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/ARM/vcombine.ll

128 lines
4.5 KiB
LLVM
Raw Normal View History

ARM big endian function argument passing llvm-svn: 208316
2014-05-08 22:06:24 +08:00
; RUN: llc -mtriple=arm-eabi -float-abi=soft -mattr=+neon %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-LE
; RUN: llc -mtriple=armeb-eabi -float-abi=soft -mattr=+neon %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-BE
Lower CONCAT_VECTOR during legalization instead of matching it during isel. Add a testcase. llvm-svn: 77992
2009-08-04 04:36:38 +08:00
define <16 x i8> @vcombine8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
Introduce target hook for optimizing register copies Allow a target to do something other than search for copies that will avoid cross register bank copies. Implement for SI by only rewriting the most basic copies, so it should look through anything like a subregister extract. I'm not entirely satisified with this because it seems like eliminating a reg_sequence that isn't fully used should work generically for all targets without them having to override something. However, it seems to be tricky to have a simple implementation of this without rewriting to invalid kinds of subregister copies on some targets. I'm not sure if there is currently a generic way to easily check if a subregister index would be valid for the current use. The current set of TargetRegisterInfo::get*Class functions don't quite behave like I would expect (e.g. getSubClassWithSubReg returns the maximal register class rather than the minimal), so I'm not sure how to make the generic test keep searching if SrcRC:SrcSubReg is a valid replacement for DefRC:DefSubReg. Making the default implementation to check for simple copies breaks a variety of ARM and x86 tests by producing illegal subregister uses. The ARM tests are not actually changed since it should still be using the same sharesSameRegisterFile implementation, this just relaxes them to not check for specific registers. llvm-svn: 248478
2015-09-24 16:36:14 +08:00
; CHECK-LABEL: vcombine8
; CHECK-DAG: vldr [[LD0:d[0-9]+]], [r0]
; CHECK-DAG: vldr [[LD1:d[0-9]+]], [r1]
; CHECK-LE-DAG: vmov r0, r1, [[LD0]]
; CHECK-LE-DAG: vmov r2, r3, [[LD1]]
; CHECK-BE-DAG: vmov r1, r0, d16
; CHECK-BE-DAG: vmov r3, r2, d17
[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
%tmp1 = load <8 x i8>, <8 x i8>* %A
%tmp2 = load <8 x i8>, <8 x i8>* %B
Lower CONCAT_VECTOR during legalization instead of matching it during isel. Add a testcase. llvm-svn: 77992
2009-08-04 04:36:38 +08:00
%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
ret <16 x i8> %tmp3
}
define <8 x i16> @vcombine16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
Introduce target hook for optimizing register copies Allow a target to do something other than search for copies that will avoid cross register bank copies. Implement for SI by only rewriting the most basic copies, so it should look through anything like a subregister extract. I'm not entirely satisified with this because it seems like eliminating a reg_sequence that isn't fully used should work generically for all targets without them having to override something. However, it seems to be tricky to have a simple implementation of this without rewriting to invalid kinds of subregister copies on some targets. I'm not sure if there is currently a generic way to easily check if a subregister index would be valid for the current use. The current set of TargetRegisterInfo::get*Class functions don't quite behave like I would expect (e.g. getSubClassWithSubReg returns the maximal register class rather than the minimal), so I'm not sure how to make the generic test keep searching if SrcRC:SrcSubReg is a valid replacement for DefRC:DefSubReg. Making the default implementation to check for simple copies breaks a variety of ARM and x86 tests by producing illegal subregister uses. The ARM tests are not actually changed since it should still be using the same sharesSameRegisterFile implementation, this just relaxes them to not check for specific registers. llvm-svn: 248478
2015-09-24 16:36:14 +08:00
; CHECK-LABEL: vcombine16
; CHECK-DAG: vldr [[LD0:d[0-9]+]], [r0]
; CHECK-DAG: vldr [[LD1:d[0-9]+]], [r1]
; CHECK-LE-DAG: vmov r0, r1, [[LD0]]
; CHECK-LE-DAG: vmov r2, r3, [[LD1]]
; CHECK-BE-DAG: vmov r1, r0, d16
; CHECK-BE-DAG: vmov r3, r2, d17
[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
%tmp1 = load <4 x i16>, <4 x i16>* %A
%tmp2 = load <4 x i16>, <4 x i16>* %B
Lower CONCAT_VECTOR during legalization instead of matching it during isel. Add a testcase. llvm-svn: 77992
2009-08-04 04:36:38 +08:00
%tmp3 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
ret <8 x i16> %tmp3
}
define <4 x i32> @vcombine32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
Introduce target hook for optimizing register copies Allow a target to do something other than search for copies that will avoid cross register bank copies. Implement for SI by only rewriting the most basic copies, so it should look through anything like a subregister extract. I'm not entirely satisified with this because it seems like eliminating a reg_sequence that isn't fully used should work generically for all targets without them having to override something. However, it seems to be tricky to have a simple implementation of this without rewriting to invalid kinds of subregister copies on some targets. I'm not sure if there is currently a generic way to easily check if a subregister index would be valid for the current use. The current set of TargetRegisterInfo::get*Class functions don't quite behave like I would expect (e.g. getSubClassWithSubReg returns the maximal register class rather than the minimal), so I'm not sure how to make the generic test keep searching if SrcRC:SrcSubReg is a valid replacement for DefRC:DefSubReg. Making the default implementation to check for simple copies breaks a variety of ARM and x86 tests by producing illegal subregister uses. The ARM tests are not actually changed since it should still be using the same sharesSameRegisterFile implementation, this just relaxes them to not check for specific registers. llvm-svn: 248478
2015-09-24 16:36:14 +08:00
; CHECK-LABEL: vcombine32
; CHECK-DAG: vldr [[LD0:d[0-9]+]], [r0]
; CHECK-DAG: vldr [[LD1:d[0-9]+]], [r1]
; CHECK-LE: vmov r2, r3, [[LD1]]
[SchedModel] Fix for read advance cycles with implicit pseudo operands. The SchedModel allows the addition of ReadAdvances to express that certain operands of the instructions are needed at a later point than the others. RegAlloc may add pseudo operands that are not part of the instruction descriptor, and therefore cannot have any read advance entries. This meant that in some cases the desired read advance was nullified by such a pseudo operand, which still had the original latency. This patch fixes this by making sure that such pseudo operands get a zero latency during DAG construction. Review: Matthias Braun, Ulrich Weigand. https://reviews.llvm.org/D49671 llvm-svn: 345606
2018-10-30 23:04:40 +08:00
; CHECK-LE: vmov r0, r1, [[LD0]]
Introduce target hook for optimizing register copies Allow a target to do something other than search for copies that will avoid cross register bank copies. Implement for SI by only rewriting the most basic copies, so it should look through anything like a subregister extract. I'm not entirely satisified with this because it seems like eliminating a reg_sequence that isn't fully used should work generically for all targets without them having to override something. However, it seems to be tricky to have a simple implementation of this without rewriting to invalid kinds of subregister copies on some targets. I'm not sure if there is currently a generic way to easily check if a subregister index would be valid for the current use. The current set of TargetRegisterInfo::get*Class functions don't quite behave like I would expect (e.g. getSubClassWithSubReg returns the maximal register class rather than the minimal), so I'm not sure how to make the generic test keep searching if SrcRC:SrcSubReg is a valid replacement for DefRC:DefSubReg. Making the default implementation to check for simple copies breaks a variety of ARM and x86 tests by producing illegal subregister uses. The ARM tests are not actually changed since it should still be using the same sharesSameRegisterFile implementation, this just relaxes them to not check for specific registers. llvm-svn: 248478
2015-09-24 16:36:14 +08:00
ARM big endian function argument passing llvm-svn: 208316
2014-05-08 22:06:24 +08:00
; CHECK-BE: vmov r1, r0, d16
; CHECK-BE: vmov r3, r2, d17
[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
%tmp1 = load <2 x i32>, <2 x i32>* %A
%tmp2 = load <2 x i32>, <2 x i32>* %B
Lower CONCAT_VECTOR during legalization instead of matching it during isel. Add a testcase. llvm-svn: 77992
2009-08-04 04:36:38 +08:00
%tmp3 = shufflevector <2 x i32> %tmp1, <2 x i32> %tmp2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
ret <4 x i32> %tmp3
}
define <4 x float> @vcombinefloat(<2 x float>* %A, <2 x float>* %B) nounwind {
Introduce target hook for optimizing register copies Allow a target to do something other than search for copies that will avoid cross register bank copies. Implement for SI by only rewriting the most basic copies, so it should look through anything like a subregister extract. I'm not entirely satisified with this because it seems like eliminating a reg_sequence that isn't fully used should work generically for all targets without them having to override something. However, it seems to be tricky to have a simple implementation of this without rewriting to invalid kinds of subregister copies on some targets. I'm not sure if there is currently a generic way to easily check if a subregister index would be valid for the current use. The current set of TargetRegisterInfo::get*Class functions don't quite behave like I would expect (e.g. getSubClassWithSubReg returns the maximal register class rather than the minimal), so I'm not sure how to make the generic test keep searching if SrcRC:SrcSubReg is a valid replacement for DefRC:DefSubReg. Making the default implementation to check for simple copies breaks a variety of ARM and x86 tests by producing illegal subregister uses. The ARM tests are not actually changed since it should still be using the same sharesSameRegisterFile implementation, this just relaxes them to not check for specific registers. llvm-svn: 248478
2015-09-24 16:36:14 +08:00
; CHECK-LABEL: vcombinefloat
; CHECK-DAG: vldr [[LD0:d[0-9]+]], [r0]
; CHECK-DAG: vldr [[LD1:d[0-9]+]], [r1]
; CHECK-LE: vmov r2, r3, [[LD1]]
[SchedModel] Fix for read advance cycles with implicit pseudo operands. The SchedModel allows the addition of ReadAdvances to express that certain operands of the instructions are needed at a later point than the others. RegAlloc may add pseudo operands that are not part of the instruction descriptor, and therefore cannot have any read advance entries. This meant that in some cases the desired read advance was nullified by such a pseudo operand, which still had the original latency. This patch fixes this by making sure that such pseudo operands get a zero latency during DAG construction. Review: Matthias Braun, Ulrich Weigand. https://reviews.llvm.org/D49671 llvm-svn: 345606
2018-10-30 23:04:40 +08:00
; CHECK-LE: vmov r0, r1, [[LD0]]
Introduce target hook for optimizing register copies Allow a target to do something other than search for copies that will avoid cross register bank copies. Implement for SI by only rewriting the most basic copies, so it should look through anything like a subregister extract. I'm not entirely satisified with this because it seems like eliminating a reg_sequence that isn't fully used should work generically for all targets without them having to override something. However, it seems to be tricky to have a simple implementation of this without rewriting to invalid kinds of subregister copies on some targets. I'm not sure if there is currently a generic way to easily check if a subregister index would be valid for the current use. The current set of TargetRegisterInfo::get*Class functions don't quite behave like I would expect (e.g. getSubClassWithSubReg returns the maximal register class rather than the minimal), so I'm not sure how to make the generic test keep searching if SrcRC:SrcSubReg is a valid replacement for DefRC:DefSubReg. Making the default implementation to check for simple copies breaks a variety of ARM and x86 tests by producing illegal subregister uses. The ARM tests are not actually changed since it should still be using the same sharesSameRegisterFile implementation, this just relaxes them to not check for specific registers. llvm-svn: 248478
2015-09-24 16:36:14 +08:00
ARM big endian function argument passing llvm-svn: 208316
2014-05-08 22:06:24 +08:00
; CHECK-BE: vmov r1, r0, d16
; CHECK-BE: vmov r3, r2, d17
[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
%tmp1 = load <2 x float>, <2 x float>* %A
%tmp2 = load <2 x float>, <2 x float>* %B
Lower CONCAT_VECTOR during legalization instead of matching it during isel. Add a testcase. llvm-svn: 77992
2009-08-04 04:36:38 +08:00
%tmp3 = shufflevector <2 x float> %tmp1, <2 x float> %tmp2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
ret <4 x float> %tmp3
}
define <2 x i64> @vcombine64(<1 x i64>* %A, <1 x i64>* %B) nounwind {
Introduce target hook for optimizing register copies Allow a target to do something other than search for copies that will avoid cross register bank copies. Implement for SI by only rewriting the most basic copies, so it should look through anything like a subregister extract. I'm not entirely satisified with this because it seems like eliminating a reg_sequence that isn't fully used should work generically for all targets without them having to override something. However, it seems to be tricky to have a simple implementation of this without rewriting to invalid kinds of subregister copies on some targets. I'm not sure if there is currently a generic way to easily check if a subregister index would be valid for the current use. The current set of TargetRegisterInfo::get*Class functions don't quite behave like I would expect (e.g. getSubClassWithSubReg returns the maximal register class rather than the minimal), so I'm not sure how to make the generic test keep searching if SrcRC:SrcSubReg is a valid replacement for DefRC:DefSubReg. Making the default implementation to check for simple copies breaks a variety of ARM and x86 tests by producing illegal subregister uses. The ARM tests are not actually changed since it should still be using the same sharesSameRegisterFile implementation, this just relaxes them to not check for specific registers. llvm-svn: 248478
2015-09-24 16:36:14 +08:00
; CHECK-LABEL: vcombine64
; CHECK-DAG: vldr [[LD0:d[0-9]+]], [r0]
; CHECK-DAG: vldr [[LD1:d[0-9]+]], [r1]
; CHECK-LE: vmov r2, r3, [[LD1]]
[SchedModel] Fix for read advance cycles with implicit pseudo operands. The SchedModel allows the addition of ReadAdvances to express that certain operands of the instructions are needed at a later point than the others. RegAlloc may add pseudo operands that are not part of the instruction descriptor, and therefore cannot have any read advance entries. This meant that in some cases the desired read advance was nullified by such a pseudo operand, which still had the original latency. This patch fixes this by making sure that such pseudo operands get a zero latency during DAG construction. Review: Matthias Braun, Ulrich Weigand. https://reviews.llvm.org/D49671 llvm-svn: 345606
2018-10-30 23:04:40 +08:00
; CHECK-LE: vmov r0, r1, [[LD0]]
Introduce target hook for optimizing register copies Allow a target to do something other than search for copies that will avoid cross register bank copies. Implement for SI by only rewriting the most basic copies, so it should look through anything like a subregister extract. I'm not entirely satisified with this because it seems like eliminating a reg_sequence that isn't fully used should work generically for all targets without them having to override something. However, it seems to be tricky to have a simple implementation of this without rewriting to invalid kinds of subregister copies on some targets. I'm not sure if there is currently a generic way to easily check if a subregister index would be valid for the current use. The current set of TargetRegisterInfo::get*Class functions don't quite behave like I would expect (e.g. getSubClassWithSubReg returns the maximal register class rather than the minimal), so I'm not sure how to make the generic test keep searching if SrcRC:SrcSubReg is a valid replacement for DefRC:DefSubReg. Making the default implementation to check for simple copies breaks a variety of ARM and x86 tests by producing illegal subregister uses. The ARM tests are not actually changed since it should still be using the same sharesSameRegisterFile implementation, this just relaxes them to not check for specific registers. llvm-svn: 248478
2015-09-24 16:36:14 +08:00
; CHECK-BE: vmov r3, r2, [[LD1]]
[SchedModel] Fix for read advance cycles with implicit pseudo operands. The SchedModel allows the addition of ReadAdvances to express that certain operands of the instructions are needed at a later point than the others. RegAlloc may add pseudo operands that are not part of the instruction descriptor, and therefore cannot have any read advance entries. This meant that in some cases the desired read advance was nullified by such a pseudo operand, which still had the original latency. This patch fixes this by making sure that such pseudo operands get a zero latency during DAG construction. Review: Matthias Braun, Ulrich Weigand. https://reviews.llvm.org/D49671 llvm-svn: 345606
2018-10-30 23:04:40 +08:00
; CHECK-BE: vmov r1, r0, [[LD0]]
[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
%tmp1 = load <1 x i64>, <1 x i64>* %A
%tmp2 = load <1 x i64>, <1 x i64>* %B
Lower CONCAT_VECTOR during legalization instead of matching it during isel. Add a testcase. llvm-svn: 77992
2009-08-04 04:36:38 +08:00
%tmp3 = shufflevector <1 x i64> %tmp1, <1 x i64> %tmp2, <2 x i32> <i32 0, i32 1>
ret <2 x i64> %tmp3
}
Add testcases for PR8411 (vget_low and vget_high implemented as shuffles). llvm-svn: 122997
2011-01-07 14:44:14 +08:00
; Check for vget_low and vget_high implemented with shufflevector. PR8411.
; They should not require storing to the stack.
define <4 x i16> @vget_low16(<8 x i16>* %A) nounwind {
; CHECK: vget_low16
; CHECK-NOT: vst
ARM big endian function argument passing llvm-svn: 208316
2014-05-08 22:06:24 +08:00
; CHECK-LE: vmov r0, r1, d16
; CHECK-BE: vmov r1, r0, d16
[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
%tmp1 = load <8 x i16>, <8 x i16>* %A
Add testcases for PR8411 (vget_low and vget_high implemented as shuffles). llvm-svn: 122997
2011-01-07 14:44:14 +08:00
%tmp2 = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
ret <4 x i16> %tmp2
}
define <8 x i8> @vget_high8(<16 x i8>* %A) nounwind {
; CHECK: vget_high8
; CHECK-NOT: vst
[DAGCombiner] use narrow load to avoid vector extract If we have (extract_subvector(load wide vector)) with no other users, that can just be (load narrow vector). This is intentionally conservative. Follow-ups may loosen the one-use constraint to account for the extract cost or just remove the one-use check. The memop chain updating is based on code that already exists multiple times in x86 lowering, so that should be pulled into a helper function as a follow-up. Background: this is a potential improvement noticed via regressions caused by making x86's peekThroughBitcasts() not loop on consecutive bitcasts (see comments in D33137). Differential Revision: https://reviews.llvm.org/D33578 llvm-svn: 304072
2017-05-27 22:07:03 +08:00
; CHECK-LE-NOT: vld1.64 {d16, d17}, [r0]
; CHECK-LE: vldr d16, [r0, #8]
; CHECK-LE: vmov r0, r1, d16
ARM: Implement big endian bit-conversion for NEON type llvm-svn: 208538
2014-05-12 19:19:20 +08:00
; CHECK-BE: vmov r1, r0, d16
[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
%tmp1 = load <16 x i8>, <16 x i8>* %A
Add testcases for PR8411 (vget_low and vget_high implemented as shuffles). llvm-svn: 122997
2011-01-07 14:44:14 +08:00
%tmp2 = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
ret <8 x i8> %tmp2
}
[ARM] Split 128-bit vectors in BUILD_VECTOR lowering Given that INSERT_VECTOR_ELT operates on D registers anyway, combining 64-bit vectors into a 128-bit vector is basically free. Therefore, try to split BUILD_VECTOR nodes before giving up and lowering them to a series of INSERT_VECTOR_ELT instructions. Sometimes this allows dramatically better lowerings; see testcases for examples. Inspired by similar code in the x86 backend for AVX. Differential Revision: https://reviews.llvm.org/D27624 llvm-svn: 289706
2016-12-15 04:44:38 +08:00
; vcombine(vld1_dup(p), vld1_dup(p2))
define <8 x i16> @vcombine_vdup(<8 x i16> %src, i16* nocapture readonly %p) {
; CHECK-LABEL: vcombine_vdup:
; CHECK: vld1.16 {d16[]},
; CHECK: vld1.16 {d17[]},
; CHECK-LE: vmov r0, r1, d16
; CHECK-LE: vmov r2, r3, d17
%a1 = load i16, i16* %p, align 2
%a2 = insertelement <4 x i16> undef, i16 %a1, i32 0
%a3 = shufflevector <4 x i16> %a2, <4 x i16> undef, <4 x i32> zeroinitializer
%p2 = getelementptr inbounds i16, i16* %p, i32 1
%b1 = load i16, i16* %p2, align 2
%b2 = insertelement <4 x i16> undef, i16 %b1, i32 0
%b3 = shufflevector <4 x i16> %b2, <4 x i16> undef, <4 x i32> zeroinitializer
%shuffle = shufflevector <4 x i16> %a3, <4 x i16> %b3, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
ret <8 x i16> %shuffle
}