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/int-cmp-44.ll

893 lines
18 KiB
LLVM
Raw Normal View History

Fix known typos Sweep the codebase for common typos. Includes some changes to visible function names that were misspelt. llvm-svn: 200018
2014-01-25 01:20:08 +08:00
; Test that compares are omitted if CC already has the right value
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; (z10 version).
;
[SystemZ] LTGFR use regclass should be GR32, not GR64. Discovered by testing int-cmp-44.ll with -verify-machineinstrs (added to test run). llvm-svn: 251299
2015-10-26 23:03:49 +08:00
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z10 -no-integrated-as \
; RUN: -verify-machineinstrs| FileCheck %s
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
declare void @foo()
; Addition provides enough for equality comparisons with zero. First teest
; the EQ case.
define i32 @f1(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f1:
; CHECK: afi %r2, 1000000
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: ber %r14
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = add i32 %a, 1000000
%cmp = icmp eq i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; ...and again with NE.
define i32 @f2(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f2:
; CHECK: afi %r2, 1000000
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: bner %r14
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = add i32 %a, 1000000
%cmp = icmp ne i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; SLT requires a comparison.
define i32 @f3(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f3:
; CHECK: afi %r2, 1000000
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: cibl %r2, 0, 0(%r14)
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = add i32 %a, 1000000
%cmp = icmp slt i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; ...SLE too.
define i32 @f4(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f4:
; CHECK: afi %r2, 1000000
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: cible %r2, 0, 0(%r14)
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = add i32 %a, 1000000
%cmp = icmp sle i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; ...SGT too.
define i32 @f5(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f5:
; CHECK: afi %r2, 1000000
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: cibh %r2, 0, 0(%r14)
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = add i32 %a, 1000000
%cmp = icmp sgt i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; ...SGE too.
define i32 @f6(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f6:
; CHECK: afi %r2, 1000000
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: cibhe %r2, 0, 0(%r14)
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = add i32 %a, 1000000
%cmp = icmp sge i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; Subtraction also provides enough for equality comparisons with zero.
define i32 @f7(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f7:
; CHECK: s %r2, 0(%r4)
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: bner %r14
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%cur = load i32 , i32 *%dest
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
%res = sub i32 %a, %cur
%cmp = icmp ne i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; ...but not for ordered comparisons.
define i32 @f8(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f8:
; CHECK: s %r2, 0(%r4)
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: cibl %r2, 0, 0(%r14)
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%cur = load i32 , i32 *%dest
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
%res = sub i32 %a, %cur
%cmp = icmp slt i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; Logic register-register instructions also provide enough for equality
; comparisons with zero.
define i32 @f9(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f9:
; CHECK: nr %r2, %r3
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: blr %r14
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = and i32 %a, %b
%cmp = icmp ne i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; ...but not for ordered comparisons.
define i32 @f10(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f10:
; CHECK: nr %r2, %r3
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: cibl %r2, 0, 0(%r14)
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = and i32 %a, %b
%cmp = icmp slt i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; Logic register-immediate instructions also provide enough for equality
; comparisons with zero if the immediate covers the whole register.
define i32 @f11(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f11:
[SystemZ] Add support for TMHH, TMHL, TMLH and TMLL For now just handles simple comparisons of an ANDed value with zero. The CC value provides enough information to do any comparison for a 2-bit mask, and some nonzero comparisons with more populated masks, but that's all future work. llvm-svn: 189469
2013-08-28 18:31:43 +08:00
; CHECK: nilf %r2, 100000001
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: blr %r14
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
[SystemZ] Add support for TMHH, TMHL, TMLH and TMLL For now just handles simple comparisons of an ANDed value with zero. The CC value provides enough information to do any comparison for a 2-bit mask, and some nonzero comparisons with more populated masks, but that's all future work. llvm-svn: 189469
2013-08-28 18:31:43 +08:00
%res = and i32 %a, 100000001
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
%cmp = icmp ne i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; Partial logic register-immediate instructions do not provide simple
; zero results.
define i32 @f12(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f12:
; CHECK: nill %r2, 65436
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: ciblh %r2, 0, 0(%r14)
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = and i32 %a, -100
%cmp = icmp ne i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; SRA provides the same CC result as a comparison with zero.
define i32 @f13(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f13:
; CHECK: sra %r2, 0(%r3)
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: ber %r14
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = ashr i32 %a, %b
%cmp = icmp eq i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; ...and again with NE.
define i32 @f14(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f14:
; CHECK: sra %r2, 0(%r3)
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: blhr %r14
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = ashr i32 %a, %b
%cmp = icmp ne i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; ...and SLT.
define i32 @f15(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f15:
; CHECK: sra %r2, 0(%r3)
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: blr %r14
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = ashr i32 %a, %b
%cmp = icmp slt i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; ...and SLE.
define i32 @f16(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f16:
; CHECK: sra %r2, 0(%r3)
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: bler %r14
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = ashr i32 %a, %b
%cmp = icmp sle i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; ...and SGT.
define i32 @f17(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f17:
; CHECK: sra %r2, 0(%r3)
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: bhr %r14
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = ashr i32 %a, %b
%cmp = icmp sgt i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; ...and SGE.
define i32 @f18(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f18:
; CHECK: sra %r2, 0(%r3)
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: bher %r14
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = ashr i32 %a, %b
%cmp = icmp sge i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; RISBG provides the same result as a comparison against zero.
; Test the EQ case.
define i64 @f19(i64 %a, i64 %b, i64 *%dest) {
; CHECK-LABEL: f19:
; CHECK: risbg %r2, %r3, 0, 190, 0
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: ber %r14
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = and i64 %b, -2
%cmp = icmp eq i64 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i64 %b, i64 *%dest
br label %exit
exit:
ret i64 %res
}
; ...and the SLT case.
define i64 @f20(i64 %a, i64 %b, i64 *%dest) {
; CHECK-LABEL: f20:
; CHECK: risbg %r2, %r3, 0, 190, 0
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: blr %r14
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = and i64 %b, -2
%cmp = icmp slt i64 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i64 %b, i64 *%dest
br label %exit
exit:
ret i64 %res
}
; Test a case where the register we're testing is set by a non-CC-clobbering
; instruction.
define i32 @f21(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f21:
; CHECK: afi %r2, 1000000
; CHECK-NEXT: #APP
; CHECK-NEXT: blah %r2
; CHECK-NEXT: #NO_APP
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: cibe %r2, 0, 0(%r14)
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%add = add i32 %a, 1000000
%res = call i32 asm "blah $0", "=r,0" (i32 %add)
%cmp = icmp eq i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; ...and again with a CC-clobbering instruction.
define i32 @f22(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f22:
; CHECK: afi %r2, 1000000
; CHECK-NEXT: #APP
; CHECK-NEXT: blah %r2
; CHECK-NEXT: #NO_APP
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: cibe %r2, 0, 0(%r14)
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%add = add i32 %a, 1000000
%res = call i32 asm "blah $0", "=r,0,~{cc}" (i32 %add)
%cmp = icmp eq i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; Check that stores do not interfere.
define i32 @f23(i32 %a, i32 %b, i32 *%dest1, i32 *%dest2) {
; CHECK-LABEL: f23:
; CHECK: afi %r2, 1000000
; CHECK-NEXT: st %r2, 0(%r4)
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: bner %r14
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%res = add i32 %a, 1000000
store i32 %res, i32 *%dest1
%cmp = icmp ne i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest2
br label %exit
exit:
ret i32 %res
}
; Check that calls do interfere.
define void @f24(i32 *%ptr) {
; CHECK-LABEL: f24:
; CHECK: afi [[REG:%r[0-9]+]], 1000000
; CHECK-NEXT: brasl %r14, foo@PLT
; CHECK-NEXT: cijlh [[REG]], 0, .L{{.*}}
; CHECK: br %r14
entry:
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%val = load i32 , i32 *%ptr
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
%xor = xor i32 %val, 1
%add = add i32 %xor, 1000000
call void @foo()
CodeGen: Allow small copyable blocks to "break" the CFG. When choosing the best successor for a block, ordinarily we would have preferred a block that preserves the CFG unless there is a strong probability the other direction. For small blocks that can be duplicated we now skip that requirement as well, subject to some simple frequency calculations. Differential Revision: https://reviews.llvm.org/D28583 llvm-svn: 293716
2017-02-01 07:48:32 +08:00
%cmp = icmp eq i32 %add, 0
br i1 %cmp, label %store, label %exit, !prof !1
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
store:
store i32 %add, i32 *%ptr
br label %exit
exit:
ret void
}
; Check that inline asms don't interfere if they don't clobber CC.
define void @f25(i32 %a, i32 *%ptr) {
; CHECK-LABEL: f25:
; CHECK: afi %r2, 1000000
; CHECK-NEXT: #APP
; CHECK-NEXT: blah
; CHECK-NEXT: #NO_APP
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: bner %r14
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%add = add i32 %a, 1000000
call void asm sideeffect "blah", "r"(i32 %add)
%cmp = icmp ne i32 %add, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %add, i32 *%ptr
br label %exit
exit:
ret void
}
; ...but do interfere if they do clobber CC.
define void @f26(i32 %a, i32 *%ptr) {
; CHECK-LABEL: f26:
; CHECK: afi %r2, 1000000
; CHECK-NEXT: #APP
; CHECK-NEXT: blah
; CHECK-NEXT: #NO_APP
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: ciblh %r2, 0, 0(%r14)
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%add = add i32 %a, 1000000
call void asm sideeffect "blah", "r,~{cc}"(i32 %add)
%cmp = icmp ne i32 %add, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %add, i32 *%ptr
br label %exit
exit:
ret void
}
; Test a case where CC is set based on a different register from the
; compare input.
define i32 @f27(i32 %a, i32 %b, i32 *%dest1, i32 *%dest2) {
; CHECK-LABEL: f27:
; CHECK: afi %r2, 1000000
; CHECK-NEXT: sr %r3, %r2
; CHECK-NEXT: st %r3, 0(%r4)
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: cibe %r2, 0, 0(%r14)
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%add = add i32 %a, 1000000
%sub = sub i32 %b, %add
store i32 %sub, i32 *%dest1
%cmp = icmp eq i32 %add, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %sub, i32 *%dest2
br label %exit
exit:
ret i32 %add
}
; Make sure that we don't confuse a base register for a destination.
define void @f28(i64 %a, i64 *%dest) {
; CHECK-LABEL: f28:
; CHECK: xi 0(%r2), 15
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK: cgibe %r2, 0, 0(%r14)
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
; CHECK: br %r14
entry:
%ptr = inttoptr i64 %a to i8 *
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%val = load i8 , i8 *%ptr
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
%xor = xor i8 %val, 15
store i8 %xor, i8 *%ptr
%cmp = icmp eq i64 %a, 0
br i1 %cmp, label %exit, label %store
store:
store i64 %a, i64 *%dest
br label %exit
exit:
ret void
}
[SystemZ] Use LOAD AND TEST to eliminate comparisons against zero llvm-svn: 187720
2013-08-05 19:03:20 +08:00
; Test that L gets converted to LT where useful.
define i32 @f29(i64 %base, i64 %index, i32 *%dest) {
; CHECK-LABEL: f29:
; CHECK: lt %r2, 0({{%r2,%r3|%r3,%r2}})
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: bler %r14
[SystemZ] Use LOAD AND TEST to eliminate comparisons against zero llvm-svn: 187720
2013-08-05 19:03:20 +08:00
; CHECK: br %r14
entry:
%add = add i64 %base, %index
%ptr = inttoptr i64 %add to i32 *
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%res = load i32 , i32 *%ptr
[SystemZ] Use LOAD AND TEST to eliminate comparisons against zero llvm-svn: 187720
2013-08-05 19:03:20 +08:00
%cmp = icmp sle i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %res, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; Test that LY gets converted to LT where useful.
define i32 @f30(i64 %base, i64 %index, i32 *%dest) {
; CHECK-LABEL: f30:
; CHECK: lt %r2, 100000({{%r2,%r3|%r3,%r2}})
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: bler %r14
[SystemZ] Use LOAD AND TEST to eliminate comparisons against zero llvm-svn: 187720
2013-08-05 19:03:20 +08:00
; CHECK: br %r14
entry:
%add1 = add i64 %base, %index
%add2 = add i64 %add1, 100000
%ptr = inttoptr i64 %add2 to i32 *
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%res = load i32 , i32 *%ptr
[SystemZ] Use LOAD AND TEST to eliminate comparisons against zero llvm-svn: 187720
2013-08-05 19:03:20 +08:00
%cmp = icmp sle i32 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %res, i32 *%dest
br label %exit
exit:
ret i32 %res
}
; Test that LG gets converted to LTG where useful.
define i64 @f31(i64 %base, i64 %index, i64 *%dest) {
; CHECK-LABEL: f31:
; CHECK: ltg %r2, 0({{%r2,%r3|%r3,%r2}})
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: bher %r14
[SystemZ] Use LOAD AND TEST to eliminate comparisons against zero llvm-svn: 187720
2013-08-05 19:03:20 +08:00
; CHECK: br %r14
entry:
%add = add i64 %base, %index
%ptr = inttoptr i64 %add to i64 *
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%res = load i64 , i64 *%ptr
[SystemZ] Use LOAD AND TEST to eliminate comparisons against zero llvm-svn: 187720
2013-08-05 19:03:20 +08:00
%cmp = icmp sge i64 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i64 %res, i64 *%dest
br label %exit
exit:
ret i64 %res
}
; Test that LGF gets converted to LTGF where useful.
define i64 @f32(i64 %base, i64 %index, i64 *%dest) {
; CHECK-LABEL: f32:
; CHECK: ltgf %r2, 0({{%r2,%r3|%r3,%r2}})
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: bhr %r14
[SystemZ] Use LOAD AND TEST to eliminate comparisons against zero llvm-svn: 187720
2013-08-05 19:03:20 +08:00
; CHECK: br %r14
entry:
%add = add i64 %base, %index
%ptr = inttoptr i64 %add to i32 *
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%val = load i32 , i32 *%ptr
[SystemZ] Use LOAD AND TEST to eliminate comparisons against zero llvm-svn: 187720
2013-08-05 19:03:20 +08:00
%res = sext i32 %val to i64
%cmp = icmp sgt i64 %res, 0
br i1 %cmp, label %exit, label %store
store:
store i64 %res, i64 *%dest
br label %exit
exit:
ret i64 %res
}
; Test that LR gets converted to LTR where useful.
define i32 @f33(i32 %dummy, i32 %val, i32 *%dest) {
; CHECK-LABEL: f33:
; CHECK: ltr %r2, %r3
; CHECK-NEXT: #APP
; CHECK-NEXT: blah %r2
; CHECK-NEXT: #NO_APP
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: blr %r14
[SystemZ] Use LOAD AND TEST to eliminate comparisons against zero llvm-svn: 187720
2013-08-05 19:03:20 +08:00
; CHECK: br %r14
entry:
call void asm sideeffect "blah $0", "{r2}"(i32 %val)
%cmp = icmp slt i32 %val, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %val, i32 *%dest
br label %exit
exit:
ret i32 %val
}
; Test that LGR gets converted to LTGR where useful.
define i64 @f34(i64 %dummy, i64 %val, i64 *%dest) {
; CHECK-LABEL: f34:
; CHECK: ltgr %r2, %r3
; CHECK-NEXT: #APP
; CHECK-NEXT: blah %r2
; CHECK-NEXT: #NO_APP
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: bhr %r14
[SystemZ] Use LOAD AND TEST to eliminate comparisons against zero llvm-svn: 187720
2013-08-05 19:03:20 +08:00
; CHECK: br %r14
entry:
call void asm sideeffect "blah $0", "{r2}"(i64 %val)
%cmp = icmp sgt i64 %val, 0
br i1 %cmp, label %exit, label %store
store:
store i64 %val, i64 *%dest
br label %exit
exit:
ret i64 %val
}
; Test that LGFR gets converted to LTGFR where useful.
define i64 @f35(i64 %dummy, i32 %val, i64 *%dest) {
; CHECK-LABEL: f35:
; CHECK: ltgfr %r2, %r3
; CHECK-NEXT: #APP
; CHECK-NEXT: blah %r2
; CHECK-NEXT: #NO_APP
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: bhr %r14
[SystemZ] Use LOAD AND TEST to eliminate comparisons against zero llvm-svn: 187720
2013-08-05 19:03:20 +08:00
; CHECK: br %r14
entry:
%ext = sext i32 %val to i64
call void asm sideeffect "blah $0", "{r2}"(i64 %ext)
%cmp = icmp sgt i64 %ext, 0
br i1 %cmp, label %exit, label %store
store:
store i64 %ext, i64 *%dest
br label %exit
exit:
ret i64 %ext
}
; Test a case where it is the source rather than destination of LR that
; we need.
define i32 @f36(i32 %val, i32 %dummy, i32 *%dest) {
; CHECK-LABEL: f36:
; CHECK: ltr %r3, %r2
; CHECK-NEXT: #APP
; CHECK-NEXT: blah %r3
; CHECK-NEXT: #NO_APP
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: blr %r14
[SystemZ] Use LOAD AND TEST to eliminate comparisons against zero llvm-svn: 187720
2013-08-05 19:03:20 +08:00
; CHECK: br %r14
entry:
call void asm sideeffect "blah $0", "{r3}"(i32 %val)
%cmp = icmp slt i32 %val, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %val, i32 *%dest
br label %exit
exit:
ret i32 %val
}
; Test a case where it is the source rather than destination of LGR that
; we need.
define i64 @f37(i64 %val, i64 %dummy, i64 *%dest) {
; CHECK-LABEL: f37:
; CHECK: ltgr %r3, %r2
; CHECK-NEXT: #APP
; CHECK-NEXT: blah %r3
; CHECK-NEXT: #NO_APP
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: blr %r14
[SystemZ] Use LOAD AND TEST to eliminate comparisons against zero llvm-svn: 187720
2013-08-05 19:03:20 +08:00
; CHECK: br %r14
entry:
call void asm sideeffect "blah $0", "{r3}"(i64 %val)
%cmp = icmp slt i64 %val, 0
br i1 %cmp, label %exit, label %store
store:
store i64 %val, i64 *%dest
br label %exit
exit:
ret i64 %val
}
; Test a case where it is the source rather than destination of LGFR that
; we need.
define i32 @f38(i32 %val, i64 %dummy, i32 *%dest) {
; CHECK-LABEL: f38:
; CHECK: ltgfr %r3, %r2
; CHECK-NEXT: #APP
; CHECK-NEXT: blah %r3
; CHECK-NEXT: #NO_APP
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: blr %r14
[SystemZ] Use LOAD AND TEST to eliminate comparisons against zero llvm-svn: 187720
2013-08-05 19:03:20 +08:00
; CHECK: br %r14
entry:
%ext = sext i32 %val to i64
call void asm sideeffect "blah $0", "{r3}"(i64 %ext)
%cmp = icmp slt i32 %val, 0
br i1 %cmp, label %exit, label %store
store:
store i32 %val, i32 *%dest
br label %exit
exit:
ret i32 %val
}
[SystemZ] Make more use of LTGFR InstCombine turns (sext (trunc)) into (ashr (shl)), then converts any comparison of the ashr against zero into a comparison of the shl against zero. This makes sense in itself, but we want to undo it for z, since the sign- extension instruction has a CC-setting form. I've included tests for both the original and InstCombined variants, but the former already worked. The patch fixes the latter. llvm-svn: 197234
2013-12-13 23:07:39 +08:00
; Test f35 for in-register extensions.
define i64 @f39(i64 %dummy, i64 %a, i64 *%dest) {
; CHECK-LABEL: f39:
; CHECK: ltgfr %r2, %r3
; CHECK-NEXT: #APP
; CHECK-NEXT: blah %r2
; CHECK-NEXT: #NO_APP
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: bhr %r14
[SystemZ] Make more use of LTGFR InstCombine turns (sext (trunc)) into (ashr (shl)), then converts any comparison of the ashr against zero into a comparison of the shl against zero. This makes sense in itself, but we want to undo it for z, since the sign- extension instruction has a CC-setting form. I've included tests for both the original and InstCombined variants, but the former already worked. The patch fixes the latter. llvm-svn: 197234
2013-12-13 23:07:39 +08:00
; CHECK: br %r14
entry:
%val = trunc i64 %a to i32
%ext = sext i32 %val to i64
call void asm sideeffect "blah $0", "{r2}"(i64 %ext)
%cmp = icmp sgt i64 %ext, 0
br i1 %cmp, label %exit, label %store
store:
store i64 %ext, i64 *%dest
br label %exit
exit:
ret i64 %ext
}
; ...and again with what InstCombine would produce for f40.
define i64 @f40(i64 %dummy, i64 %a, i64 *%dest) {
; CHECK-LABEL: f40:
; CHECK: ltgfr %r2, %r3
; CHECK-NEXT: #APP
; CHECK-NEXT: blah %r2
; CHECK-NEXT: #NO_APP
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: bhr %r14
[SystemZ] Make more use of LTGFR InstCombine turns (sext (trunc)) into (ashr (shl)), then converts any comparison of the ashr against zero into a comparison of the shl against zero. This makes sense in itself, but we want to undo it for z, since the sign- extension instruction has a CC-setting form. I've included tests for both the original and InstCombined variants, but the former already worked. The patch fixes the latter. llvm-svn: 197234
2013-12-13 23:07:39 +08:00
; CHECK: br %r14
entry:
%shl = shl i64 %a, 32
%ext = ashr i64 %shl, 32
call void asm sideeffect "blah $0", "{r2}"(i64 %ext)
%cmp = icmp sgt i64 %shl, 0
br i1 %cmp, label %exit, label %store
store:
store i64 %ext, i64 *%dest
br label %exit
exit:
ret i64 %ext
}
[SystemZ] Optimize X [!=]= Y in cases where X - Y or Y - X is also computed In those cases it's better to compare the result of the subtraction against zero. llvm-svn: 197239
2013-12-13 23:50:30 +08:00
; Try a form of f7 in which the subtraction operands are compared directly.
define i32 @f41(i32 %a, i32 %b, i32 *%dest) {
; CHECK-LABEL: f41:
; CHECK: s %r2, 0(%r4)
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: bner %r14
[SystemZ] Optimize X [!=]= Y in cases where X - Y or Y - X is also computed In those cases it's better to compare the result of the subtraction against zero. llvm-svn: 197239
2013-12-13 23:50:30 +08:00
; CHECK: br %r14
entry:
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%cur = load i32 , i32 *%dest
[SystemZ] Optimize X [!=]= Y in cases where X - Y or Y - X is also computed In those cases it's better to compare the result of the subtraction against zero. llvm-svn: 197239
2013-12-13 23:50:30 +08:00
%res = sub i32 %a, %cur
%cmp = icmp ne i32 %a, %cur
br i1 %cmp, label %exit, label %store
store:
store i32 %b, i32 *%dest
br label %exit
exit:
ret i32 %res
}
[SystemZ] Optimize comparisons with truncated extended loads If the extension of a loaded value is compared against zero and used in other arithmetic, InstCombine will change the comparison to use the unextended load. It's also possible that the comparison could be against the unextended load from the outset. In DAG form this becomes a truncation of an extending load. We want to strip the truncation if possible so that we can use load-and-test instructions. llvm-svn: 197804
2013-12-20 19:56:02 +08:00
; A version of f32 that tests the unextended value.
define i64 @f42(i64 %base, i64 %index, i64 *%dest) {
; CHECK-LABEL: f42:
; CHECK: ltgf %r2, 0({{%r2,%r3|%r3,%r2}})
[SystemZ] Implement conditional returns Return is now considered a predicable instruction, and is converted to a newly-added CondReturn (which maps to BCR to %r14) instruction by the if conversion pass. Also, fused compare-and-branch transform knows about conditional returns, emitting the proper fused instructions for them. This transform triggers on a *lot* of tests, hence the huge diffstat. The changes are mostly jX to br %r14 -> bXr %r14. Author: koriakin Differential Revision: http://reviews.llvm.org/D17339 llvm-svn: 265689
2016-04-08 00:11:44 +08:00
; CHECK-NEXT: bhr %r14
[SystemZ] Optimize comparisons with truncated extended loads If the extension of a loaded value is compared against zero and used in other arithmetic, InstCombine will change the comparison to use the unextended load. It's also possible that the comparison could be against the unextended load from the outset. In DAG form this becomes a truncation of an extending load. We want to strip the truncation if possible so that we can use load-and-test instructions. llvm-svn: 197804
2013-12-20 19:56:02 +08:00
; CHECK: br %r14
entry:
%add = add i64 %base, %index
%ptr = inttoptr i64 %add to i32 *
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%val = load i32 , i32 *%ptr
[SystemZ] Optimize comparisons with truncated extended loads If the extension of a loaded value is compared against zero and used in other arithmetic, InstCombine will change the comparison to use the unextended load. It's also possible that the comparison could be against the unextended load from the outset. In DAG form this becomes a truncation of an extending load. We want to strip the truncation if possible so that we can use load-and-test instructions. llvm-svn: 197804
2013-12-20 19:56:02 +08:00
%res = sext i32 %val to i64
%cmp = icmp sgt i32 %val, 0
br i1 %cmp, label %exit, label %store
store:
store i64 %res, i64 *%dest
br label %exit
exit:
ret i64 %res
}
CodeGen: Allow small copyable blocks to "break" the CFG. When choosing the best successor for a block, ordinarily we would have preferred a block that preserves the CFG unless there is a strong probability the other direction. For small blocks that can be duplicated we now skip that requirement as well, subject to some simple frequency calculations. Differential Revision: https://reviews.llvm.org/D28583 llvm-svn: 293716
2017-02-01 07:48:32 +08:00
!1 = !{!"branch_weights", i32 2, i32 1}