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/2014-01-09-pseudo_expand_im...

57 lines
2.2 KiB
LLVM
Raw Normal View History

ARM: fixup more tests to specify the target more explicitly This changes the tests that were targeting ARM EABI to explicitly specify the environment rather than relying on the default. This breaks with the new Windows on ARM support when running the tests on Windows where the default environment is no longer EABI. Take the opportunity to avoid a pointless redirect (helps when trying to debug with providing a command line invocation which can be copy and pasted) and removing a few greps in favour of FileCheck. llvm-svn: 205541
2014-04-04 00:01:44 +08:00
; RUN: llc -mtriple=arm-eabi -mattr=+neon -print-before=post-RA-sched %s -o - 2>&1 \
; RUN: | FileCheck %s
PR 18466: Fix ARM Pseudo Expansion When expanding neon pseudo stores, it may miss the implicit uses of sub regs, which may cause post RA scheduler reorder instructions that breakes anti dependency. For example: VST1d64QPseudo %R0<kill>, 16, %Q9_Q10, pred:14, pred:%noreg will be expanded to VST1d64Q %R0<kill>, 16, %D18, pred:14, pred:%noreg; An instruction that defines %D20 may be scheduled before the store by mistake. This patches adds implicit uses for such case. For the example above, it emits: VST1d64Q %R0<kill>, 8, %D18, pred:14, pred:%noreg, %Q9_Q10<imp-use> llvm-svn: 199282
2014-01-15 09:32:12 +08:00
define void @vst(i8* %m, [4 x i64] %v) {
entry:
; CHECK: vst:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; CHECK: VST1d64Q killed $r{{[0-9]+}}, 8, $d{{[0-9]+}}, 14, $noreg, implicit killed $q{{[0-9]+}}_q{{[0-9]+}}
PR 18466: Fix ARM Pseudo Expansion When expanding neon pseudo stores, it may miss the implicit uses of sub regs, which may cause post RA scheduler reorder instructions that breakes anti dependency. For example: VST1d64QPseudo %R0<kill>, 16, %Q9_Q10, pred:14, pred:%noreg will be expanded to VST1d64Q %R0<kill>, 16, %D18, pred:14, pred:%noreg; An instruction that defines %D20 may be scheduled before the store by mistake. This patches adds implicit uses for such case. For the example above, it emits: VST1d64Q %R0<kill>, 8, %D18, pred:14, pred:%noreg, %Q9_Q10<imp-use> llvm-svn: 199282
2014-01-15 09:32:12 +08:00
%v0 = extractvalue [4 x i64] %v, 0
%v1 = extractvalue [4 x i64] %v, 1
%v2 = extractvalue [4 x i64] %v, 2
%v3 = extractvalue [4 x i64] %v, 3
%t0 = bitcast i64 %v0 to <8 x i8>
%t1 = bitcast i64 %v1 to <8 x i8>
%t2 = bitcast i64 %v2 to <8 x i8>
%t3 = bitcast i64 %v3 to <8 x i8>
%s0 = bitcast <8 x i8> %t0 to <1 x i64>
%s1 = bitcast <8 x i8> %t1 to <1 x i64>
%s2 = bitcast <8 x i8> %t2 to <1 x i64>
%s3 = bitcast <8 x i8> %t3 to <1 x i64>
%tmp0 = bitcast <1 x i64> %s2 to i64
%tmp1 = bitcast <1 x i64> %s3 to i64
%n0 = insertelement <2 x i64> undef, i64 %tmp0, i32 0
%n1 = insertelement <2 x i64> %n0, i64 %tmp1, i32 1
[ARM][NEON] Use address space in vld([1234]|[234]lane) and vst([1234]|[234]lane) instructions This commit changes the interface of the vld[1234], vld[234]lane, and vst[1234], vst[234]lane ARM neon intrinsics and associates an address space with the pointer that these intrinsics take. This changes, e.g., <2 x i32> @llvm.arm.neon.vld1.v2i32(i8*, i32) to <2 x i32> @llvm.arm.neon.vld1.v2i32.p0i8(i8*, i32) This change ensures that address spaces are fully taken into account in the ARM target during lowering of interleaved loads and stores. Differential Revision: http://reviews.llvm.org/D12985 llvm-svn: 248887
2015-09-30 18:56:37 +08:00
call void @llvm.arm.neon.vst4.p0i8.v1i64(i8* %m, <1 x i64> %s0, <1 x i64> %s1, <1 x i64> %s2, <1 x i64> %s3, i32 8)
PR 18466: Fix ARM Pseudo Expansion When expanding neon pseudo stores, it may miss the implicit uses of sub regs, which may cause post RA scheduler reorder instructions that breakes anti dependency. For example: VST1d64QPseudo %R0<kill>, 16, %Q9_Q10, pred:14, pred:%noreg will be expanded to VST1d64Q %R0<kill>, 16, %D18, pred:14, pred:%noreg; An instruction that defines %D20 may be scheduled before the store by mistake. This patches adds implicit uses for such case. For the example above, it emits: VST1d64Q %R0<kill>, 8, %D18, pred:14, pred:%noreg, %Q9_Q10<imp-use> llvm-svn: 199282
2014-01-15 09:32:12 +08:00
call void @bar(<2 x i64> %n1)
ret void
}
%struct.__neon_int8x8x4_t = type { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> }
define <8 x i8> @vtbx4(<8 x i8>* %A, %struct.__neon_int8x8x4_t* %B, <8 x i8>* %C) nounwind {
; CHECK: vtbx4:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; CHECK: VTBX4 {{.*}}, 14, $noreg, implicit $q{{[0-9]+}}_q{{[0-9]+}}
[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 %struct.__neon_int8x8x4_t, %struct.__neon_int8x8x4_t* %B
PR 18466: Fix ARM Pseudo Expansion When expanding neon pseudo stores, it may miss the implicit uses of sub regs, which may cause post RA scheduler reorder instructions that breakes anti dependency. For example: VST1d64QPseudo %R0<kill>, 16, %Q9_Q10, pred:14, pred:%noreg will be expanded to VST1d64Q %R0<kill>, 16, %D18, pred:14, pred:%noreg; An instruction that defines %D20 may be scheduled before the store by mistake. This patches adds implicit uses for such case. For the example above, it emits: VST1d64Q %R0<kill>, 8, %D18, pred:14, pred:%noreg, %Q9_Q10<imp-use> llvm-svn: 199282
2014-01-15 09:32:12 +08:00
%tmp3 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 1
%tmp5 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 2
%tmp6 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 3
[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
%tmp7 = load <8 x i8>, <8 x i8>* %C
PR 18466: Fix ARM Pseudo Expansion When expanding neon pseudo stores, it may miss the implicit uses of sub regs, which may cause post RA scheduler reorder instructions that breakes anti dependency. For example: VST1d64QPseudo %R0<kill>, 16, %Q9_Q10, pred:14, pred:%noreg will be expanded to VST1d64Q %R0<kill>, 16, %D18, pred:14, pred:%noreg; An instruction that defines %D20 may be scheduled before the store by mistake. This patches adds implicit uses for such case. For the example above, it emits: VST1d64Q %R0<kill>, 8, %D18, pred:14, pred:%noreg, %Q9_Q10<imp-use> llvm-svn: 199282
2014-01-15 09:32:12 +08:00
%tmp8 = call <8 x i8> @llvm.arm.neon.vtbx4(<8 x i8> %tmp1, <8 x i8> %tmp3, <8 x i8> %tmp4, <8 x i8> %tmp5, <8 x i8> %tmp6, <8 x i8> %tmp7)
call void @bar2(%struct.__neon_int8x8x4_t %tmp2, <8 x i8> %tmp8)
ret <8 x i8> %tmp8
}
[ARM][NEON] Use address space in vld([1234]|[234]lane) and vst([1234]|[234]lane) instructions This commit changes the interface of the vld[1234], vld[234]lane, and vst[1234], vst[234]lane ARM neon intrinsics and associates an address space with the pointer that these intrinsics take. This changes, e.g., <2 x i32> @llvm.arm.neon.vld1.v2i32(i8*, i32) to <2 x i32> @llvm.arm.neon.vld1.v2i32.p0i8(i8*, i32) This change ensures that address spaces are fully taken into account in the ARM target during lowering of interleaved loads and stores. Differential Revision: http://reviews.llvm.org/D12985 llvm-svn: 248887
2015-09-30 18:56:37 +08:00
declare void @llvm.arm.neon.vst4.p0i8.v1i64(i8*, <1 x i64>, <1 x i64>, <1 x i64>, <1 x i64>, i32)
PR 18466: Fix ARM Pseudo Expansion When expanding neon pseudo stores, it may miss the implicit uses of sub regs, which may cause post RA scheduler reorder instructions that breakes anti dependency. For example: VST1d64QPseudo %R0<kill>, 16, %Q9_Q10, pred:14, pred:%noreg will be expanded to VST1d64Q %R0<kill>, 16, %D18, pred:14, pred:%noreg; An instruction that defines %D20 may be scheduled before the store by mistake. This patches adds implicit uses for such case. For the example above, it emits: VST1d64Q %R0<kill>, 8, %D18, pred:14, pred:%noreg, %Q9_Q10<imp-use> llvm-svn: 199282
2014-01-15 09:32:12 +08:00
declare <8 x i8> @llvm.arm.neon.vtbx4(<8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>) nounwind readnone
declare void @bar2(%struct.__neon_int8x8x4_t, <8 x i8>)
declare void @bar(<2 x i64> %arg)