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/arm64-sminv.ll

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

145 lines
4.5 KiB
LLVM
Raw Normal View History

[AARCH64] Enable AARCH64 lit tests on windows dev machines As discussed on PR27654, this patch fixes the triples of a lot of aarch64 tests and enables lit tests on windows This will hopefully help stop cases where windows developers break the aarch64 target Differential Revision: https://reviews.llvm.org/D22191 llvm-svn: 275973
2016-07-19 21:35:11 +08:00
; RUN: llc < %s -mtriple=arm64-eabi -aarch64-neon-syntax=apple -asm-verbose=false | FileCheck %s
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
define signext i8 @test_vminv_s8(<8 x i8> %a1) {
; CHECK: test_vminv_s8
; CHECK: sminv.8b b[[REGNUM:[0-9]+]], v0
; CHECK-NEXT: smov.b w0, v[[REGNUM]][0]
; CHECK-NEXT: ret
entry:
AArch64/ARM64: move ARM64 into AArch64's place This commit starts with a "git mv ARM64 AArch64" and continues out from there, renaming the C++ classes, intrinsics, and other target-local objects for consistency. "ARM64" test directories are also moved, and tests that began their life in ARM64 use an arm64 triple, those from AArch64 use an aarch64 triple. Both should be equivalent though. This finishes the AArch64 merge, and everyone should feel free to continue committing as normal now. llvm-svn: 209577
2014-05-24 20:50:23 +08:00
%vminv.i = tail call i32 @llvm.aarch64.neon.sminv.i32.v8i8(<8 x i8> %a1)
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
%0 = trunc i32 %vminv.i to i8
ret i8 %0
}
define signext i16 @test_vminv_s16(<4 x i16> %a1) {
; CHECK: test_vminv_s16
; CHECK: sminv.4h h[[REGNUM:[0-9]+]], v0
; CHECK-NEXT: smov.h w0, v[[REGNUM]][0]
; CHECK-NEXT: ret
entry:
AArch64/ARM64: move ARM64 into AArch64's place This commit starts with a "git mv ARM64 AArch64" and continues out from there, renaming the C++ classes, intrinsics, and other target-local objects for consistency. "ARM64" test directories are also moved, and tests that began their life in ARM64 use an arm64 triple, those from AArch64 use an aarch64 triple. Both should be equivalent though. This finishes the AArch64 merge, and everyone should feel free to continue committing as normal now. llvm-svn: 209577
2014-05-24 20:50:23 +08:00
%vminv.i = tail call i32 @llvm.aarch64.neon.sminv.i32.v4i16(<4 x i16> %a1)
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
%0 = trunc i32 %vminv.i to i16
ret i16 %0
}
define i32 @test_vminv_s32(<2 x i32> %a1) {
; CHECK: test_vminv_s32
; 2 x i32 is not supported by the ISA, thus, this is a special case
; CHECK: sminp.2s v[[REGNUM:[0-9]+]], v0, v0
; CHECK-NEXT: fmov w0, s[[REGNUM]]
; CHECK-NEXT: ret
entry:
AArch64/ARM64: move ARM64 into AArch64's place This commit starts with a "git mv ARM64 AArch64" and continues out from there, renaming the C++ classes, intrinsics, and other target-local objects for consistency. "ARM64" test directories are also moved, and tests that began their life in ARM64 use an arm64 triple, those from AArch64 use an aarch64 triple. Both should be equivalent though. This finishes the AArch64 merge, and everyone should feel free to continue committing as normal now. llvm-svn: 209577
2014-05-24 20:50:23 +08:00
%vminv.i = tail call i32 @llvm.aarch64.neon.sminv.i32.v2i32(<2 x i32> %a1)
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
ret i32 %vminv.i
}
define signext i8 @test_vminvq_s8(<16 x i8> %a1) {
; CHECK: test_vminvq_s8
; CHECK: sminv.16b b[[REGNUM:[0-9]+]], v0
; CHECK-NEXT: smov.b w0, v[[REGNUM]][0]
; CHECK-NEXT: ret
entry:
AArch64/ARM64: move ARM64 into AArch64's place This commit starts with a "git mv ARM64 AArch64" and continues out from there, renaming the C++ classes, intrinsics, and other target-local objects for consistency. "ARM64" test directories are also moved, and tests that began their life in ARM64 use an arm64 triple, those from AArch64 use an aarch64 triple. Both should be equivalent though. This finishes the AArch64 merge, and everyone should feel free to continue committing as normal now. llvm-svn: 209577
2014-05-24 20:50:23 +08:00
%vminv.i = tail call i32 @llvm.aarch64.neon.sminv.i32.v16i8(<16 x i8> %a1)
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
%0 = trunc i32 %vminv.i to i8
ret i8 %0
}
define signext i16 @test_vminvq_s16(<8 x i16> %a1) {
; CHECK: test_vminvq_s16
; CHECK: sminv.8h h[[REGNUM:[0-9]+]], v0
; CHECK-NEXT: smov.h w0, v[[REGNUM]][0]
; CHECK-NEXT: ret
entry:
AArch64/ARM64: move ARM64 into AArch64's place This commit starts with a "git mv ARM64 AArch64" and continues out from there, renaming the C++ classes, intrinsics, and other target-local objects for consistency. "ARM64" test directories are also moved, and tests that began their life in ARM64 use an arm64 triple, those from AArch64 use an aarch64 triple. Both should be equivalent though. This finishes the AArch64 merge, and everyone should feel free to continue committing as normal now. llvm-svn: 209577
2014-05-24 20:50:23 +08:00
%vminv.i = tail call i32 @llvm.aarch64.neon.sminv.i32.v8i16(<8 x i16> %a1)
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
%0 = trunc i32 %vminv.i to i16
ret i16 %0
}
define i32 @test_vminvq_s32(<4 x i32> %a1) {
; CHECK: test_vminvq_s32
; CHECK: sminv.4s [[REGNUM:s[0-9]+]], v0
; CHECK-NEXT: fmov w0, [[REGNUM]]
; CHECK-NEXT: ret
entry:
AArch64/ARM64: move ARM64 into AArch64's place This commit starts with a "git mv ARM64 AArch64" and continues out from there, renaming the C++ classes, intrinsics, and other target-local objects for consistency. "ARM64" test directories are also moved, and tests that began their life in ARM64 use an arm64 triple, those from AArch64 use an aarch64 triple. Both should be equivalent though. This finishes the AArch64 merge, and everyone should feel free to continue committing as normal now. llvm-svn: 209577
2014-05-24 20:50:23 +08:00
%vminv.i = tail call i32 @llvm.aarch64.neon.sminv.i32.v4i32(<4 x i32> %a1)
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
ret i32 %vminv.i
}
[AArch64] Avoid going through GPRs for across-vector instructions. This adds new node types for each intrinsic. For instance, for addv, we have AArch64ISD::UADDV, such that: (v4i32 (uaddv ...)) is the same as (v4i32 (scalar_to_vector (i32 (int_aarch64_neon_uaddv ...)))) that is, (v4i32 (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), (i32 (int_aarch64_neon_uaddv ...)), ssub) In a combine, we transform all such across-vector-lanes intrinsics to: (i32 (extract_vector_elt (uaddv ...), 0)) This has one big advantage: by making the extract_element explicit, we enable the existing patterns for lane-aware instructions to fire. This lets us avoid needlessly going through the GPRs. Consider: uint32x4_t test_mul(uint32x4_t a, uint32x4_t b) { return vmulq_n_u32(a, vaddvq_u32(b)); } We now generate: addv.4s s1, v1 mul.4s v0, v0, v1[0] instead of the previous: addv.4s s1, v1 fmov w8, s1 dup.4s v1, w8 mul.4s v0, v1, v0 rdar://20044838 llvm-svn: 231840
2015-03-11 04:45:38 +08:00
define <8 x i8> @test_vminv_s8_used_by_laneop(<8 x i8> %a1, <8 x i8> %a2) {
; CHECK-LABEL: test_vminv_s8_used_by_laneop:
; CHECK: sminv.8b b[[REGNUM:[0-9]+]], v1
[AArch64][TableGen] Skip tied result operands for InstAlias Summary: This patch fixes an issue so that the right alias is printed when the instruction has tied operands. It checks the number of operands in the resulting instruction as opposed to the alias, and then skips over tied operands that should not be printed in the alias. This allows to generate the preferred assembly syntax for the AArch64 'ins' instruction, which should always be displayed as 'mov' according to the ARM Architecture Reference Manual. Several unit tests have changed as a result, but only to reflect the preferred disassembly. Some other InstAlias patterns (movk/bic/orr) needed a slight adjustment to stop them becoming the default and breaking other unit tests. Please note that the patch is mostly the same as https://reviews.llvm.org/D29219 which was reverted because of an issue found when running TableGen with the Address Sanitizer. That issue has been addressed in this iteration of the patch. Reviewers: rengolin, stoklund, huntergr, SjoerdMeijer, rovka Reviewed By: rengolin, SjoerdMeijer Subscribers: fhahn, aemerson, javed.absar, kristof.beyls, llvm-commits Differential Revision: https://reviews.llvm.org/D40030 llvm-svn: 318650
2017-11-20 22:36:40 +08:00
; CHECK-NEXT: mov.b v0[3], v[[REGNUM]][0]
[AArch64] Avoid going through GPRs for across-vector instructions. This adds new node types for each intrinsic. For instance, for addv, we have AArch64ISD::UADDV, such that: (v4i32 (uaddv ...)) is the same as (v4i32 (scalar_to_vector (i32 (int_aarch64_neon_uaddv ...)))) that is, (v4i32 (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), (i32 (int_aarch64_neon_uaddv ...)), ssub) In a combine, we transform all such across-vector-lanes intrinsics to: (i32 (extract_vector_elt (uaddv ...), 0)) This has one big advantage: by making the extract_element explicit, we enable the existing patterns for lane-aware instructions to fire. This lets us avoid needlessly going through the GPRs. Consider: uint32x4_t test_mul(uint32x4_t a, uint32x4_t b) { return vmulq_n_u32(a, vaddvq_u32(b)); } We now generate: addv.4s s1, v1 mul.4s v0, v0, v1[0] instead of the previous: addv.4s s1, v1 fmov w8, s1 dup.4s v1, w8 mul.4s v0, v1, v0 rdar://20044838 llvm-svn: 231840
2015-03-11 04:45:38 +08:00
; CHECK-NEXT: ret
entry:
%0 = tail call i32 @llvm.aarch64.neon.sminv.i32.v8i8(<8 x i8> %a2)
%1 = trunc i32 %0 to i8
%2 = insertelement <8 x i8> %a1, i8 %1, i32 3
ret <8 x i8> %2
}
define <4 x i16> @test_vminv_s16_used_by_laneop(<4 x i16> %a1, <4 x i16> %a2) {
; CHECK-LABEL: test_vminv_s16_used_by_laneop:
; CHECK: sminv.4h h[[REGNUM:[0-9]+]], v1
[AArch64][TableGen] Skip tied result operands for InstAlias Summary: This patch fixes an issue so that the right alias is printed when the instruction has tied operands. It checks the number of operands in the resulting instruction as opposed to the alias, and then skips over tied operands that should not be printed in the alias. This allows to generate the preferred assembly syntax for the AArch64 'ins' instruction, which should always be displayed as 'mov' according to the ARM Architecture Reference Manual. Several unit tests have changed as a result, but only to reflect the preferred disassembly. Some other InstAlias patterns (movk/bic/orr) needed a slight adjustment to stop them becoming the default and breaking other unit tests. Please note that the patch is mostly the same as https://reviews.llvm.org/D29219 which was reverted because of an issue found when running TableGen with the Address Sanitizer. That issue has been addressed in this iteration of the patch. Reviewers: rengolin, stoklund, huntergr, SjoerdMeijer, rovka Reviewed By: rengolin, SjoerdMeijer Subscribers: fhahn, aemerson, javed.absar, kristof.beyls, llvm-commits Differential Revision: https://reviews.llvm.org/D40030 llvm-svn: 318650
2017-11-20 22:36:40 +08:00
; CHECK-NEXT: mov.h v0[3], v[[REGNUM]][0]
[AArch64] Avoid going through GPRs for across-vector instructions. This adds new node types for each intrinsic. For instance, for addv, we have AArch64ISD::UADDV, such that: (v4i32 (uaddv ...)) is the same as (v4i32 (scalar_to_vector (i32 (int_aarch64_neon_uaddv ...)))) that is, (v4i32 (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), (i32 (int_aarch64_neon_uaddv ...)), ssub) In a combine, we transform all such across-vector-lanes intrinsics to: (i32 (extract_vector_elt (uaddv ...), 0)) This has one big advantage: by making the extract_element explicit, we enable the existing patterns for lane-aware instructions to fire. This lets us avoid needlessly going through the GPRs. Consider: uint32x4_t test_mul(uint32x4_t a, uint32x4_t b) { return vmulq_n_u32(a, vaddvq_u32(b)); } We now generate: addv.4s s1, v1 mul.4s v0, v0, v1[0] instead of the previous: addv.4s s1, v1 fmov w8, s1 dup.4s v1, w8 mul.4s v0, v1, v0 rdar://20044838 llvm-svn: 231840
2015-03-11 04:45:38 +08:00
; CHECK-NEXT: ret
entry:
%0 = tail call i32 @llvm.aarch64.neon.sminv.i32.v4i16(<4 x i16> %a2)
%1 = trunc i32 %0 to i16
%2 = insertelement <4 x i16> %a1, i16 %1, i32 3
ret <4 x i16> %2
}
define <2 x i32> @test_vminv_s32_used_by_laneop(<2 x i32> %a1, <2 x i32> %a2) {
; CHECK-LABEL: test_vminv_s32_used_by_laneop:
; CHECK: sminp.2s v[[REGNUM:[0-9]+]], v1, v1
[AArch64][TableGen] Skip tied result operands for InstAlias Summary: This patch fixes an issue so that the right alias is printed when the instruction has tied operands. It checks the number of operands in the resulting instruction as opposed to the alias, and then skips over tied operands that should not be printed in the alias. This allows to generate the preferred assembly syntax for the AArch64 'ins' instruction, which should always be displayed as 'mov' according to the ARM Architecture Reference Manual. Several unit tests have changed as a result, but only to reflect the preferred disassembly. Some other InstAlias patterns (movk/bic/orr) needed a slight adjustment to stop them becoming the default and breaking other unit tests. Please note that the patch is mostly the same as https://reviews.llvm.org/D29219 which was reverted because of an issue found when running TableGen with the Address Sanitizer. That issue has been addressed in this iteration of the patch. Reviewers: rengolin, stoklund, huntergr, SjoerdMeijer, rovka Reviewed By: rengolin, SjoerdMeijer Subscribers: fhahn, aemerson, javed.absar, kristof.beyls, llvm-commits Differential Revision: https://reviews.llvm.org/D40030 llvm-svn: 318650
2017-11-20 22:36:40 +08:00
; CHECK-NEXT: mov.s v0[1], v[[REGNUM]][0]
[AArch64] Avoid going through GPRs for across-vector instructions. This adds new node types for each intrinsic. For instance, for addv, we have AArch64ISD::UADDV, such that: (v4i32 (uaddv ...)) is the same as (v4i32 (scalar_to_vector (i32 (int_aarch64_neon_uaddv ...)))) that is, (v4i32 (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), (i32 (int_aarch64_neon_uaddv ...)), ssub) In a combine, we transform all such across-vector-lanes intrinsics to: (i32 (extract_vector_elt (uaddv ...), 0)) This has one big advantage: by making the extract_element explicit, we enable the existing patterns for lane-aware instructions to fire. This lets us avoid needlessly going through the GPRs. Consider: uint32x4_t test_mul(uint32x4_t a, uint32x4_t b) { return vmulq_n_u32(a, vaddvq_u32(b)); } We now generate: addv.4s s1, v1 mul.4s v0, v0, v1[0] instead of the previous: addv.4s s1, v1 fmov w8, s1 dup.4s v1, w8 mul.4s v0, v1, v0 rdar://20044838 llvm-svn: 231840
2015-03-11 04:45:38 +08:00
; CHECK-NEXT: ret
entry:
%0 = tail call i32 @llvm.aarch64.neon.sminv.i32.v2i32(<2 x i32> %a2)
%1 = insertelement <2 x i32> %a1, i32 %0, i32 1
ret <2 x i32> %1
}
define <16 x i8> @test_vminvq_s8_used_by_laneop(<16 x i8> %a1, <16 x i8> %a2) {
; CHECK-LABEL: test_vminvq_s8_used_by_laneop:
; CHECK: sminv.16b b[[REGNUM:[0-9]+]], v1
[AArch64][TableGen] Skip tied result operands for InstAlias Summary: This patch fixes an issue so that the right alias is printed when the instruction has tied operands. It checks the number of operands in the resulting instruction as opposed to the alias, and then skips over tied operands that should not be printed in the alias. This allows to generate the preferred assembly syntax for the AArch64 'ins' instruction, which should always be displayed as 'mov' according to the ARM Architecture Reference Manual. Several unit tests have changed as a result, but only to reflect the preferred disassembly. Some other InstAlias patterns (movk/bic/orr) needed a slight adjustment to stop them becoming the default and breaking other unit tests. Please note that the patch is mostly the same as https://reviews.llvm.org/D29219 which was reverted because of an issue found when running TableGen with the Address Sanitizer. That issue has been addressed in this iteration of the patch. Reviewers: rengolin, stoklund, huntergr, SjoerdMeijer, rovka Reviewed By: rengolin, SjoerdMeijer Subscribers: fhahn, aemerson, javed.absar, kristof.beyls, llvm-commits Differential Revision: https://reviews.llvm.org/D40030 llvm-svn: 318650
2017-11-20 22:36:40 +08:00
; CHECK-NEXT: mov.b v0[3], v[[REGNUM]][0]
[AArch64] Avoid going through GPRs for across-vector instructions. This adds new node types for each intrinsic. For instance, for addv, we have AArch64ISD::UADDV, such that: (v4i32 (uaddv ...)) is the same as (v4i32 (scalar_to_vector (i32 (int_aarch64_neon_uaddv ...)))) that is, (v4i32 (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), (i32 (int_aarch64_neon_uaddv ...)), ssub) In a combine, we transform all such across-vector-lanes intrinsics to: (i32 (extract_vector_elt (uaddv ...), 0)) This has one big advantage: by making the extract_element explicit, we enable the existing patterns for lane-aware instructions to fire. This lets us avoid needlessly going through the GPRs. Consider: uint32x4_t test_mul(uint32x4_t a, uint32x4_t b) { return vmulq_n_u32(a, vaddvq_u32(b)); } We now generate: addv.4s s1, v1 mul.4s v0, v0, v1[0] instead of the previous: addv.4s s1, v1 fmov w8, s1 dup.4s v1, w8 mul.4s v0, v1, v0 rdar://20044838 llvm-svn: 231840
2015-03-11 04:45:38 +08:00
; CHECK-NEXT: ret
entry:
%0 = tail call i32 @llvm.aarch64.neon.sminv.i32.v16i8(<16 x i8> %a2)
%1 = trunc i32 %0 to i8
%2 = insertelement <16 x i8> %a1, i8 %1, i32 3
ret <16 x i8> %2
}
define <8 x i16> @test_vminvq_s16_used_by_laneop(<8 x i16> %a1, <8 x i16> %a2) {
; CHECK-LABEL: test_vminvq_s16_used_by_laneop:
; CHECK: sminv.8h h[[REGNUM:[0-9]+]], v1
[AArch64][TableGen] Skip tied result operands for InstAlias Summary: This patch fixes an issue so that the right alias is printed when the instruction has tied operands. It checks the number of operands in the resulting instruction as opposed to the alias, and then skips over tied operands that should not be printed in the alias. This allows to generate the preferred assembly syntax for the AArch64 'ins' instruction, which should always be displayed as 'mov' according to the ARM Architecture Reference Manual. Several unit tests have changed as a result, but only to reflect the preferred disassembly. Some other InstAlias patterns (movk/bic/orr) needed a slight adjustment to stop them becoming the default and breaking other unit tests. Please note that the patch is mostly the same as https://reviews.llvm.org/D29219 which was reverted because of an issue found when running TableGen with the Address Sanitizer. That issue has been addressed in this iteration of the patch. Reviewers: rengolin, stoklund, huntergr, SjoerdMeijer, rovka Reviewed By: rengolin, SjoerdMeijer Subscribers: fhahn, aemerson, javed.absar, kristof.beyls, llvm-commits Differential Revision: https://reviews.llvm.org/D40030 llvm-svn: 318650
2017-11-20 22:36:40 +08:00
; CHECK-NEXT: mov.h v0[3], v[[REGNUM]][0]
[AArch64] Avoid going through GPRs for across-vector instructions. This adds new node types for each intrinsic. For instance, for addv, we have AArch64ISD::UADDV, such that: (v4i32 (uaddv ...)) is the same as (v4i32 (scalar_to_vector (i32 (int_aarch64_neon_uaddv ...)))) that is, (v4i32 (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), (i32 (int_aarch64_neon_uaddv ...)), ssub) In a combine, we transform all such across-vector-lanes intrinsics to: (i32 (extract_vector_elt (uaddv ...), 0)) This has one big advantage: by making the extract_element explicit, we enable the existing patterns for lane-aware instructions to fire. This lets us avoid needlessly going through the GPRs. Consider: uint32x4_t test_mul(uint32x4_t a, uint32x4_t b) { return vmulq_n_u32(a, vaddvq_u32(b)); } We now generate: addv.4s s1, v1 mul.4s v0, v0, v1[0] instead of the previous: addv.4s s1, v1 fmov w8, s1 dup.4s v1, w8 mul.4s v0, v1, v0 rdar://20044838 llvm-svn: 231840
2015-03-11 04:45:38 +08:00
; CHECK-NEXT: ret
entry:
%0 = tail call i32 @llvm.aarch64.neon.sminv.i32.v8i16(<8 x i16> %a2)
%1 = trunc i32 %0 to i16
%2 = insertelement <8 x i16> %a1, i16 %1, i32 3
ret <8 x i16> %2
}
define <4 x i32> @test_vminvq_s32_used_by_laneop(<4 x i32> %a1, <4 x i32> %a2) {
; CHECK-LABEL: test_vminvq_s32_used_by_laneop:
; CHECK: sminv.4s s[[REGNUM:[0-9]+]], v1
[AArch64][TableGen] Skip tied result operands for InstAlias Summary: This patch fixes an issue so that the right alias is printed when the instruction has tied operands. It checks the number of operands in the resulting instruction as opposed to the alias, and then skips over tied operands that should not be printed in the alias. This allows to generate the preferred assembly syntax for the AArch64 'ins' instruction, which should always be displayed as 'mov' according to the ARM Architecture Reference Manual. Several unit tests have changed as a result, but only to reflect the preferred disassembly. Some other InstAlias patterns (movk/bic/orr) needed a slight adjustment to stop them becoming the default and breaking other unit tests. Please note that the patch is mostly the same as https://reviews.llvm.org/D29219 which was reverted because of an issue found when running TableGen with the Address Sanitizer. That issue has been addressed in this iteration of the patch. Reviewers: rengolin, stoklund, huntergr, SjoerdMeijer, rovka Reviewed By: rengolin, SjoerdMeijer Subscribers: fhahn, aemerson, javed.absar, kristof.beyls, llvm-commits Differential Revision: https://reviews.llvm.org/D40030 llvm-svn: 318650
2017-11-20 22:36:40 +08:00
; CHECK-NEXT: mov.s v0[3], v[[REGNUM]][0]
[AArch64] Avoid going through GPRs for across-vector instructions. This adds new node types for each intrinsic. For instance, for addv, we have AArch64ISD::UADDV, such that: (v4i32 (uaddv ...)) is the same as (v4i32 (scalar_to_vector (i32 (int_aarch64_neon_uaddv ...)))) that is, (v4i32 (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), (i32 (int_aarch64_neon_uaddv ...)), ssub) In a combine, we transform all such across-vector-lanes intrinsics to: (i32 (extract_vector_elt (uaddv ...), 0)) This has one big advantage: by making the extract_element explicit, we enable the existing patterns for lane-aware instructions to fire. This lets us avoid needlessly going through the GPRs. Consider: uint32x4_t test_mul(uint32x4_t a, uint32x4_t b) { return vmulq_n_u32(a, vaddvq_u32(b)); } We now generate: addv.4s s1, v1 mul.4s v0, v0, v1[0] instead of the previous: addv.4s s1, v1 fmov w8, s1 dup.4s v1, w8 mul.4s v0, v1, v0 rdar://20044838 llvm-svn: 231840
2015-03-11 04:45:38 +08:00
; CHECK-NEXT: ret
entry:
%0 = tail call i32 @llvm.aarch64.neon.sminv.i32.v4i32(<4 x i32> %a2)
%1 = insertelement <4 x i32> %a1, i32 %0, i32 3
ret <4 x i32> %1
}
AArch64/ARM64: move ARM64 into AArch64's place This commit starts with a "git mv ARM64 AArch64" and continues out from there, renaming the C++ classes, intrinsics, and other target-local objects for consistency. "ARM64" test directories are also moved, and tests that began their life in ARM64 use an arm64 triple, those from AArch64 use an aarch64 triple. Both should be equivalent though. This finishes the AArch64 merge, and everyone should feel free to continue committing as normal now. llvm-svn: 209577
2014-05-24 20:50:23 +08:00
declare i32 @llvm.aarch64.neon.sminv.i32.v4i32(<4 x i32>)
declare i32 @llvm.aarch64.neon.sminv.i32.v8i16(<8 x i16>)
declare i32 @llvm.aarch64.neon.sminv.i32.v16i8(<16 x i8>)
declare i32 @llvm.aarch64.neon.sminv.i32.v2i32(<2 x i32>)
declare i32 @llvm.aarch64.neon.sminv.i32.v4i16(<4 x i16>)
declare i32 @llvm.aarch64.neon.sminv.i32.v8i8(<8 x i8>)
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00