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/frame-07.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

250 lines
9.3 KiB
LLVM
Raw Normal View History

[SystemZ] Add CodeGen test cases This adds all CodeGen tests for the SystemZ target. This version of the patch incorporates feedback from a review by Sean Silva. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181204
2013-05-07 00:17:29 +08:00
; Test the saving and restoring of FPRs in large frames.
;
[SystemZ] Add CodeGen support for scalar f64 ops in vector registers The z13 vector facility includes some instructions that operate only on the high f64 in a v2f64, effectively extending the FP register set from 16 to 32 registers. It's still better to use the old instructions if the operands happen to fit though, since the older instructions have a shorter encoding. Based on a patch by Richard Sandiford. llvm-svn: 236524
2015-05-06 03:28:34 +08:00
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z10 | FileCheck -check-prefix=CHECK-NOFP %s
Replace "no-frame-pointer-*" function attributes with "frame-pointer" Part of the effort to refactoring frame pointer code generation. We used to use two function attributes "no-frame-pointer-elim" and "no-frame-pointer-elim-non-leaf" to represent three kinds of frame pointer usage: (all) frames use frame pointer, (non-leaf) frames use frame pointer, (none) frame use frame pointer. This CL makes the idea explicit by using only one enum function attribute "frame-pointer" Option "-frame-pointer=" replaces "-disable-fp-elim" for tools such as llc. "no-frame-pointer-elim" and "no-frame-pointer-elim-non-leaf" are still supported for easy migration to "frame-pointer". tests are mostly updated with // replace command line args ‘-disable-fp-elim=false’ with ‘-frame-pointer=none’ grep -iIrnl '\-disable-fp-elim=false' * | xargs sed -i '' -e "s/-disable-fp-elim=false/-frame-pointer=none/g" // replace command line args ‘-disable-fp-elim’ with ‘-frame-pointer=all’ grep -iIrnl '\-disable-fp-elim' * | xargs sed -i '' -e "s/-disable-fp-elim/-frame-pointer=all/g" Patch by Yuanfang Chen (tabloid.adroit)! Differential Revision: https://reviews.llvm.org/D56351 llvm-svn: 351049
2019-01-14 18:55:55 +08:00
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z10 -frame-pointer=all | FileCheck -check-prefix=CHECK-FP %s
[SystemZ] Add CodeGen test cases This adds all CodeGen tests for the SystemZ target. This version of the patch incorporates feedback from a review by Sean Silva. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181204
2013-05-07 00:17:29 +08:00
; Test a frame size that requires some FPRs to be saved and loaded using
; the 20-bit STDY and LDY while others can use the 12-bit STD and LD.
[SystemZ] Allocate a second register scavenging slot This is another prerequisite for frame-to-frame MVC copies. I'll commit the patch that makes use of the slot separately. The downside of trying to test many corner cases with each of the available addressing modes is that a fair few tests need to account for the new frame layout. I do still think it's useful to have all these tests though, since it's something that wouldn't get much coverage otherwise. llvm-svn: 185698
2013-07-05 21:11:52 +08:00
; The frame is big enough to require two emergency spill slots at 160(%r15),
[SystemZ] Add CodeGen test cases This adds all CodeGen tests for the SystemZ target. This version of the patch incorporates feedback from a review by Sean Silva. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181204
2013-05-07 00:17:29 +08:00
; as well as the 8 FPR save slots. Get a frame of size 4128 by allocating
[SystemZ] Allocate a second register scavenging slot This is another prerequisite for frame-to-frame MVC copies. I'll commit the patch that makes use of the slot separately. The downside of trying to test many corner cases with each of the available addressing modes is that a fair few tests need to account for the new frame layout. I do still think it's useful to have all these tests though, since it's something that wouldn't get much coverage otherwise. llvm-svn: 185698
2013-07-05 21:11:52 +08:00
; (4128 - 176 - 8 * 8) / 8 = 486 extra doublewords.
[SystemZ] Add CodeGen test cases This adds all CodeGen tests for the SystemZ target. This version of the patch incorporates feedback from a review by Sean Silva. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181204
2013-05-07 00:17:29 +08:00
define void @f1(double *%ptr, i64 %x) {
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 $NAME fi done llvm-svn: 186280
2013-07-14 14:24:09 +08:00
; CHECK-NOFP-LABEL: f1:
[SystemZ] Add CodeGen test cases This adds all CodeGen tests for the SystemZ target. This version of the patch incorporates feedback from a review by Sean Silva. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181204
2013-05-07 00:17:29 +08:00
; CHECK-NOFP: aghi %r15, -4128
; CHECK-NOFP: .cfi_def_cfa_offset 4288
; CHECK-NOFP: stdy %f8, 4120(%r15)
; CHECK-NOFP: stdy %f9, 4112(%r15)
; CHECK-NOFP: stdy %f10, 4104(%r15)
; CHECK-NOFP: stdy %f11, 4096(%r15)
; CHECK-NOFP: std %f12, 4088(%r15)
; CHECK-NOFP: std %f13, 4080(%r15)
; CHECK-NOFP: std %f14, 4072(%r15)
; CHECK-NOFP: std %f15, 4064(%r15)
; CHECK-NOFP: .cfi_offset %f8, -168
; CHECK-NOFP: .cfi_offset %f9, -176
; CHECK-NOFP: .cfi_offset %f10, -184
; CHECK-NOFP: .cfi_offset %f11, -192
; CHECK-NOFP: .cfi_offset %f12, -200
; CHECK-NOFP: .cfi_offset %f13, -208
; CHECK-NOFP: .cfi_offset %f14, -216
; CHECK-NOFP: .cfi_offset %f15, -224
; ...main function body...
; CHECK-NOFP: ldy %f8, 4120(%r15)
; CHECK-NOFP: ldy %f9, 4112(%r15)
; CHECK-NOFP: ldy %f10, 4104(%r15)
; CHECK-NOFP: ldy %f11, 4096(%r15)
; CHECK-NOFP: ld %f12, 4088(%r15)
; CHECK-NOFP: ld %f13, 4080(%r15)
; CHECK-NOFP: ld %f14, 4072(%r15)
; CHECK-NOFP: ld %f15, 4064(%r15)
; CHECK-NOFP: aghi %r15, 4128
; CHECK-NOFP: br %r14
;
Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change and all updated tests passed locally. This update was done with the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$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-FP-LABEL: f1:
[SystemZ] Add CodeGen test cases This adds all CodeGen tests for the SystemZ target. This version of the patch incorporates feedback from a review by Sean Silva. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181204
2013-05-07 00:17:29 +08:00
; CHECK-FP: stmg %r11, %r15, 88(%r15)
; CHECK-FP: aghi %r15, -4128
; CHECK-FP: .cfi_def_cfa_offset 4288
; CHECK-FP: lgr %r11, %r15
; CHECK-FP: .cfi_def_cfa_register %r11
; CHECK-FP: stdy %f8, 4120(%r11)
; CHECK-FP: stdy %f9, 4112(%r11)
; CHECK-FP: stdy %f10, 4104(%r11)
; CHECK-FP: stdy %f11, 4096(%r11)
; CHECK-FP: std %f12, 4088(%r11)
; CHECK-FP: std %f13, 4080(%r11)
; CHECK-FP: std %f14, 4072(%r11)
; CHECK-FP: std %f15, 4064(%r11)
; ...main function body...
; CHECK-FP: ldy %f8, 4120(%r11)
; CHECK-FP: ldy %f9, 4112(%r11)
; CHECK-FP: ldy %f10, 4104(%r11)
; CHECK-FP: ldy %f11, 4096(%r11)
; CHECK-FP: ld %f12, 4088(%r11)
; CHECK-FP: ld %f13, 4080(%r11)
; CHECK-FP: ld %f14, 4072(%r11)
; CHECK-FP: ld %f15, 4064(%r11)
; CHECK-FP: lmg %r11, %r15, 4216(%r11)
; CHECK-FP: br %r14
[SystemZ] Allocate a second register scavenging slot This is another prerequisite for frame-to-frame MVC copies. I'll commit the patch that makes use of the slot separately. The downside of trying to test many corner cases with each of the available addressing modes is that a fair few tests need to account for the new frame layout. I do still think it's useful to have all these tests though, since it's something that wouldn't get much coverage otherwise. llvm-svn: 185698
2013-07-05 21:11:52 +08:00
%y = alloca [486 x i64], align 8
[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
%elem = getelementptr inbounds [486 x i64], [486 x i64]* %y, i64 0, i64 0
[SystemZ] Add CodeGen test cases This adds all CodeGen tests for the SystemZ target. This version of the patch incorporates feedback from a review by Sean Silva. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181204
2013-05-07 00:17:29 +08:00
store volatile i64 %x, i64* %elem
[SystemZ] Test case formatting fixes Fix systematically wrong whitespace from a prior automated change. NFC. llvm-svn: 337542
2018-07-20 20:12:10 +08:00
%l0 = load volatile double, double *%ptr
%l1 = load volatile double, double *%ptr
%l2 = load volatile double, double *%ptr
%l3 = load volatile double, double *%ptr
%l4 = load volatile double, double *%ptr
%l5 = load volatile double, double *%ptr
%l6 = load volatile double, double *%ptr
%l7 = load volatile double, double *%ptr
%l8 = load volatile double, double *%ptr
%l9 = load volatile double, double *%ptr
%l10 = load volatile double, double *%ptr
%l11 = load volatile double, double *%ptr
%l12 = load volatile double, double *%ptr
%l13 = load volatile double, double *%ptr
%l14 = load volatile double, double *%ptr
%l15 = load volatile double, double *%ptr
[SystemZ] Add CodeGen test cases This adds all CodeGen tests for the SystemZ target. This version of the patch incorporates feedback from a review by Sean Silva. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181204
2013-05-07 00:17:29 +08:00
%add0 = fadd double %l0, %l0
%add1 = fadd double %l1, %add0
%add2 = fadd double %l2, %add1
%add3 = fadd double %l3, %add2
%add4 = fadd double %l4, %add3
%add5 = fadd double %l5, %add4
%add6 = fadd double %l6, %add5
%add7 = fadd double %l7, %add6
%add8 = fadd double %l8, %add7
%add9 = fadd double %l9, %add8
%add10 = fadd double %l10, %add9
%add11 = fadd double %l11, %add10
%add12 = fadd double %l12, %add11
%add13 = fadd double %l13, %add12
%add14 = fadd double %l14, %add13
%add15 = fadd double %l15, %add14
store volatile double %add0, double *%ptr
store volatile double %add1, double *%ptr
store volatile double %add2, double *%ptr
store volatile double %add3, double *%ptr
store volatile double %add4, double *%ptr
store volatile double %add5, double *%ptr
store volatile double %add6, double *%ptr
store volatile double %add7, double *%ptr
store volatile double %add8, double *%ptr
store volatile double %add9, double *%ptr
store volatile double %add10, double *%ptr
store volatile double %add11, double *%ptr
store volatile double %add12, double *%ptr
store volatile double %add13, double *%ptr
store volatile double %add14, double *%ptr
store volatile double %add15, double *%ptr
ret void
}
; Test a frame size that requires some FPRs to be saved and loaded using
; an indexed STD and LD while others can use the 20-bit STDY and LDY.
; The index can be any call-clobbered GPR except %r0.
;
; Don't require the accesses to share the same LLILH; that would be a
; good optimisation but is really a different test.
;
; As above, get a frame of size 524320 by allocating
[SystemZ] Allocate a second register scavenging slot This is another prerequisite for frame-to-frame MVC copies. I'll commit the patch that makes use of the slot separately. The downside of trying to test many corner cases with each of the available addressing modes is that a fair few tests need to account for the new frame layout. I do still think it's useful to have all these tests though, since it's something that wouldn't get much coverage otherwise. llvm-svn: 185698
2013-07-05 21:11:52 +08:00
; (524320 - 176 - 8 * 8) / 8 = 65510 extra doublewords.
[SystemZ] Add CodeGen test cases This adds all CodeGen tests for the SystemZ target. This version of the patch incorporates feedback from a review by Sean Silva. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181204
2013-05-07 00:17:29 +08:00
define void @f2(double *%ptr, i64 %x) {
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 $NAME fi done llvm-svn: 186280
2013-07-14 14:24:09 +08:00
; CHECK-NOFP-LABEL: f2:
[SystemZ] Add CodeGen test cases This adds all CodeGen tests for the SystemZ target. This version of the patch incorporates feedback from a review by Sean Silva. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181204
2013-05-07 00:17:29 +08:00
; CHECK-NOFP: agfi %r15, -524320
; CHECK-NOFP: .cfi_def_cfa_offset 524480
; CHECK-NOFP: llilh [[INDEX:%r[1-5]]], 8
; CHECK-NOFP: std %f8, 24([[INDEX]],%r15)
; CHECK-NOFP: std %f9, 16({{%r[1-5]}},%r15)
; CHECK-NOFP: std %f10, 8({{%r[1-5]}},%r15)
; CHECK-NOFP: std %f11, 0({{%r[1-5]}},%r15)
; CHECK-NOFP: stdy %f12, 524280(%r15)
; CHECK-NOFP: stdy %f13, 524272(%r15)
; CHECK-NOFP: stdy %f14, 524264(%r15)
; CHECK-NOFP: stdy %f15, 524256(%r15)
; CHECK-NOFP: .cfi_offset %f8, -168
; CHECK-NOFP: .cfi_offset %f9, -176
; CHECK-NOFP: .cfi_offset %f10, -184
; CHECK-NOFP: .cfi_offset %f11, -192
; CHECK-NOFP: .cfi_offset %f12, -200
; CHECK-NOFP: .cfi_offset %f13, -208
; CHECK-NOFP: .cfi_offset %f14, -216
; CHECK-NOFP: .cfi_offset %f15, -224
; ...main function body...
; CHECK-NOFP: ld %f8, 24({{%r[1-5]}},%r15)
; CHECK-NOFP: ld %f9, 16({{%r[1-5]}},%r15)
; CHECK-NOFP: ld %f10, 8({{%r[1-5]}},%r15)
; CHECK-NOFP: ld %f11, 0({{%r[1-5]}},%r15)
; CHECK-NOFP: ldy %f12, 524280(%r15)
; CHECK-NOFP: ldy %f13, 524272(%r15)
; CHECK-NOFP: ldy %f14, 524264(%r15)
; CHECK-NOFP: ldy %f15, 524256(%r15)
; CHECK-NOFP: agfi %r15, 524320
; CHECK-NOFP: br %r14
;
Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change and all updated tests passed locally. This update was done with the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$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-FP-LABEL: f2:
[SystemZ] Add CodeGen test cases This adds all CodeGen tests for the SystemZ target. This version of the patch incorporates feedback from a review by Sean Silva. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181204
2013-05-07 00:17:29 +08:00
; CHECK-FP: stmg %r11, %r15, 88(%r15)
; CHECK-FP: agfi %r15, -524320
; CHECK-FP: .cfi_def_cfa_offset 524480
; CHECK-FP: llilh [[INDEX:%r[1-5]]], 8
; CHECK-FP: std %f8, 24([[INDEX]],%r11)
; CHECK-FP: std %f9, 16({{%r[1-5]}},%r11)
; CHECK-FP: std %f10, 8({{%r[1-5]}},%r11)
; CHECK-FP: std %f11, 0({{%r[1-5]}},%r11)
; CHECK-FP: stdy %f12, 524280(%r11)
; CHECK-FP: stdy %f13, 524272(%r11)
; CHECK-FP: stdy %f14, 524264(%r11)
; CHECK-FP: stdy %f15, 524256(%r11)
; CHECK-FP: .cfi_offset %f8, -168
; CHECK-FP: .cfi_offset %f9, -176
; CHECK-FP: .cfi_offset %f10, -184
; CHECK-FP: .cfi_offset %f11, -192
; CHECK-FP: .cfi_offset %f12, -200
; CHECK-FP: .cfi_offset %f13, -208
; CHECK-FP: .cfi_offset %f14, -216
; CHECK-FP: .cfi_offset %f15, -224
; ...main function body...
; CHECK-FP: ld %f8, 24({{%r[1-5]}},%r11)
; CHECK-FP: ld %f9, 16({{%r[1-5]}},%r11)
; CHECK-FP: ld %f10, 8({{%r[1-5]}},%r11)
; CHECK-FP: ld %f11, 0({{%r[1-5]}},%r11)
; CHECK-FP: ldy %f12, 524280(%r11)
; CHECK-FP: ldy %f13, 524272(%r11)
; CHECK-FP: ldy %f14, 524264(%r11)
; CHECK-FP: ldy %f15, 524256(%r11)
; CHECK-FP: aghi %r11, 128
; CHECK-FP: lmg %r11, %r15, 524280(%r11)
; CHECK-FP: br %r14
[SystemZ] Allocate a second register scavenging slot This is another prerequisite for frame-to-frame MVC copies. I'll commit the patch that makes use of the slot separately. The downside of trying to test many corner cases with each of the available addressing modes is that a fair few tests need to account for the new frame layout. I do still think it's useful to have all these tests though, since it's something that wouldn't get much coverage otherwise. llvm-svn: 185698
2013-07-05 21:11:52 +08:00
%y = alloca [65510 x i64], align 8
[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
%elem = getelementptr inbounds [65510 x i64], [65510 x i64]* %y, i64 0, i64 0
[SystemZ] Add CodeGen test cases This adds all CodeGen tests for the SystemZ target. This version of the patch incorporates feedback from a review by Sean Silva. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181204
2013-05-07 00:17:29 +08:00
store volatile i64 %x, i64* %elem
[SystemZ] Test case formatting fixes Fix systematically wrong whitespace from a prior automated change. NFC. llvm-svn: 337542
2018-07-20 20:12:10 +08:00
%l0 = load volatile double, double *%ptr
%l1 = load volatile double, double *%ptr
%l2 = load volatile double, double *%ptr
%l3 = load volatile double, double *%ptr
%l4 = load volatile double, double *%ptr
%l5 = load volatile double, double *%ptr
%l6 = load volatile double, double *%ptr
%l7 = load volatile double, double *%ptr
%l8 = load volatile double, double *%ptr
%l9 = load volatile double, double *%ptr
%l10 = load volatile double, double *%ptr
%l11 = load volatile double, double *%ptr
%l12 = load volatile double, double *%ptr
%l13 = load volatile double, double *%ptr
%l14 = load volatile double, double *%ptr
%l15 = load volatile double, double *%ptr
[SystemZ] Add CodeGen test cases This adds all CodeGen tests for the SystemZ target. This version of the patch incorporates feedback from a review by Sean Silva. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181204
2013-05-07 00:17:29 +08:00
%add0 = fadd double %l0, %l0
%add1 = fadd double %l1, %add0
%add2 = fadd double %l2, %add1
%add3 = fadd double %l3, %add2
%add4 = fadd double %l4, %add3
%add5 = fadd double %l5, %add4
%add6 = fadd double %l6, %add5
%add7 = fadd double %l7, %add6
%add8 = fadd double %l8, %add7
%add9 = fadd double %l9, %add8
%add10 = fadd double %l10, %add9
%add11 = fadd double %l11, %add10
%add12 = fadd double %l12, %add11
%add13 = fadd double %l13, %add12
%add14 = fadd double %l14, %add13
%add15 = fadd double %l15, %add14
store volatile double %add0, double *%ptr
store volatile double %add1, double *%ptr
store volatile double %add2, double *%ptr
store volatile double %add3, double *%ptr
store volatile double %add4, double *%ptr
store volatile double %add5, double *%ptr
store volatile double %add6, double *%ptr
store volatile double %add7, double *%ptr
store volatile double %add8, double *%ptr
store volatile double %add9, double *%ptr
store volatile double %add10, double *%ptr
store volatile double %add11, double *%ptr
store volatile double %add12, double *%ptr
store volatile double %add13, double *%ptr
store volatile double %add14, double *%ptr
store volatile double %add15, double *%ptr
ret void
}