NOT: %r2
; CHECK-NOT: %r3
; CHECK: br %r14
call void @llvm.memcpy.p0i8.p0i8.i32(i8 *%dest, i8 *%src, i32 0, i32 1,
i1 false)
ret void
}
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
; Test a no-op move, i64 version.
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
define void @f2(i8 *%dest, i8 *%src) {
Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change and all updated tests passed locally. This update was done with the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc.*debug" $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 sed -i '' "s/;\(.*\)-LABEL-LABEL:/;\1-LABEL:/" $TEMP sed -i '' "s/;\(.*\)-NEXT-LABEL:/;\1-NEXT:/" $TEMP sed -i '' "s/;\(.*\)-NOT-LABEL:/;\1-NOT:/" $TEMP sed -i '' "s/;\(.*\)-DAG-LABEL:/;\1-DAG:/" $TEMP mv $TEMP $NAME fi done llvm-svn: 186280
2013-07-14 14:24:09 +08:00
; CHECK-LABEL: f2:
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
; CHECK-NOT: %r2
; CHECK-NOT: %r3
; CHECK: br %r14
call void @llvm.memcpy.p0i8.p0i8.i64(i8 *%dest, i8 *%src, i64 0, i32 1,
i1 false)
ret void
}
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
; Test a 1-byte move, i32 version.
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
define void @f3(i8 *%dest, i8 *%src) {
Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change and all updated tests passed locally. This update was done with the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc.*debug" $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 sed -i '' "s/;\(.*\)-LABEL-LABEL:/;\1-LABEL:/" $TEMP sed -i '' "s/;\(.*\)-NEXT-LABEL:/;\1-NEXT:/" $TEMP sed -i '' "s/;\(.*\)-NOT-LABEL:/;\1-NOT:/" $TEMP sed -i '' "s/;\(.*\)-DAG-LABEL:/;\1-DAG:/" $TEMP mv $TEMP $NAME fi done llvm-svn: 186280
2013-07-14 14:24:09 +08:00
; CHECK-LABEL: f3:
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
; CHECK: mvc 0(1,%r2), 0(%r3)
; CHECK: br %r14
call void @llvm.memcpy.p0i8.p0i8.i32(i8 *%dest, i8 *%src, i32 1, i32 1,
i1 false)
ret void
}
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
; Test a 1-byte move, i64 version.
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
define void @f4(i8 *%dest, i8 *%src) {
Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change and all updated tests passed locally. This update was done with the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc.*debug" $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 sed -i '' "s/;\(.*\)-LABEL-LABEL:/;\1-LABEL:/" $TEMP sed -i '' "s/;\(.*\)-NEXT-LABEL:/;\1-NEXT:/" $TEMP sed -i '' "s/;\(.*\)-NOT-LABEL:/;\1-NOT:/" $TEMP sed -i '' "s/;\(.*\)-DAG-LABEL:/;\1-DAG:/" $TEMP mv $TEMP $NAME fi done llvm-svn: 186280
2013-07-14 14:24:09 +08:00
; CHECK-LABEL: f4:
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
; CHECK: mvc 0(1,%r2), 0(%r3)
; CHECK: br %r14
call void @llvm.memcpy.p0i8.p0i8.i64(i8 *%dest, i8 *%src, i64 1, i32 1,
i1 false)
ret void
}
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
; Test the upper range of a single MVC, i32 version.
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
define void @f5(i8 *%dest, i8 *%src) {
Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change and all updated tests passed locally. This update was done with the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc.*debug" $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 sed -i '' "s/;\(.*\)-LABEL-LABEL:/;\1-LABEL:/" $TEMP sed -i '' "s/;\(.*\)-NEXT-LABEL:/;\1-NEXT:/" $TEMP sed -i '' "s/;\(.*\)-NOT-LABEL:/;\1-NOT:/" $TEMP sed -i '' "s/;\(.*\)-DAG-LABEL:/;\1-DAG:/" $TEMP mv $TEMP $NAME fi done llvm-svn: 186280
2013-07-14 14:24:09 +08:00
; CHECK-LABEL: f5:
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
; CHECK: mvc 0(256,%r2), 0(%r3)
; CHECK: br %r14
call void @llvm.memcpy.p0i8.p0i8.i32(i8 *%dest, i8 *%src, i32 256, i32 1,
i1 false)
ret void
}
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
; Test the upper range of a single MVC, i64 version.
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
define void @f6(i8 *%dest, i8 *%src) {
Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change and all updated tests passed locally. This update was done with the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc.*debug" $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 sed -i '' "s/;\(.*\)-LABEL-LABEL:/;\1-LABEL:/" $TEMP sed -i '' "s/;\(.*\)-NEXT-LABEL:/;\1-NEXT:/" $TEMP sed -i '' "s/;\(.*\)-NOT-LABEL:/;\1-NOT:/" $TEMP sed -i '' "s/;\(.*\)-DAG-LABEL:/;\1-DAG:/" $TEMP mv $TEMP $NAME fi done llvm-svn: 186280
2013-07-14 14:24:09 +08:00
; CHECK-LABEL: f6:
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
; CHECK: mvc 0(256,%r2), 0(%r3)
; CHECK: br %r14
call void @llvm.memcpy.p0i8.p0i8.i64(i8 *%dest, i8 *%src, i64 256, i32 1,
i1 false)
ret void
}
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
; Test the first case that needs two MVCs.
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
define void @f7(i8 *%dest, i8 *%src) {
Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change and all updated tests passed locally. This update was done with the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc.*debug" $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 sed -i '' "s/;\(.*\)-LABEL-LABEL:/;\1-LABEL:/" $TEMP sed -i '' "s/;\(.*\)-NEXT-LABEL:/;\1-NEXT:/" $TEMP sed -i '' "s/;\(.*\)-NOT-LABEL:/;\1-NOT:/" $TEMP sed -i '' "s/;\(.*\)-DAG-LABEL:/;\1-DAG:/" $TEMP mv $TEMP $NAME fi done llvm-svn: 186280
2013-07-14 14:24:09 +08:00
; CHECK-LABEL: f7:
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
; CHECK: mvc 0(256,%r2), 0(%r3)
; CHECK: mvc 256(1,%r2), 256(%r3)
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
; CHECK: br %r14
call void @llvm.memcpy.p0i8.p0i8.i32(i8 *%dest, i8 *%src, i32 257, i32 1,
i1 false)
ret void
}
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
; Test the last-but-one case that needs two MVCs.
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
define void @f8(i8 *%dest, i8 *%src) {
Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change and all updated tests passed locally. This update was done with the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc.*debug" $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 sed -i '' "s/;\(.*\)-LABEL-LABEL:/;\1-LABEL:/" $TEMP sed -i '' "s/;\(.*\)-NEXT-LABEL:/;\1-NEXT:/" $TEMP sed -i '' "s/;\(.*\)-NOT-LABEL:/;\1-NOT:/" $TEMP sed -i '' "s/;\(.*\)-DAG-LABEL:/;\1-DAG:/" $TEMP mv $TEMP $NAME fi done llvm-svn: 186280
2013-07-14 14:24:09 +08:00
; CHECK-LABEL: f8:
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
; CHECK: mvc 0(256,%r2), 0(%r3)
; CHECK: mvc 256(255,%r2), 256(%r3)
; CHECK: br %r14
call void @llvm.memcpy.p0i8.p0i8.i64(i8 *%dest, i8 *%src, i64 511, i32 1,
i1 false)
ret void
}
; Test the last case that needs two MVCs.
define void @f9(i8 *%dest, i8 *%src) {
; CHECK-LABEL: f9:
; CHECK: mvc 0(256,%r2), 0(%r3)
; CHECK: mvc 256(256,%r2), 256(%r3)
; CHECK: br %r14
call void @llvm.memcpy.p0i8.p0i8.i64(i8 *%dest, i8 *%src, i64 512, i32 1,
i1 false)
ret void
}
; Test an arbitrary value that uses straight-line code.
define void @f10(i8 *%dest, i8 *%src) {
; CHECK-LABEL: f10:
; CHECK: mvc 0(256,%r2), 0(%r3)
; CHECK: mvc 256(256,%r2), 256(%r3)
; CHECK: mvc 512(256,%r2), 512(%r3)
; CHECK: mvc 768(256,%r2), 768(%r3)
; CHECK: mvc 1024(255,%r2), 1024(%r3)
; CHECK: br %r14
call void @llvm.memcpy.p0i8.p0i8.i64(i8 *%dest, i8 *%src, i64 1279, i32 1,
i1 false)
ret void
}
; ...and again in cases where not all parts are in range of MVC.
define void @f11(i8 *%srcbase, i8 *%destbase) {
; CHECK-LABEL: f11:
; CHECK: mvc 4000(256,%r2), 3500(%r3)
; CHECK: lay [[NEWDEST:%r[1-5]]], 4256(%r2)
; CHECK: mvc 0(256,[[NEWDEST]]), 3756(%r3)
; CHECK: mvc 256(256,[[NEWDEST]]), 4012(%r3)
; CHECK: lay [[NEWSRC:%r[1-5]]], 4268(%r3)
; CHECK: mvc 512(256,[[NEWDEST]]), 0([[NEWSRC]])
; CHECK: mvc 768(255,[[NEWDEST]]), 256([[NEWSRC]])
; CHECK: br %r14
[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 llvm-svn: 230786
2015-02-28 03:29:02 +08:00
%dest = getelementptr i8, i8 *%srcbase, i64 4000
%src = getelementptr i8, i8* %destbase, i64 3500
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
call void @llvm.memcpy.p0i8.p0i8.i64(i8 *%dest, i8 *%src, i64 1279, i32 1,
i1 false)
ret void
}
; ...and again with a destination frame base that goes out of range.
define void @f12() {
; CHECK-LABEL: f12:
; CHECK: brasl %r14, foo@PLT
; CHECK: mvc 4076(256,%r15), 2100(%r15)
; CHECK: lay [[NEWDEST:%r[1-5]]], 4332(%r15)
; CHECK: mvc 0(256,[[NEWDEST]]), 2356(%r15)
; CHECK: mvc 256(256,[[NEWDEST]]), 2612(%r15)
; CHECK: mvc 512(256,[[NEWDEST]]), 2868(%r15)
; CHECK: mvc 768(255,[[NEWDEST]]), 3124(%r15)
; CHECK: brasl %r14, foo@PLT
; CHECK: br %r14
%arr = alloca [6000 x i8]
[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 llvm-svn: 230786
2015-02-28 03:29:02 +08:00
%dest = getelementptr [6000 x i8], [6000 x i8] *%arr, i64 0, i64 3900
%src = getelementptr [6000 x i8], [6000 x i8] *%arr, i64 0, i64 1924
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
call void @foo(i8 *%dest, i8 *%src)
call void @llvm.memcpy.p0i8.p0i8.i64(i8 *%dest, i8 *%src, i64 1279, i32 1,
i1 false)
call void @foo(i8 *%dest, i8 *%src)
ret void
}
; ...and again with a source frame base that goes out of range.
define void @f13() {
; CHECK-LABEL: f13:
; CHECK: brasl %r14, foo@PLT
; CHECK: mvc 200(256,%r15), 3826(%r15)
; CHECK: mvc 456(256,%r15), 4082(%r15)
; CHECK: lay [[NEWSRC:%r[1-5]]], 4338(%r15)
; CHECK: mvc 712(256,%r15), 0([[NEWSRC]])
; CHECK: mvc 968(256,%r15), 256([[NEWSRC]])
; CHECK: mvc 1224(255,%r15), 512([[NEWSRC]])
; CHECK: brasl %r14, foo@PLT
; CHECK: br %r14
%arr = alloca [6000 x i8]
[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 llvm-svn: 230786
2015-02-28 03:29:02 +08:00
%dest = getelementptr [6000 x i8], [6000 x i8] *%arr, i64 0, i64 24
%src = getelementptr [6000 x i8], [6000 x i8] *%arr, i64 0, i64 3650
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
call void @foo(i8 *%dest, i8 *%src)
call void @llvm.memcpy.p0i8.p0i8.i64(i8 *%dest, i8 *%src, i64 1279, i32 1,
i1 false)
call void @foo(i8 *%dest, i8 *%src)
ret void
}
; Test the last case that is done using straight-line code.
define void @f14(i8 *%dest, i8 *%src) {
; CHECK-LABEL: f14:
; CHECK: mvc 0(256,%r2), 0(%r3)
; CHECK: mvc 256(256,%r2), 256(%r3)
; CHECK: mvc 512(256,%r2), 512(%r3)
; CHECK: mvc 768(256,%r2), 768(%r3)
; CHECK: mvc 1024(256,%r2), 1024(%r3)
; CHECK: mvc 1280(256,%r2), 1280(%r3)
; CHECK: br %r14
call void @llvm.memcpy.p0i8.p0i8.i64(i8 *%dest, i8 *%src, i64 1536, i32 1,
i1 false)
ret void
}
; Test the first case that is done using a loop.
define void @f15(i8 *%dest, i8 *%src) {
; CHECK-LABEL: f15:
; CHECK: lghi [[COUNT:%r[0-5]]], 6
; CHECK: [[LABEL:\.L[^:]*]]:
; CHECK: pfd 2, 768(%r2)
; CHECK: mvc 0(256,%r2), 0(%r3)
; CHECK: la %r2, 256(%r2)
; CHECK: la %r3, 256(%r3)
; CHECK: brctg [[COUNT]], [[LABEL]]
; CHECK: mvc 0(1,%r2), 0(%r3)
; CHECK: br %r14
call void @llvm.memcpy.p0i8.p0i8.i64(i8 *%dest, i8 *%src, i64 1537, i32 1,
i1 false)
ret void
}
; ...and again with frame bases, where the base must be loaded into a
; register before the loop.
define void @f16() {
; CHECK-LABEL: f16:
; CHECK: brasl %r14, foo@PLT
; CHECK-DAG: lghi [[COUNT:%r[0-5]]], 6
; CHECK-DAG: la [[BASE:%r[0-5]]], 160(%r15)
; CHECK: [[LABEL:\.L[^:]*]]:
; CHECK: pfd 2, 2368([[BASE]])
; CHECK: mvc 1600(256,[[BASE]]), 0([[BASE]])
; CHECK: la [[BASE]], 256([[BASE]])
; CHECK: brctg [[COUNT]], [[LABEL]]
; CHECK: mvc 1600(1,[[BASE]]), 0([[BASE]])
; CHECK: brasl %r14, foo@PLT
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
; CHECK: br %r14
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
%arr = alloca [3200 x i8]
[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 llvm-svn: 230786
2015-02-28 03:29:02 +08:00
%dest = getelementptr [3200 x i8], [3200 x i8] *%arr, i64 0, i64 1600
%src = getelementptr [3200 x i8], [3200 x i8] *%arr, i64 0, i64 0
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
call void @foo(i8 *%dest, i8 *%src)
call void @llvm.memcpy.p0i8.p0i8.i64(i8 *%dest, i8 *%src, i64 1537, i32 1,
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
i1 false)
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
call void @foo(i8 *%dest, i8 *%src)
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
ret void
}