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/AArch64/cond-sel.ll

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

262 lines
8.2 KiB
LLVM
Raw Normal View History

Recommit "Enable MachineOutliner by default under -Oz for AArch64" Fixed the ASAN failure from before in r338148, so recommiting. This patch enables the MachineOutliner by default in AArch64 under -Oz. The MachineOutliner offers around a 4.5% improvement on the current -Oz code size improvements. We have done work into improving the debuggability of outlined code, so that users of -Oz won't be surprised by the optimization. We have also been executing the LLVM test suite and common external tests such as the SPEC suites continuously with no issue. The outliner has a low compile-time overhead of roughly 1%. At this point, the outliner would be a really good addition to the -Oz pass pipeline! llvm-svn: 338160
2018-07-28 04:18:27 +08:00
; RUN: llc -enable-machine-outliner=never -verify-machineinstrs < %s -mtriple=aarch64-none-linux-gnu -mcpu=cyclone | FileCheck %s
; RUN: llc -enable-machine-outliner=never -verify-machineinstrs < %s -mtriple=aarch64-none-linux-gnu -mattr=-fp-armv8 | FileCheck --check-prefix=CHECK-NOFP %s
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
@var32 = global i32 0
@var64 = global i64 0
ARM64: add patterns for csXYZ with reversed operands. AArch64 tests for this, and it's obviously a good idea. Have to invert the condition code, of course. llvm-svn: 206170
2014-04-14 20:51:02 +08:00
define void @test_csel(i32 %lhs32, i32 %rhs32, i64 %lhs64) minsize {
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test_csel:
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
%tst1 = icmp ugt i32 %lhs32, %rhs32
%val1 = select i1 %tst1, i32 42, i32 52
store i32 %val1, i32* @var32
AArch64: allow MOV (imm) alias to be printed The backend has been around for years, it's pretty ridiculous that we can't even use the preferred form for printing "MOV" aliases. Unfortunately, TableGen can't handle the complex predicates when printing so it's a bunch of nasty C++. Oh well. llvm-svn: 272865
2016-06-16 09:42:25 +08:00
; CHECK-DAG: mov [[W52:w[0-9]+]], #{{52|0x34}}
; CHECK-DAG: mov [[W42:w[0-9]+]], #{{42|0x2a}}
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
; CHECK: csel {{w[0-9]+}}, [[W42]], [[W52]], hi
%rhs64 = sext i32 %rhs32 to i64
%tst2 = icmp sle i64 %lhs64, %rhs64
%val2 = select i1 %tst2, i64 %lhs64, i64 %rhs64
store i64 %val2, i64* @var64
ARM64: add patterns for csXYZ with reversed operands. AArch64 tests for this, and it's obviously a good idea. Have to invert the condition code, of course. llvm-svn: 206170
2014-04-14 20:51:02 +08:00
; CHECK: sxtw [[EXT_RHS:x[0-9]+]], {{[wx]}}[[RHS:[0-9]+]]
; CHECK: cmp [[LHS:x[0-9]+]], w[[RHS]], sxtw
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
; CHECK: csel {{x[0-9]+}}, [[LHS]], [[EXT_RHS]], le
ret void
; CHECK: ret
}
define void @test_floatcsel(float %lhs32, float %rhs32, double %lhs64, double %rhs64) {
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test_floatcsel:
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
%tst1 = fcmp one float %lhs32, %rhs32
; CHECK: fcmp {{s[0-9]+}}, {{s[0-9]+}}
[AArch64] Make the use of FP instructions optional, but enabled by default. This adds a new subtarget feature called FPARMv8 (implied by NEON), and predicates the support of the FP instructions and registers on this feature. llvm-svn: 193739
2013-10-31 17:32:11 +08:00
; CHECK-NOFP-NOT: fcmp
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
%val1 = select i1 %tst1, i32 42, i32 52
store i32 %val1, i32* @var32
AArch64: allow MOV (imm) alias to be printed The backend has been around for years, it's pretty ridiculous that we can't even use the preferred form for printing "MOV" aliases. Unfortunately, TableGen can't handle the complex predicates when printing so it's a bunch of nasty C++. Oh well. llvm-svn: 272865
2016-06-16 09:42:25 +08:00
; CHECK: mov [[W52:w[0-9]+]], #{{52|0x34}}
; CHECK: mov [[W42:w[0-9]+]], #{{42|0x2a}}
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
; CHECK: csel [[MAYBETRUE:w[0-9]+]], [[W42]], [[W52]], mi
; CHECK: csel {{w[0-9]+}}, [[W42]], [[MAYBETRUE]], gt
%tst2 = fcmp ueq double %lhs64, %rhs64
; CHECK: fcmp {{d[0-9]+}}, {{d[0-9]+}}
[AArch64] Make the use of FP instructions optional, but enabled by default. This adds a new subtarget feature called FPARMv8 (implied by NEON), and predicates the support of the FP instructions and registers on this feature. llvm-svn: 193739
2013-10-31 17:32:11 +08:00
; CHECK-NOFP-NOT: fcmp
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
%val2 = select i1 %tst2, i64 9, i64 15
store i64 %val2, i64* @var64
[AArch64] Prefer "mov" over "orr" to materialize constants. This is generally more readable due to the way the assembler aliases work. (This causes a lot of test changes, but it's not really as scary as it looks at first glance; it's just mechanically changing a bunch of checks for orr to check for mov instead.) Differential Revision: https://reviews.llvm.org/D59720 llvm-svn: 356954
2019-03-26 05:25:28 +08:00
; CHECK: mov w[[CONST15:[0-9]+]], #15
AArch64: allow MOV (imm) alias to be printed The backend has been around for years, it's pretty ridiculous that we can't even use the preferred form for printing "MOV" aliases. Unfortunately, TableGen can't handle the complex predicates when printing so it's a bunch of nasty C++. Oh well. llvm-svn: 272865
2016-06-16 09:42:25 +08:00
; CHECK: mov {{[wx]}}[[CONST9:[0-9]+]], #{{9|0x9}}
ARM64: use 32-bit moves for constants where possible. If we know that a particular 64-bit constant has all high bits zero, then we can rely on the fact that 32-bit ARM64 instructions automatically zero out the high bits of an x-register. This gives the expansion logic less constraints to satisfy and so sometimes allows it to pick better sequences. Came up while porting test/CodeGen/AArch64/movw-consts.ll: this will allow a 32-bit MOVN to be used in @test8 soon. llvm-svn: 206379
2014-04-16 19:52:51 +08:00
; CHECK: csel [[MAYBETRUE:x[0-9]+]], x[[CONST9]], x[[CONST15]], eq
; CHECK: csel {{x[0-9]+}}, x[[CONST9]], [[MAYBETRUE]], vs
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
ret void
; CHECK: ret
}
ARM64: add patterns for csXYZ with reversed operands. AArch64 tests for this, and it's obviously a good idea. Have to invert the condition code, of course. llvm-svn: 206170
2014-04-14 20:51:02 +08:00
define void @test_csinc(i32 %lhs32, i32 %rhs32, i64 %lhs64) minsize {
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test_csinc:
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
; Note that commuting rhs and lhs in the select changes ugt to ule (i.e. hi to ls).
%tst1 = icmp ugt i32 %lhs32, %rhs32
%inc1 = add i32 %rhs32, 1
%val1 = select i1 %tst1, i32 %inc1, i32 %lhs32
store volatile i32 %val1, i32* @var32
; CHECK: cmp [[LHS:w[0-9]+]], [[RHS:w[0-9]+]]
; CHECK: csinc {{w[0-9]+}}, [[LHS]], [[RHS]], ls
%rhs2 = add i32 %rhs32, 42
%tst2 = icmp sle i32 %lhs32, %rhs2
%inc2 = add i32 %rhs32, 1
%val2 = select i1 %tst2, i32 %lhs32, i32 %inc2
store volatile i32 %val2, i32* @var32
; CHECK: cmp [[LHS:w[0-9]+]], {{w[0-9]+}}
; CHECK: csinc {{w[0-9]+}}, [[LHS]], {{w[0-9]+}}, le
; Note that commuting rhs and lhs in the select changes ugt to ule (i.e. hi to ls).
%rhs3 = sext i32 %rhs32 to i64
%tst3 = icmp ugt i64 %lhs64, %rhs3
%inc3 = add i64 %rhs3, 1
%val3 = select i1 %tst3, i64 %inc3, i64 %lhs64
store volatile i64 %val3, i64* @var64
; CHECK: cmp [[LHS:x[0-9]+]], {{w[0-9]+}}
; CHECK: csinc {{x[0-9]+}}, [[LHS]], {{x[0-9]+}}, ls
%rhs4 = zext i32 %rhs32 to i64
%tst4 = icmp sle i64 %lhs64, %rhs4
%inc4 = add i64 %rhs4, 1
%val4 = select i1 %tst4, i64 %lhs64, i64 %inc4
store volatile i64 %val4, i64* @var64
; CHECK: cmp [[LHS:x[0-9]+]], {{w[0-9]+}}
; CHECK: csinc {{x[0-9]+}}, [[LHS]], {{x[0-9]+}}, le
ret void
; CHECK: ret
}
ARM64: add patterns for csXYZ with reversed operands. AArch64 tests for this, and it's obviously a good idea. Have to invert the condition code, of course. llvm-svn: 206170
2014-04-14 20:51:02 +08:00
define void @test_csinv(i32 %lhs32, i32 %rhs32, i64 %lhs64) minsize {
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test_csinv:
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
; Note that commuting rhs and lhs in the select changes ugt to ule (i.e. hi to ls).
%tst1 = icmp ugt i32 %lhs32, %rhs32
%inc1 = xor i32 -1, %rhs32
%val1 = select i1 %tst1, i32 %inc1, i32 %lhs32
store volatile i32 %val1, i32* @var32
; CHECK: cmp [[LHS:w[0-9]+]], [[RHS:w[0-9]+]]
; CHECK: csinv {{w[0-9]+}}, [[LHS]], [[RHS]], ls
%rhs2 = add i32 %rhs32, 42
%tst2 = icmp sle i32 %lhs32, %rhs2
%inc2 = xor i32 -1, %rhs32
%val2 = select i1 %tst2, i32 %lhs32, i32 %inc2
store volatile i32 %val2, i32* @var32
; CHECK: cmp [[LHS:w[0-9]+]], {{w[0-9]+}}
; CHECK: csinv {{w[0-9]+}}, [[LHS]], {{w[0-9]+}}, le
; Note that commuting rhs and lhs in the select changes ugt to ule (i.e. hi to ls).
%rhs3 = sext i32 %rhs32 to i64
%tst3 = icmp ugt i64 %lhs64, %rhs3
%inc3 = xor i64 -1, %rhs3
%val3 = select i1 %tst3, i64 %inc3, i64 %lhs64
store volatile i64 %val3, i64* @var64
; CHECK: cmp [[LHS:x[0-9]+]], {{w[0-9]+}}
; CHECK: csinv {{x[0-9]+}}, [[LHS]], {{x[0-9]+}}, ls
%rhs4 = zext i32 %rhs32 to i64
%tst4 = icmp sle i64 %lhs64, %rhs4
%inc4 = xor i64 -1, %rhs4
%val4 = select i1 %tst4, i64 %lhs64, i64 %inc4
store volatile i64 %val4, i64* @var64
; CHECK: cmp [[LHS:x[0-9]+]], {{w[0-9]+}}
; CHECK: csinv {{x[0-9]+}}, [[LHS]], {{x[0-9]+}}, le
ret void
; CHECK: ret
}
[AArch64] Generate csinv instruction more often Reviewers: t.p.northover, jmolloy Subscribers: aemerson, rengolin, mcrosier, llvm-commits Differential Revision: http://reviews.llvm.org/D17546 llvm-svn: 261675
2016-02-24 03:34:13 +08:00
define void @test_csinv0(i32 %lhs32, i32 %rhs32, i64 %lhs64, i64 %rhs64) minsize {
; CHECK-LABEL: test_csinv0:
%tst1 = icmp ugt i32 %lhs32, %rhs32
%val1 = select i1 %tst1, i32 0, i32 -1
store volatile i32 %val1, i32* @var32
; CHECK: cmp [[LHS:w[0-9]+]], [[RHS:w[0-9]+]]
; CHECK: csetm {{w[0-9]+}}, ls
%rhs2 = add i32 %rhs32, 42
%tst2 = icmp sle i32 %lhs32, %rhs2
%val2 = select i1 %tst2, i32 -1, i32 %rhs2
store volatile i32 %val2, i32* @var32
; CHECK: cmp [[LHS2:w[0-9]+]], [[RHS2:w[0-9]+]]
; CHECK: csinv {{w[0-9]+}}, [[RHS2]], wzr, gt
; Note that commuting rhs and lhs in the select changes ugt to ule (i.e. hi to ls).
%rhs3 = mul i64 %rhs64, 19
%tst3 = icmp ugt i64 %lhs64, %rhs3
%val3 = select i1 %tst3, i64 %rhs3, i64 -1
store volatile i64 %val3, i64* @var64
; CHECK: cmp [[LHS3:x[0-9]+]], [[RHS3:x[0-9]+]]
; CHECK: csinv {{x[0-9]+}}, [[RHS3]], xzr, hi
ret void
; CHECK: ret
}
ARM64: add patterns for csXYZ with reversed operands. AArch64 tests for this, and it's obviously a good idea. Have to invert the condition code, of course. llvm-svn: 206170
2014-04-14 20:51:02 +08:00
define void @test_csneg(i32 %lhs32, i32 %rhs32, i64 %lhs64) minsize {
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test_csneg:
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
; Note that commuting rhs and lhs in the select changes ugt to ule (i.e. hi to ls).
%tst1 = icmp ugt i32 %lhs32, %rhs32
%inc1 = sub i32 0, %rhs32
%val1 = select i1 %tst1, i32 %inc1, i32 %lhs32
store volatile i32 %val1, i32* @var32
; CHECK: cmp [[LHS:w[0-9]+]], [[RHS:w[0-9]+]]
; CHECK: csneg {{w[0-9]+}}, [[LHS]], [[RHS]], ls
%rhs2 = add i32 %rhs32, 42
%tst2 = icmp sle i32 %lhs32, %rhs2
%inc2 = sub i32 0, %rhs32
%val2 = select i1 %tst2, i32 %lhs32, i32 %inc2
store volatile i32 %val2, i32* @var32
; CHECK: cmp [[LHS:w[0-9]+]], {{w[0-9]+}}
; CHECK: csneg {{w[0-9]+}}, [[LHS]], {{w[0-9]+}}, le
; Note that commuting rhs and lhs in the select changes ugt to ule (i.e. hi to ls).
%rhs3 = sext i32 %rhs32 to i64
%tst3 = icmp ugt i64 %lhs64, %rhs3
%inc3 = sub i64 0, %rhs3
%val3 = select i1 %tst3, i64 %inc3, i64 %lhs64
store volatile i64 %val3, i64* @var64
; CHECK: cmp [[LHS:x[0-9]+]], {{w[0-9]+}}
; CHECK: csneg {{x[0-9]+}}, [[LHS]], {{x[0-9]+}}, ls
%rhs4 = zext i32 %rhs32 to i64
%tst4 = icmp sle i64 %lhs64, %rhs4
%inc4 = sub i64 0, %rhs4
%val4 = select i1 %tst4, i64 %lhs64, i64 %inc4
store volatile i64 %val4, i64* @var64
; CHECK: cmp [[LHS:x[0-9]+]], {{w[0-9]+}}
; CHECK: csneg {{x[0-9]+}}, [[LHS]], {{x[0-9]+}}, le
ret void
; CHECK: ret
}
define void @test_cset(i32 %lhs, i32 %rhs, i64 %lhs64) {
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test_cset:
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
; N.b. code is not optimal here (32-bit csinc would be better) but
; incoming DAG is too complex
%tst1 = icmp eq i32 %lhs, %rhs
%val1 = zext i1 %tst1 to i32
store i32 %val1, i32* @var32
; CHECK: cmp {{w[0-9]+}}, {{w[0-9]+}}
TableGen: use PrintMethods to print more aliases llvm-svn: 208607
2014-05-13 02:04:06 +08:00
; CHECK: cset {{w[0-9]+}}, eq
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
%rhs64 = sext i32 %rhs to i64
%tst2 = icmp ule i64 %lhs64, %rhs64
%val2 = zext i1 %tst2 to i64
store i64 %val2, i64* @var64
TableGen: use PrintMethods to print more aliases llvm-svn: 208607
2014-05-13 02:04:06 +08:00
; CHECK: cset {{w[0-9]+}}, ls
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
ret void
; CHECK: ret
}
define void @test_csetm(i32 %lhs, i32 %rhs, i64 %lhs64) {
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test_csetm:
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
%tst1 = icmp eq i32 %lhs, %rhs
%val1 = sext i1 %tst1 to i32
store i32 %val1, i32* @var32
; CHECK: cmp {{w[0-9]+}}, {{w[0-9]+}}
TableGen: use PrintMethods to print more aliases llvm-svn: 208607
2014-05-13 02:04:06 +08:00
; CHECK: csetm {{w[0-9]+}}, eq
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
%rhs64 = sext i32 %rhs to i64
%tst2 = icmp ule i64 %lhs64, %rhs64
%val2 = sext i1 %tst2 to i64
store i64 %val2, i64* @var64
TableGen: use PrintMethods to print more aliases llvm-svn: 208607
2014-05-13 02:04:06 +08:00
; CHECK: csetm {{x[0-9]+}}, ls
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
ret void
; CHECK: ret
}
AArch64: skip select/setcc combine in complex case. In an llvm-stress generated test, we were trying to create a v0iN type and asserting when that failed. This case could probably be handled by the function, but not without added complexity and the situation it arises in is sufficiently odd that there's probably no benefit anyway. Should fix PR20775. llvm-svn: 216725
2014-08-29 21:05:18 +08:00
define <1 x i1> @test_wide_comparison(i32 %in) {
; CHECK-LABEL: test_wide_comparison:
; CHECK: cmp w0, #1234
; CHECK: cset
%tmp = icmp sgt i32 %in, 1234
%res = select i1 %tmp, <1 x i1> <i1 1>, <1 x i1> zeroinitializer
ret <1 x i1> %res
}
AArch64: only try to get operand of a known node. A bug in r216725 meant we tried to discover the type of a SETCC before confirming the node actually was a SETCC. llvm-svn: 216734
2014-08-29 23:34:58 +08:00
define i32 @test_select_undef() {
; CHECK-LABEL: test_select_undef:
; CHECK: ret
%res = select i1 undef, i32 0, i32 42
ret i32 %res
}