maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/CodeGen/aarch64-poly64.c

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

604 lines
34 KiB
C
Raw Normal View History

[ARM64] Allow the disabling of NEON and crypto instructions. Update tests to pass -target-feature +neon. llvm-svn: 206394
2014-04-16 23:33:48 +08:00
// RUN: %clang_cc1 -triple arm64-none-linux-gnu -target-feature +neon \
IRGen: Add optnone attribute on function during O0 Amongst other, this will help LTO to correctly handle/honor files compiled with O0, helping debugging failures. It also seems in line with how we handle other options, like how -fnoinline adds the appropriate attribute as well. Differential Revision: https://reviews.llvm.org/D28404 llvm-svn: 304127
2017-05-29 13:38:20 +08:00
// RUN: -ffp-contract=fast -disable-O0-optnone -emit-llvm -o - %s | opt -S -mem2reg \
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// RUN: | FileCheck %s
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
// Test new aarch64 intrinsics with poly64
#include <arm_neon.h>
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <1 x i64> @test_vceq_p64(<1 x i64> %a, <1 x i64> %b) #0 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[CMP_I:%.*]] = icmp eq <1 x i64> %a, %b
// CHECK: [[SEXT_I:%.*]] = sext <1 x i1> [[CMP_I]] to <1 x i64>
// CHECK: ret <1 x i64> [[SEXT_I]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
uint64x1_t test_vceq_p64(poly64x1_t a, poly64x1_t b) {
return vceq_p64(a, b);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vceqq_p64(<2 x i64> %a, <2 x i64> %b) #1 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[CMP_I:%.*]] = icmp eq <2 x i64> %a, %b
// CHECK: [[SEXT_I:%.*]] = sext <2 x i1> [[CMP_I]] to <2 x i64>
// CHECK: ret <2 x i64> [[SEXT_I]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
uint64x2_t test_vceqq_p64(poly64x2_t a, poly64x2_t b) {
return vceqq_p64(a, b);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <1 x i64> @test_vtst_p64(<1 x i64> %a, <1 x i64> %b) #0 {
Update for LLVM changes InstSimplify has gained the ability to remove needless bitcasts which perturbed some clang codegen tests. llvm-svn: 276728
2016-07-26 13:52:37 +08:00
// CHECK: [[TMP4:%.*]] = and <1 x i64> %a, %b
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP5:%.*]] = icmp ne <1 x i64> [[TMP4]], zeroinitializer
// CHECK: [[VTST_I:%.*]] = sext <1 x i1> [[TMP5]] to <1 x i64>
// CHECK: ret <1 x i64> [[VTST_I]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
uint64x1_t test_vtst_p64(poly64x1_t a, poly64x1_t b) {
return vtst_p64(a, b);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vtstq_p64(<2 x i64> %a, <2 x i64> %b) #1 {
Update for LLVM changes InstSimplify has gained the ability to remove needless bitcasts which perturbed some clang codegen tests. llvm-svn: 276728
2016-07-26 13:52:37 +08:00
// CHECK: [[TMP4:%.*]] = and <2 x i64> %a, %b
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP5:%.*]] = icmp ne <2 x i64> [[TMP4]], zeroinitializer
// CHECK: [[VTST_I:%.*]] = sext <2 x i1> [[TMP5]] to <2 x i64>
// CHECK: ret <2 x i64> [[VTST_I]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
uint64x2_t test_vtstq_p64(poly64x2_t a, poly64x2_t b) {
return vtstq_p64(a, b);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <1 x i64> @test_vbsl_p64(<1 x i64> %a, <1 x i64> %b, <1 x i64> %c) #0 {
Update for LLVM changes InstSimplify has gained the ability to remove needless bitcasts which perturbed some clang codegen tests. llvm-svn: 276728
2016-07-26 13:52:37 +08:00
// CHECK: [[VBSL3_I:%.*]] = and <1 x i64> %a, %b
// CHECK: [[TMP3:%.*]] = xor <1 x i64> %a, <i64 -1>
// CHECK: [[VBSL4_I:%.*]] = and <1 x i64> [[TMP3]], %c
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[VBSL5_I:%.*]] = or <1 x i64> [[VBSL3_I]], [[VBSL4_I]]
// CHECK: ret <1 x i64> [[VBSL5_I]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x1_t test_vbsl_p64(poly64x1_t a, poly64x1_t b, poly64x1_t c) {
return vbsl_p64(a, b, c);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vbslq_p64(<2 x i64> %a, <2 x i64> %b, <2 x i64> %c) #1 {
Update for LLVM changes InstSimplify has gained the ability to remove needless bitcasts which perturbed some clang codegen tests. llvm-svn: 276728
2016-07-26 13:52:37 +08:00
// CHECK: [[VBSL3_I:%.*]] = and <2 x i64> %a, %b
// CHECK: [[TMP3:%.*]] = xor <2 x i64> %a, <i64 -1, i64 -1>
// CHECK: [[VBSL4_I:%.*]] = and <2 x i64> [[TMP3]], %c
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[VBSL5_I:%.*]] = or <2 x i64> [[VBSL3_I]], [[VBSL4_I]]
// CHECK: ret <2 x i64> [[VBSL5_I]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2_t test_vbslq_p64(poly64x2_t a, poly64x2_t b, poly64x2_t c) {
return vbslq_p64(a, b, c);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define i64 @test_vget_lane_p64(<1 x i64> %v) #0 {
[ARM] Fix arm_neon.h with -flax-vector-conversions=none Really, we were already 99% of the way there; just needed a couple minor fixes that affected 64-bit-only builtins. Based on D61717. Note that the change to builtin_str changes the type of a few __builtin_neon_* intrinsics that had the "wrong" type. Fixes https://bugs.llvm.org/show_bug.cgi?id=43341 Differential Revision: https://reviews.llvm.org/D68683 llvm-svn: 374191
2019-10-10 01:57:59 +08:00
// CHECK: [[VGET_LANE:%.*]] = extractelement <1 x i64> %v, i32 0
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: ret i64 [[VGET_LANE]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64_t test_vget_lane_p64(poly64x1_t v) {
return vget_lane_p64(v, 0);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define i64 @test_vgetq_lane_p64(<2 x i64> %v) #1 {
[ARM] Fix arm_neon.h with -flax-vector-conversions=none Really, we were already 99% of the way there; just needed a couple minor fixes that affected 64-bit-only builtins. Based on D61717. Note that the change to builtin_str changes the type of a few __builtin_neon_* intrinsics that had the "wrong" type. Fixes https://bugs.llvm.org/show_bug.cgi?id=43341 Differential Revision: https://reviews.llvm.org/D68683 llvm-svn: 374191
2019-10-10 01:57:59 +08:00
// CHECK: [[VGETQ_LANE:%.*]] = extractelement <2 x i64> %v, i32 1
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: ret i64 [[VGETQ_LANE]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64_t test_vgetq_lane_p64(poly64x2_t v) {
return vgetq_lane_p64(v, 1);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <1 x i64> @test_vset_lane_p64(i64 %a, <1 x i64> %v) #0 {
[ARM] Fix arm_neon.h with -flax-vector-conversions=none Really, we were already 99% of the way there; just needed a couple minor fixes that affected 64-bit-only builtins. Based on D61717. Note that the change to builtin_str changes the type of a few __builtin_neon_* intrinsics that had the "wrong" type. Fixes https://bugs.llvm.org/show_bug.cgi?id=43341 Differential Revision: https://reviews.llvm.org/D68683 llvm-svn: 374191
2019-10-10 01:57:59 +08:00
// CHECK: [[VSET_LANE:%.*]] = insertelement <1 x i64> %v, i64 %a, i32 0
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: ret <1 x i64> [[VSET_LANE]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x1_t test_vset_lane_p64(poly64_t a, poly64x1_t v) {
return vset_lane_p64(a, v, 0);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vsetq_lane_p64(i64 %a, <2 x i64> %v) #1 {
[ARM] Fix arm_neon.h with -flax-vector-conversions=none Really, we were already 99% of the way there; just needed a couple minor fixes that affected 64-bit-only builtins. Based on D61717. Note that the change to builtin_str changes the type of a few __builtin_neon_* intrinsics that had the "wrong" type. Fixes https://bugs.llvm.org/show_bug.cgi?id=43341 Differential Revision: https://reviews.llvm.org/D68683 llvm-svn: 374191
2019-10-10 01:57:59 +08:00
// CHECK: [[VSET_LANE:%.*]] = insertelement <2 x i64> %v, i64 %a, i32 1
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: ret <2 x i64> [[VSET_LANE]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2_t test_vsetq_lane_p64(poly64_t a, poly64x2_t v) {
return vsetq_lane_p64(a, v, 1);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <1 x i64> @test_vcopy_lane_p64(<1 x i64> %a, <1 x i64> %b) #0 {
[ARM] Fix arm_neon.h with -flax-vector-conversions=none Really, we were already 99% of the way there; just needed a couple minor fixes that affected 64-bit-only builtins. Based on D61717. Note that the change to builtin_str changes the type of a few __builtin_neon_* intrinsics that had the "wrong" type. Fixes https://bugs.llvm.org/show_bug.cgi?id=43341 Differential Revision: https://reviews.llvm.org/D68683 llvm-svn: 374191
2019-10-10 01:57:59 +08:00
// CHECK: [[VGET_LANE:%.*]] = extractelement <1 x i64> %b, i32 0
// CHECK: [[VSET_LANE:%.*]] = insertelement <1 x i64> %a, i64 [[VGET_LANE]], i32 0
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: ret <1 x i64> [[VSET_LANE]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x1_t test_vcopy_lane_p64(poly64x1_t a, poly64x1_t b) {
return vcopy_lane_p64(a, 0, b, 0);
ARM64: add a few bits of polynomial intrinsic codegen. llvm-svn: 205303
2014-04-01 20:23:08 +08:00
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vcopyq_lane_p64(<2 x i64> %a, <1 x i64> %b) #1 {
[ARM] Fix arm_neon.h with -flax-vector-conversions=none Really, we were already 99% of the way there; just needed a couple minor fixes that affected 64-bit-only builtins. Based on D61717. Note that the change to builtin_str changes the type of a few __builtin_neon_* intrinsics that had the "wrong" type. Fixes https://bugs.llvm.org/show_bug.cgi?id=43341 Differential Revision: https://reviews.llvm.org/D68683 llvm-svn: 374191
2019-10-10 01:57:59 +08:00
// CHECK: [[VGET_LANE:%.*]] = extractelement <1 x i64> %b, i32 0
// CHECK: [[VSET_LANE:%.*]] = insertelement <2 x i64> %a, i64 [[VGET_LANE]], i32 1
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: ret <2 x i64> [[VSET_LANE]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2_t test_vcopyq_lane_p64(poly64x2_t a, poly64x1_t b) {
return vcopyq_lane_p64(a, 1, b, 0);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vcopyq_laneq_p64(<2 x i64> %a, <2 x i64> %b) #1 {
[ARM] Fix arm_neon.h with -flax-vector-conversions=none Really, we were already 99% of the way there; just needed a couple minor fixes that affected 64-bit-only builtins. Based on D61717. Note that the change to builtin_str changes the type of a few __builtin_neon_* intrinsics that had the "wrong" type. Fixes https://bugs.llvm.org/show_bug.cgi?id=43341 Differential Revision: https://reviews.llvm.org/D68683 llvm-svn: 374191
2019-10-10 01:57:59 +08:00
// CHECK: [[VGETQ_LANE:%.*]] = extractelement <2 x i64> %b, i32 1
// CHECK: [[VSET_LANE:%.*]] = insertelement <2 x i64> %a, i64 [[VGETQ_LANE]], i32 1
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: ret <2 x i64> [[VSET_LANE]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2_t test_vcopyq_laneq_p64(poly64x2_t a, poly64x2_t b) {
return vcopyq_laneq_p64(a, 1, b, 1);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <1 x i64> @test_vcreate_p64(i64 %a) #0 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP0:%.*]] = bitcast i64 %a to <1 x i64>
// CHECK: ret <1 x i64> [[TMP0]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x1_t test_vcreate_p64(uint64_t a) {
return vcreate_p64(a);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <1 x i64> @test_vdup_n_p64(i64 %a) #0 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[VECINIT_I:%.*]] = insertelement <1 x i64> undef, i64 %a, i32 0
// CHECK: ret <1 x i64> [[VECINIT_I]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x1_t test_vdup_n_p64(poly64_t a) {
return vdup_n_p64(a);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vdupq_n_p64(i64 %a) #1 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[VECINIT_I:%.*]] = insertelement <2 x i64> undef, i64 %a, i32 0
// CHECK: [[VECINIT1_I:%.*]] = insertelement <2 x i64> [[VECINIT_I]], i64 %a, i32 1
// CHECK: ret <2 x i64> [[VECINIT1_I]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2_t test_vdupq_n_p64(poly64_t a) {
return vdupq_n_p64(a);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <1 x i64> @test_vmov_n_p64(i64 %a) #0 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[VECINIT_I:%.*]] = insertelement <1 x i64> undef, i64 %a, i32 0
// CHECK: ret <1 x i64> [[VECINIT_I]]
[AArch64]Add 2 intrinsics vmov_n_p64/vmovq_n_p64, the alias for vdup_n_p64/vdup_n_p64. As this change is too small, commit it directly. llvm-svn: 220946
2014-10-31 10:41:37 +08:00
poly64x1_t test_vmov_n_p64(poly64_t a) {
return vmov_n_p64(a);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vmovq_n_p64(i64 %a) #1 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[VECINIT_I:%.*]] = insertelement <2 x i64> undef, i64 %a, i32 0
// CHECK: [[VECINIT1_I:%.*]] = insertelement <2 x i64> [[VECINIT_I]], i64 %a, i32 1
// CHECK: ret <2 x i64> [[VECINIT1_I]]
[AArch64]Add 2 intrinsics vmov_n_p64/vmovq_n_p64, the alias for vdup_n_p64/vdup_n_p64. As this change is too small, commit it directly. llvm-svn: 220946
2014-10-31 10:41:37 +08:00
poly64x2_t test_vmovq_n_p64(poly64_t a) {
return vmovq_n_p64(a);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <1 x i64> @test_vdup_lane_p64(<1 x i64> %vec) #0 {
[ARM] Enabling range checks on Neon intrinsics' lane arguments Summary: Range checks were not properly performed in the lane arguments of Neon intrinsics implemented based on splat operations. Calls to those intrinsics where translated to `__builtin__shufflevector` calls directly by the pre-processor through the arm_neon.h macros, missing the chance for the proper range checks. This patch enables the range check by introducing an auxiliary splat instruction in arm_neon.td, delaying the translation to shufflevector calls to CGBuiltin.cpp in clang after the checks were performed. Reviewers: jmolloy, t.p.northover, rsmith, olista01, ostannard Reviewed By: ostannard Subscribers: ostannard, dnsampaio, danielkiss, kristof.beyls, cfe-commits Tags: #clang Differential Revision: https://reviews.llvm.org/D74619
2020-03-06 00:45:03 +08:00
// CHECK: [[TMP0:%.*]] = bitcast <1 x i64> [[VEC:%.*]] to <8 x i8>
// CHECK: [[TMP1:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x i64>
// CHECK: [[LANE:%.*]] = shufflevector <1 x i64> [[TMP1]], <1 x i64> [[TMP1]], <1 x i32> zeroinitializer
// CHECK: ret <1 x i64> [[LANE]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x1_t test_vdup_lane_p64(poly64x1_t vec) {
return vdup_lane_p64(vec, 0);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vdupq_lane_p64(<1 x i64> %vec) #1 {
[ARM] Enabling range checks on Neon intrinsics' lane arguments Summary: Range checks were not properly performed in the lane arguments of Neon intrinsics implemented based on splat operations. Calls to those intrinsics where translated to `__builtin__shufflevector` calls directly by the pre-processor through the arm_neon.h macros, missing the chance for the proper range checks. This patch enables the range check by introducing an auxiliary splat instruction in arm_neon.td, delaying the translation to shufflevector calls to CGBuiltin.cpp in clang after the checks were performed. Reviewers: jmolloy, t.p.northover, rsmith, olista01, ostannard Reviewed By: ostannard Subscribers: ostannard, dnsampaio, danielkiss, kristof.beyls, cfe-commits Tags: #clang Differential Revision: https://reviews.llvm.org/D74619
2020-03-06 00:45:03 +08:00
// CHECK: [[TMP0:%.*]] = bitcast <1 x i64> [[VEC:%.*]] to <8 x i8>
// CHECK: [[TMP1:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x i64>
// CHECK: [[LANE:%.*]] = shufflevector <1 x i64> [[TMP1]], <1 x i64> [[TMP1]], <2 x i32> zeroinitializer
// CHECK: ret <2 x i64> [[LANE]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2_t test_vdupq_lane_p64(poly64x1_t vec) {
return vdupq_lane_p64(vec, 0);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vdupq_laneq_p64(<2 x i64> %vec) #1 {
[ARM] Enabling range checks on Neon intrinsics' lane arguments Summary: Range checks were not properly performed in the lane arguments of Neon intrinsics implemented based on splat operations. Calls to those intrinsics where translated to `__builtin__shufflevector` calls directly by the pre-processor through the arm_neon.h macros, missing the chance for the proper range checks. This patch enables the range check by introducing an auxiliary splat instruction in arm_neon.td, delaying the translation to shufflevector calls to CGBuiltin.cpp in clang after the checks were performed. Reviewers: jmolloy, t.p.northover, rsmith, olista01, ostannard Reviewed By: ostannard Subscribers: ostannard, dnsampaio, danielkiss, kristof.beyls, cfe-commits Tags: #clang Differential Revision: https://reviews.llvm.org/D74619
2020-03-06 00:45:03 +08:00
// CHECK: [[TMP0:%.*]] = bitcast <2 x i64> [[VEC:%.*]] to <16 x i8>
// CHECK: [[TMP1:%.*]] = bitcast <16 x i8> [[TMP0]] to <2 x i64>
// CHECK: [[LANE:%.*]] = shufflevector <2 x i64> [[TMP1]], <2 x i64> [[TMP1]], <2 x i32> <i32 1, i32 1>
// CHECK: ret <2 x i64> [[LANE]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2_t test_vdupq_laneq_p64(poly64x2_t vec) {
return vdupq_laneq_p64(vec, 1);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vcombine_p64(<1 x i64> %low, <1 x i64> %high) #1 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[SHUFFLE_I:%.*]] = shufflevector <1 x i64> %low, <1 x i64> %high, <2 x i32> <i32 0, i32 1>
// CHECK: ret <2 x i64> [[SHUFFLE_I]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2_t test_vcombine_p64(poly64x1_t low, poly64x1_t high) {
return vcombine_p64(low, high);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <1 x i64> @test_vld1_p64(i64* %ptr) #0 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP0:%.*]] = bitcast i64* %ptr to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <1 x i64>*
// CHECK: [[TMP2:%.*]] = load <1 x i64>, <1 x i64>* [[TMP1]]
// CHECK: ret <1 x i64> [[TMP2]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x1_t test_vld1_p64(poly64_t const * ptr) {
return vld1_p64(ptr);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vld1q_p64(i64* %ptr) #1 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP0:%.*]] = bitcast i64* %ptr to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <2 x i64>*
// CHECK: [[TMP2:%.*]] = load <2 x i64>, <2 x i64>* [[TMP1]]
// CHECK: ret <2 x i64> [[TMP2]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2_t test_vld1q_p64(poly64_t const * ptr) {
return vld1q_p64(ptr);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define void @test_vst1_p64(i64* %ptr, <1 x i64> %val) #0 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP0:%.*]] = bitcast i64* %ptr to i8*
// CHECK: [[TMP1:%.*]] = bitcast <1 x i64> %val to <8 x i8>
// CHECK: [[TMP2:%.*]] = bitcast i8* [[TMP0]] to <1 x i64>*
// CHECK: [[TMP3:%.*]] = bitcast <8 x i8> [[TMP1]] to <1 x i64>
// CHECK: store <1 x i64> [[TMP3]], <1 x i64>* [[TMP2]]
// CHECK: ret void
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
void test_vst1_p64(poly64_t * ptr, poly64x1_t val) {
return vst1_p64(ptr, val);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define void @test_vst1q_p64(i64* %ptr, <2 x i64> %val) #1 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP0:%.*]] = bitcast i64* %ptr to i8*
// CHECK: [[TMP1:%.*]] = bitcast <2 x i64> %val to <16 x i8>
// CHECK: [[TMP2:%.*]] = bitcast i8* [[TMP0]] to <2 x i64>*
// CHECK: [[TMP3:%.*]] = bitcast <16 x i8> [[TMP1]] to <2 x i64>
// CHECK: store <2 x i64> [[TMP3]], <2 x i64>* [[TMP2]]
// CHECK: ret void
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
void test_vst1q_p64(poly64_t * ptr, poly64x2_t val) {
return vst1q_p64(ptr, val);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define %struct.poly64x1x2_t @test_vld2_p64(i64* %ptr) #2 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[RETVAL:%.*]] = alloca %struct.poly64x1x2_t, align 8
// CHECK: [[__RET:%.*]] = alloca %struct.poly64x1x2_t, align 8
// CHECK: [[TMP0:%.*]] = bitcast %struct.poly64x1x2_t* [[__RET]] to i8*
// CHECK: [[TMP1:%.*]] = bitcast i64* %ptr to i8*
// CHECK: [[TMP2:%.*]] = bitcast i8* [[TMP1]] to <1 x i64>*
// CHECK: [[VLD2:%.*]] = call { <1 x i64>, <1 x i64> } @llvm.aarch64.neon.ld2.v1i64.p0v1i64(<1 x i64>* [[TMP2]])
// CHECK: [[TMP3:%.*]] = bitcast i8* [[TMP0]] to { <1 x i64>, <1 x i64> }*
// CHECK: store { <1 x i64>, <1 x i64> } [[VLD2]], { <1 x i64>, <1 x i64> }* [[TMP3]]
// CHECK: [[TMP4:%.*]] = bitcast %struct.poly64x1x2_t* [[RETVAL]] to i8*
// CHECK: [[TMP5:%.*]] = bitcast %struct.poly64x1x2_t* [[__RET]] to i8*
Change memcpy/memove/memset to have dest and source alignment attributes (Step 1). Summary: Upstream LLVM is changing the the prototypes of the @llvm.memcpy/memmove/memset intrinsics. This change updates the Clang tests for this change. The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change removes the alignment argument in favour of placing the alignment attribute on the source and destination pointers of the memory intrinsic call. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) At this time the source and destination alignments must be the same (Step 1). Step 2 of the change, to be landed shortly, will relax that contraint and allow the source and destination to have different alignments. llvm-svn: 322964
2018-01-20 01:12:54 +08:00
// CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP4]], i8* align 8 [[TMP5]], i64 16, i1 false)
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP6:%.*]] = load %struct.poly64x1x2_t, %struct.poly64x1x2_t* [[RETVAL]], align 8
// CHECK: ret %struct.poly64x1x2_t [[TMP6]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x1x2_t test_vld2_p64(poly64_t const * ptr) {
return vld2_p64(ptr);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define %struct.poly64x2x2_t @test_vld2q_p64(i64* %ptr) #2 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[RETVAL:%.*]] = alloca %struct.poly64x2x2_t, align 16
// CHECK: [[__RET:%.*]] = alloca %struct.poly64x2x2_t, align 16
// CHECK: [[TMP0:%.*]] = bitcast %struct.poly64x2x2_t* [[__RET]] to i8*
// CHECK: [[TMP1:%.*]] = bitcast i64* %ptr to i8*
// CHECK: [[TMP2:%.*]] = bitcast i8* [[TMP1]] to <2 x i64>*
// CHECK: [[VLD2:%.*]] = call { <2 x i64>, <2 x i64> } @llvm.aarch64.neon.ld2.v2i64.p0v2i64(<2 x i64>* [[TMP2]])
// CHECK: [[TMP3:%.*]] = bitcast i8* [[TMP0]] to { <2 x i64>, <2 x i64> }*
// CHECK: store { <2 x i64>, <2 x i64> } [[VLD2]], { <2 x i64>, <2 x i64> }* [[TMP3]]
// CHECK: [[TMP4:%.*]] = bitcast %struct.poly64x2x2_t* [[RETVAL]] to i8*
// CHECK: [[TMP5:%.*]] = bitcast %struct.poly64x2x2_t* [[__RET]] to i8*
Change memcpy/memove/memset to have dest and source alignment attributes (Step 1). Summary: Upstream LLVM is changing the the prototypes of the @llvm.memcpy/memmove/memset intrinsics. This change updates the Clang tests for this change. The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change removes the alignment argument in favour of placing the alignment attribute on the source and destination pointers of the memory intrinsic call. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) At this time the source and destination alignments must be the same (Step 1). Step 2 of the change, to be landed shortly, will relax that contraint and allow the source and destination to have different alignments. llvm-svn: 322964
2018-01-20 01:12:54 +08:00
// CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 [[TMP4]], i8* align 16 [[TMP5]], i64 32, i1 false)
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP6:%.*]] = load %struct.poly64x2x2_t, %struct.poly64x2x2_t* [[RETVAL]], align 16
// CHECK: ret %struct.poly64x2x2_t [[TMP6]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2x2_t test_vld2q_p64(poly64_t const * ptr) {
return vld2q_p64(ptr);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define %struct.poly64x1x3_t @test_vld3_p64(i64* %ptr) #2 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[RETVAL:%.*]] = alloca %struct.poly64x1x3_t, align 8
// CHECK: [[__RET:%.*]] = alloca %struct.poly64x1x3_t, align 8
// CHECK: [[TMP0:%.*]] = bitcast %struct.poly64x1x3_t* [[__RET]] to i8*
// CHECK: [[TMP1:%.*]] = bitcast i64* %ptr to i8*
// CHECK: [[TMP2:%.*]] = bitcast i8* [[TMP1]] to <1 x i64>*
// CHECK: [[VLD3:%.*]] = call { <1 x i64>, <1 x i64>, <1 x i64> } @llvm.aarch64.neon.ld3.v1i64.p0v1i64(<1 x i64>* [[TMP2]])
// CHECK: [[TMP3:%.*]] = bitcast i8* [[TMP0]] to { <1 x i64>, <1 x i64>, <1 x i64> }*
// CHECK: store { <1 x i64>, <1 x i64>, <1 x i64> } [[VLD3]], { <1 x i64>, <1 x i64>, <1 x i64> }* [[TMP3]]
// CHECK: [[TMP4:%.*]] = bitcast %struct.poly64x1x3_t* [[RETVAL]] to i8*
// CHECK: [[TMP5:%.*]] = bitcast %struct.poly64x1x3_t* [[__RET]] to i8*
Change memcpy/memove/memset to have dest and source alignment attributes (Step 1). Summary: Upstream LLVM is changing the the prototypes of the @llvm.memcpy/memmove/memset intrinsics. This change updates the Clang tests for this change. The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change removes the alignment argument in favour of placing the alignment attribute on the source and destination pointers of the memory intrinsic call. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) At this time the source and destination alignments must be the same (Step 1). Step 2 of the change, to be landed shortly, will relax that contraint and allow the source and destination to have different alignments. llvm-svn: 322964
2018-01-20 01:12:54 +08:00
// CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP4]], i8* align 8 [[TMP5]], i64 24, i1 false)
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP6:%.*]] = load %struct.poly64x1x3_t, %struct.poly64x1x3_t* [[RETVAL]], align 8
// CHECK: ret %struct.poly64x1x3_t [[TMP6]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x1x3_t test_vld3_p64(poly64_t const * ptr) {
return vld3_p64(ptr);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define %struct.poly64x2x3_t @test_vld3q_p64(i64* %ptr) #2 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[RETVAL:%.*]] = alloca %struct.poly64x2x3_t, align 16
// CHECK: [[__RET:%.*]] = alloca %struct.poly64x2x3_t, align 16
// CHECK: [[TMP0:%.*]] = bitcast %struct.poly64x2x3_t* [[__RET]] to i8*
// CHECK: [[TMP1:%.*]] = bitcast i64* %ptr to i8*
// CHECK: [[TMP2:%.*]] = bitcast i8* [[TMP1]] to <2 x i64>*
// CHECK: [[VLD3:%.*]] = call { <2 x i64>, <2 x i64>, <2 x i64> } @llvm.aarch64.neon.ld3.v2i64.p0v2i64(<2 x i64>* [[TMP2]])
// CHECK: [[TMP3:%.*]] = bitcast i8* [[TMP0]] to { <2 x i64>, <2 x i64>, <2 x i64> }*
// CHECK: store { <2 x i64>, <2 x i64>, <2 x i64> } [[VLD3]], { <2 x i64>, <2 x i64>, <2 x i64> }* [[TMP3]]
// CHECK: [[TMP4:%.*]] = bitcast %struct.poly64x2x3_t* [[RETVAL]] to i8*
// CHECK: [[TMP5:%.*]] = bitcast %struct.poly64x2x3_t* [[__RET]] to i8*
Change memcpy/memove/memset to have dest and source alignment attributes (Step 1). Summary: Upstream LLVM is changing the the prototypes of the @llvm.memcpy/memmove/memset intrinsics. This change updates the Clang tests for this change. The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change removes the alignment argument in favour of placing the alignment attribute on the source and destination pointers of the memory intrinsic call. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) At this time the source and destination alignments must be the same (Step 1). Step 2 of the change, to be landed shortly, will relax that contraint and allow the source and destination to have different alignments. llvm-svn: 322964
2018-01-20 01:12:54 +08:00
// CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 [[TMP4]], i8* align 16 [[TMP5]], i64 48, i1 false)
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP6:%.*]] = load %struct.poly64x2x3_t, %struct.poly64x2x3_t* [[RETVAL]], align 16
// CHECK: ret %struct.poly64x2x3_t [[TMP6]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2x3_t test_vld3q_p64(poly64_t const * ptr) {
return vld3q_p64(ptr);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define %struct.poly64x1x4_t @test_vld4_p64(i64* %ptr) #2 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[RETVAL:%.*]] = alloca %struct.poly64x1x4_t, align 8
// CHECK: [[__RET:%.*]] = alloca %struct.poly64x1x4_t, align 8
// CHECK: [[TMP0:%.*]] = bitcast %struct.poly64x1x4_t* [[__RET]] to i8*
// CHECK: [[TMP1:%.*]] = bitcast i64* %ptr to i8*
// CHECK: [[TMP2:%.*]] = bitcast i8* [[TMP1]] to <1 x i64>*
// CHECK: [[VLD4:%.*]] = call { <1 x i64>, <1 x i64>, <1 x i64>, <1 x i64> } @llvm.aarch64.neon.ld4.v1i64.p0v1i64(<1 x i64>* [[TMP2]])
// CHECK: [[TMP3:%.*]] = bitcast i8* [[TMP0]] to { <1 x i64>, <1 x i64>, <1 x i64>, <1 x i64> }*
// CHECK: store { <1 x i64>, <1 x i64>, <1 x i64>, <1 x i64> } [[VLD4]], { <1 x i64>, <1 x i64>, <1 x i64>, <1 x i64> }* [[TMP3]]
// CHECK: [[TMP4:%.*]] = bitcast %struct.poly64x1x4_t* [[RETVAL]] to i8*
// CHECK: [[TMP5:%.*]] = bitcast %struct.poly64x1x4_t* [[__RET]] to i8*
Change memcpy/memove/memset to have dest and source alignment attributes (Step 1). Summary: Upstream LLVM is changing the the prototypes of the @llvm.memcpy/memmove/memset intrinsics. This change updates the Clang tests for this change. The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change removes the alignment argument in favour of placing the alignment attribute on the source and destination pointers of the memory intrinsic call. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) At this time the source and destination alignments must be the same (Step 1). Step 2 of the change, to be landed shortly, will relax that contraint and allow the source and destination to have different alignments. llvm-svn: 322964
2018-01-20 01:12:54 +08:00
// CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP4]], i8* align 8 [[TMP5]], i64 32, i1 false)
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP6:%.*]] = load %struct.poly64x1x4_t, %struct.poly64x1x4_t* [[RETVAL]], align 8
// CHECK: ret %struct.poly64x1x4_t [[TMP6]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x1x4_t test_vld4_p64(poly64_t const * ptr) {
return vld4_p64(ptr);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define %struct.poly64x2x4_t @test_vld4q_p64(i64* %ptr) #2 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[RETVAL:%.*]] = alloca %struct.poly64x2x4_t, align 16
// CHECK: [[__RET:%.*]] = alloca %struct.poly64x2x4_t, align 16
// CHECK: [[TMP0:%.*]] = bitcast %struct.poly64x2x4_t* [[__RET]] to i8*
// CHECK: [[TMP1:%.*]] = bitcast i64* %ptr to i8*
// CHECK: [[TMP2:%.*]] = bitcast i8* [[TMP1]] to <2 x i64>*
// CHECK: [[VLD4:%.*]] = call { <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } @llvm.aarch64.neon.ld4.v2i64.p0v2i64(<2 x i64>* [[TMP2]])
// CHECK: [[TMP3:%.*]] = bitcast i8* [[TMP0]] to { <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> }*
// CHECK: store { <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } [[VLD4]], { <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> }* [[TMP3]]
// CHECK: [[TMP4:%.*]] = bitcast %struct.poly64x2x4_t* [[RETVAL]] to i8*
// CHECK: [[TMP5:%.*]] = bitcast %struct.poly64x2x4_t* [[__RET]] to i8*
Change memcpy/memove/memset to have dest and source alignment attributes (Step 1). Summary: Upstream LLVM is changing the the prototypes of the @llvm.memcpy/memmove/memset intrinsics. This change updates the Clang tests for this change. The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change removes the alignment argument in favour of placing the alignment attribute on the source and destination pointers of the memory intrinsic call. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) At this time the source and destination alignments must be the same (Step 1). Step 2 of the change, to be landed shortly, will relax that contraint and allow the source and destination to have different alignments. llvm-svn: 322964
2018-01-20 01:12:54 +08:00
// CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 [[TMP4]], i8* align 16 [[TMP5]], i64 64, i1 false)
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP6:%.*]] = load %struct.poly64x2x4_t, %struct.poly64x2x4_t* [[RETVAL]], align 16
// CHECK: ret %struct.poly64x2x4_t [[TMP6]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2x4_t test_vld4q_p64(poly64_t const * ptr) {
return vld4q_p64(ptr);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define void @test_vst2_p64(i64* %ptr, [2 x <1 x i64>] %val.coerce) #2 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[VAL:%.*]] = alloca %struct.poly64x1x2_t, align 8
// CHECK: [[__S1:%.*]] = alloca %struct.poly64x1x2_t, align 8
// CHECK: [[COERCE_DIVE:%.*]] = getelementptr inbounds %struct.poly64x1x2_t, %struct.poly64x1x2_t* [[VAL]], i32 0, i32 0
// CHECK: store [2 x <1 x i64>] [[VAL]].coerce, [2 x <1 x i64>]* [[COERCE_DIVE]], align 8
// CHECK: [[TMP0:%.*]] = bitcast %struct.poly64x1x2_t* [[__S1]] to i8*
// CHECK: [[TMP1:%.*]] = bitcast %struct.poly64x1x2_t* [[VAL]] to i8*
Change memcpy/memove/memset to have dest and source alignment attributes (Step 1). Summary: Upstream LLVM is changing the the prototypes of the @llvm.memcpy/memmove/memset intrinsics. This change updates the Clang tests for this change. The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change removes the alignment argument in favour of placing the alignment attribute on the source and destination pointers of the memory intrinsic call. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) At this time the source and destination alignments must be the same (Step 1). Step 2 of the change, to be landed shortly, will relax that contraint and allow the source and destination to have different alignments. llvm-svn: 322964
2018-01-20 01:12:54 +08:00
// CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP0]], i8* align 8 [[TMP1]], i64 16, i1 false)
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP2:%.*]] = bitcast i64* %ptr to i8*
// CHECK: [[VAL1:%.*]] = getelementptr inbounds %struct.poly64x1x2_t, %struct.poly64x1x2_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x <1 x i64>], [2 x <1 x i64>]* [[VAL1]], i64 0, i64 0
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP3:%.*]] = load <1 x i64>, <1 x i64>* [[ARRAYIDX]], align 8
// CHECK: [[TMP4:%.*]] = bitcast <1 x i64> [[TMP3]] to <8 x i8>
// CHECK: [[VAL2:%.*]] = getelementptr inbounds %struct.poly64x1x2_t, %struct.poly64x1x2_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX3:%.*]] = getelementptr inbounds [2 x <1 x i64>], [2 x <1 x i64>]* [[VAL2]], i64 0, i64 1
// CHECK: [[TMP5:%.*]] = load <1 x i64>, <1 x i64>* [[ARRAYIDX3]], align 8
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP6:%.*]] = bitcast <1 x i64> [[TMP5]] to <8 x i8>
// CHECK: [[TMP7:%.*]] = bitcast <8 x i8> [[TMP4]] to <1 x i64>
// CHECK: [[TMP8:%.*]] = bitcast <8 x i8> [[TMP6]] to <1 x i64>
// CHECK: call void @llvm.aarch64.neon.st2.v1i64.p0i8(<1 x i64> [[TMP7]], <1 x i64> [[TMP8]], i8* [[TMP2]])
// CHECK: ret void
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
void test_vst2_p64(poly64_t * ptr, poly64x1x2_t val) {
return vst2_p64(ptr, val);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define void @test_vst2q_p64(i64* %ptr, [2 x <2 x i64>] %val.coerce) #2 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[VAL:%.*]] = alloca %struct.poly64x2x2_t, align 16
// CHECK: [[__S1:%.*]] = alloca %struct.poly64x2x2_t, align 16
// CHECK: [[COERCE_DIVE:%.*]] = getelementptr inbounds %struct.poly64x2x2_t, %struct.poly64x2x2_t* [[VAL]], i32 0, i32 0
// CHECK: store [2 x <2 x i64>] [[VAL]].coerce, [2 x <2 x i64>]* [[COERCE_DIVE]], align 16
// CHECK: [[TMP0:%.*]] = bitcast %struct.poly64x2x2_t* [[__S1]] to i8*
// CHECK: [[TMP1:%.*]] = bitcast %struct.poly64x2x2_t* [[VAL]] to i8*
Change memcpy/memove/memset to have dest and source alignment attributes (Step 1). Summary: Upstream LLVM is changing the the prototypes of the @llvm.memcpy/memmove/memset intrinsics. This change updates the Clang tests for this change. The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change removes the alignment argument in favour of placing the alignment attribute on the source and destination pointers of the memory intrinsic call. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) At this time the source and destination alignments must be the same (Step 1). Step 2 of the change, to be landed shortly, will relax that contraint and allow the source and destination to have different alignments. llvm-svn: 322964
2018-01-20 01:12:54 +08:00
// CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 [[TMP0]], i8* align 16 [[TMP1]], i64 32, i1 false)
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP2:%.*]] = bitcast i64* %ptr to i8*
// CHECK: [[VAL1:%.*]] = getelementptr inbounds %struct.poly64x2x2_t, %struct.poly64x2x2_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x <2 x i64>], [2 x <2 x i64>]* [[VAL1]], i64 0, i64 0
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP3:%.*]] = load <2 x i64>, <2 x i64>* [[ARRAYIDX]], align 16
// CHECK: [[TMP4:%.*]] = bitcast <2 x i64> [[TMP3]] to <16 x i8>
// CHECK: [[VAL2:%.*]] = getelementptr inbounds %struct.poly64x2x2_t, %struct.poly64x2x2_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX3:%.*]] = getelementptr inbounds [2 x <2 x i64>], [2 x <2 x i64>]* [[VAL2]], i64 0, i64 1
// CHECK: [[TMP5:%.*]] = load <2 x i64>, <2 x i64>* [[ARRAYIDX3]], align 16
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP6:%.*]] = bitcast <2 x i64> [[TMP5]] to <16 x i8>
// CHECK: [[TMP7:%.*]] = bitcast <16 x i8> [[TMP4]] to <2 x i64>
// CHECK: [[TMP8:%.*]] = bitcast <16 x i8> [[TMP6]] to <2 x i64>
// CHECK: call void @llvm.aarch64.neon.st2.v2i64.p0i8(<2 x i64> [[TMP7]], <2 x i64> [[TMP8]], i8* [[TMP2]])
// CHECK: ret void
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
void test_vst2q_p64(poly64_t * ptr, poly64x2x2_t val) {
return vst2q_p64(ptr, val);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define void @test_vst3_p64(i64* %ptr, [3 x <1 x i64>] %val.coerce) #2 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[VAL:%.*]] = alloca %struct.poly64x1x3_t, align 8
// CHECK: [[__S1:%.*]] = alloca %struct.poly64x1x3_t, align 8
// CHECK: [[COERCE_DIVE:%.*]] = getelementptr inbounds %struct.poly64x1x3_t, %struct.poly64x1x3_t* [[VAL]], i32 0, i32 0
// CHECK: store [3 x <1 x i64>] [[VAL]].coerce, [3 x <1 x i64>]* [[COERCE_DIVE]], align 8
// CHECK: [[TMP0:%.*]] = bitcast %struct.poly64x1x3_t* [[__S1]] to i8*
// CHECK: [[TMP1:%.*]] = bitcast %struct.poly64x1x3_t* [[VAL]] to i8*
Change memcpy/memove/memset to have dest and source alignment attributes (Step 1). Summary: Upstream LLVM is changing the the prototypes of the @llvm.memcpy/memmove/memset intrinsics. This change updates the Clang tests for this change. The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change removes the alignment argument in favour of placing the alignment attribute on the source and destination pointers of the memory intrinsic call. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) At this time the source and destination alignments must be the same (Step 1). Step 2 of the change, to be landed shortly, will relax that contraint and allow the source and destination to have different alignments. llvm-svn: 322964
2018-01-20 01:12:54 +08:00
// CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP0]], i8* align 8 [[TMP1]], i64 24, i1 false)
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP2:%.*]] = bitcast i64* %ptr to i8*
// CHECK: [[VAL1:%.*]] = getelementptr inbounds %struct.poly64x1x3_t, %struct.poly64x1x3_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX:%.*]] = getelementptr inbounds [3 x <1 x i64>], [3 x <1 x i64>]* [[VAL1]], i64 0, i64 0
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP3:%.*]] = load <1 x i64>, <1 x i64>* [[ARRAYIDX]], align 8
// CHECK: [[TMP4:%.*]] = bitcast <1 x i64> [[TMP3]] to <8 x i8>
// CHECK: [[VAL2:%.*]] = getelementptr inbounds %struct.poly64x1x3_t, %struct.poly64x1x3_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX3:%.*]] = getelementptr inbounds [3 x <1 x i64>], [3 x <1 x i64>]* [[VAL2]], i64 0, i64 1
// CHECK: [[TMP5:%.*]] = load <1 x i64>, <1 x i64>* [[ARRAYIDX3]], align 8
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP6:%.*]] = bitcast <1 x i64> [[TMP5]] to <8 x i8>
// CHECK: [[VAL4:%.*]] = getelementptr inbounds %struct.poly64x1x3_t, %struct.poly64x1x3_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX5:%.*]] = getelementptr inbounds [3 x <1 x i64>], [3 x <1 x i64>]* [[VAL4]], i64 0, i64 2
// CHECK: [[TMP7:%.*]] = load <1 x i64>, <1 x i64>* [[ARRAYIDX5]], align 8
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP8:%.*]] = bitcast <1 x i64> [[TMP7]] to <8 x i8>
// CHECK: [[TMP9:%.*]] = bitcast <8 x i8> [[TMP4]] to <1 x i64>
// CHECK: [[TMP10:%.*]] = bitcast <8 x i8> [[TMP6]] to <1 x i64>
// CHECK: [[TMP11:%.*]] = bitcast <8 x i8> [[TMP8]] to <1 x i64>
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: call void @llvm.aarch64.neon.st3.v1i64.p0i8(<1 x i64> [[TMP9]], <1 x i64> [[TMP10]], <1 x i64> [[TMP11]], i8* [[TMP2]])
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: ret void
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
void test_vst3_p64(poly64_t * ptr, poly64x1x3_t val) {
return vst3_p64(ptr, val);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define void @test_vst3q_p64(i64* %ptr, [3 x <2 x i64>] %val.coerce) #2 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[VAL:%.*]] = alloca %struct.poly64x2x3_t, align 16
// CHECK: [[__S1:%.*]] = alloca %struct.poly64x2x3_t, align 16
// CHECK: [[COERCE_DIVE:%.*]] = getelementptr inbounds %struct.poly64x2x3_t, %struct.poly64x2x3_t* [[VAL]], i32 0, i32 0
// CHECK: store [3 x <2 x i64>] [[VAL]].coerce, [3 x <2 x i64>]* [[COERCE_DIVE]], align 16
// CHECK: [[TMP0:%.*]] = bitcast %struct.poly64x2x3_t* [[__S1]] to i8*
// CHECK: [[TMP1:%.*]] = bitcast %struct.poly64x2x3_t* [[VAL]] to i8*
Change memcpy/memove/memset to have dest and source alignment attributes (Step 1). Summary: Upstream LLVM is changing the the prototypes of the @llvm.memcpy/memmove/memset intrinsics. This change updates the Clang tests for this change. The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change removes the alignment argument in favour of placing the alignment attribute on the source and destination pointers of the memory intrinsic call. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) At this time the source and destination alignments must be the same (Step 1). Step 2 of the change, to be landed shortly, will relax that contraint and allow the source and destination to have different alignments. llvm-svn: 322964
2018-01-20 01:12:54 +08:00
// CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 [[TMP0]], i8* align 16 [[TMP1]], i64 48, i1 false)
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP2:%.*]] = bitcast i64* %ptr to i8*
// CHECK: [[VAL1:%.*]] = getelementptr inbounds %struct.poly64x2x3_t, %struct.poly64x2x3_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX:%.*]] = getelementptr inbounds [3 x <2 x i64>], [3 x <2 x i64>]* [[VAL1]], i64 0, i64 0
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP3:%.*]] = load <2 x i64>, <2 x i64>* [[ARRAYIDX]], align 16
// CHECK: [[TMP4:%.*]] = bitcast <2 x i64> [[TMP3]] to <16 x i8>
// CHECK: [[VAL2:%.*]] = getelementptr inbounds %struct.poly64x2x3_t, %struct.poly64x2x3_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX3:%.*]] = getelementptr inbounds [3 x <2 x i64>], [3 x <2 x i64>]* [[VAL2]], i64 0, i64 1
// CHECK: [[TMP5:%.*]] = load <2 x i64>, <2 x i64>* [[ARRAYIDX3]], align 16
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP6:%.*]] = bitcast <2 x i64> [[TMP5]] to <16 x i8>
// CHECK: [[VAL4:%.*]] = getelementptr inbounds %struct.poly64x2x3_t, %struct.poly64x2x3_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX5:%.*]] = getelementptr inbounds [3 x <2 x i64>], [3 x <2 x i64>]* [[VAL4]], i64 0, i64 2
// CHECK: [[TMP7:%.*]] = load <2 x i64>, <2 x i64>* [[ARRAYIDX5]], align 16
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP8:%.*]] = bitcast <2 x i64> [[TMP7]] to <16 x i8>
// CHECK: [[TMP9:%.*]] = bitcast <16 x i8> [[TMP4]] to <2 x i64>
// CHECK: [[TMP10:%.*]] = bitcast <16 x i8> [[TMP6]] to <2 x i64>
// CHECK: [[TMP11:%.*]] = bitcast <16 x i8> [[TMP8]] to <2 x i64>
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: call void @llvm.aarch64.neon.st3.v2i64.p0i8(<2 x i64> [[TMP9]], <2 x i64> [[TMP10]], <2 x i64> [[TMP11]], i8* [[TMP2]])
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: ret void
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
void test_vst3q_p64(poly64_t * ptr, poly64x2x3_t val) {
return vst3q_p64(ptr, val);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define void @test_vst4_p64(i64* %ptr, [4 x <1 x i64>] %val.coerce) #2 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[VAL:%.*]] = alloca %struct.poly64x1x4_t, align 8
// CHECK: [[__S1:%.*]] = alloca %struct.poly64x1x4_t, align 8
// CHECK: [[COERCE_DIVE:%.*]] = getelementptr inbounds %struct.poly64x1x4_t, %struct.poly64x1x4_t* [[VAL]], i32 0, i32 0
// CHECK: store [4 x <1 x i64>] [[VAL]].coerce, [4 x <1 x i64>]* [[COERCE_DIVE]], align 8
// CHECK: [[TMP0:%.*]] = bitcast %struct.poly64x1x4_t* [[__S1]] to i8*
// CHECK: [[TMP1:%.*]] = bitcast %struct.poly64x1x4_t* [[VAL]] to i8*
Change memcpy/memove/memset to have dest and source alignment attributes (Step 1). Summary: Upstream LLVM is changing the the prototypes of the @llvm.memcpy/memmove/memset intrinsics. This change updates the Clang tests for this change. The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change removes the alignment argument in favour of placing the alignment attribute on the source and destination pointers of the memory intrinsic call. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) At this time the source and destination alignments must be the same (Step 1). Step 2 of the change, to be landed shortly, will relax that contraint and allow the source and destination to have different alignments. llvm-svn: 322964
2018-01-20 01:12:54 +08:00
// CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP0]], i8* align 8 [[TMP1]], i64 32, i1 false)
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP2:%.*]] = bitcast i64* %ptr to i8*
// CHECK: [[VAL1:%.*]] = getelementptr inbounds %struct.poly64x1x4_t, %struct.poly64x1x4_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX:%.*]] = getelementptr inbounds [4 x <1 x i64>], [4 x <1 x i64>]* [[VAL1]], i64 0, i64 0
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP3:%.*]] = load <1 x i64>, <1 x i64>* [[ARRAYIDX]], align 8
// CHECK: [[TMP4:%.*]] = bitcast <1 x i64> [[TMP3]] to <8 x i8>
// CHECK: [[VAL2:%.*]] = getelementptr inbounds %struct.poly64x1x4_t, %struct.poly64x1x4_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX3:%.*]] = getelementptr inbounds [4 x <1 x i64>], [4 x <1 x i64>]* [[VAL2]], i64 0, i64 1
// CHECK: [[TMP5:%.*]] = load <1 x i64>, <1 x i64>* [[ARRAYIDX3]], align 8
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP6:%.*]] = bitcast <1 x i64> [[TMP5]] to <8 x i8>
// CHECK: [[VAL4:%.*]] = getelementptr inbounds %struct.poly64x1x4_t, %struct.poly64x1x4_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX5:%.*]] = getelementptr inbounds [4 x <1 x i64>], [4 x <1 x i64>]* [[VAL4]], i64 0, i64 2
// CHECK: [[TMP7:%.*]] = load <1 x i64>, <1 x i64>* [[ARRAYIDX5]], align 8
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP8:%.*]] = bitcast <1 x i64> [[TMP7]] to <8 x i8>
// CHECK: [[VAL6:%.*]] = getelementptr inbounds %struct.poly64x1x4_t, %struct.poly64x1x4_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX7:%.*]] = getelementptr inbounds [4 x <1 x i64>], [4 x <1 x i64>]* [[VAL6]], i64 0, i64 3
// CHECK: [[TMP9:%.*]] = load <1 x i64>, <1 x i64>* [[ARRAYIDX7]], align 8
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP10:%.*]] = bitcast <1 x i64> [[TMP9]] to <8 x i8>
// CHECK: [[TMP11:%.*]] = bitcast <8 x i8> [[TMP4]] to <1 x i64>
// CHECK: [[TMP12:%.*]] = bitcast <8 x i8> [[TMP6]] to <1 x i64>
// CHECK: [[TMP13:%.*]] = bitcast <8 x i8> [[TMP8]] to <1 x i64>
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[TMP14:%.*]] = bitcast <8 x i8> [[TMP10]] to <1 x i64>
// CHECK: call void @llvm.aarch64.neon.st4.v1i64.p0i8(<1 x i64> [[TMP11]], <1 x i64> [[TMP12]], <1 x i64> [[TMP13]], <1 x i64> [[TMP14]], i8* [[TMP2]])
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: ret void
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
void test_vst4_p64(poly64_t * ptr, poly64x1x4_t val) {
return vst4_p64(ptr, val);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define void @test_vst4q_p64(i64* %ptr, [4 x <2 x i64>] %val.coerce) #2 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[VAL:%.*]] = alloca %struct.poly64x2x4_t, align 16
// CHECK: [[__S1:%.*]] = alloca %struct.poly64x2x4_t, align 16
// CHECK: [[COERCE_DIVE:%.*]] = getelementptr inbounds %struct.poly64x2x4_t, %struct.poly64x2x4_t* [[VAL]], i32 0, i32 0
// CHECK: store [4 x <2 x i64>] [[VAL]].coerce, [4 x <2 x i64>]* [[COERCE_DIVE]], align 16
// CHECK: [[TMP0:%.*]] = bitcast %struct.poly64x2x4_t* [[__S1]] to i8*
// CHECK: [[TMP1:%.*]] = bitcast %struct.poly64x2x4_t* [[VAL]] to i8*
Change memcpy/memove/memset to have dest and source alignment attributes (Step 1). Summary: Upstream LLVM is changing the the prototypes of the @llvm.memcpy/memmove/memset intrinsics. This change updates the Clang tests for this change. The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change removes the alignment argument in favour of placing the alignment attribute on the source and destination pointers of the memory intrinsic call. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) At this time the source and destination alignments must be the same (Step 1). Step 2 of the change, to be landed shortly, will relax that contraint and allow the source and destination to have different alignments. llvm-svn: 322964
2018-01-20 01:12:54 +08:00
// CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 [[TMP0]], i8* align 16 [[TMP1]], i64 64, i1 false)
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP2:%.*]] = bitcast i64* %ptr to i8*
// CHECK: [[VAL1:%.*]] = getelementptr inbounds %struct.poly64x2x4_t, %struct.poly64x2x4_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX:%.*]] = getelementptr inbounds [4 x <2 x i64>], [4 x <2 x i64>]* [[VAL1]], i64 0, i64 0
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP3:%.*]] = load <2 x i64>, <2 x i64>* [[ARRAYIDX]], align 16
// CHECK: [[TMP4:%.*]] = bitcast <2 x i64> [[TMP3]] to <16 x i8>
// CHECK: [[VAL2:%.*]] = getelementptr inbounds %struct.poly64x2x4_t, %struct.poly64x2x4_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX3:%.*]] = getelementptr inbounds [4 x <2 x i64>], [4 x <2 x i64>]* [[VAL2]], i64 0, i64 1
// CHECK: [[TMP5:%.*]] = load <2 x i64>, <2 x i64>* [[ARRAYIDX3]], align 16
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP6:%.*]] = bitcast <2 x i64> [[TMP5]] to <16 x i8>
// CHECK: [[VAL4:%.*]] = getelementptr inbounds %struct.poly64x2x4_t, %struct.poly64x2x4_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX5:%.*]] = getelementptr inbounds [4 x <2 x i64>], [4 x <2 x i64>]* [[VAL4]], i64 0, i64 2
// CHECK: [[TMP7:%.*]] = load <2 x i64>, <2 x i64>* [[ARRAYIDX5]], align 16
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP8:%.*]] = bitcast <2 x i64> [[TMP7]] to <16 x i8>
// CHECK: [[VAL6:%.*]] = getelementptr inbounds %struct.poly64x2x4_t, %struct.poly64x2x4_t* [[__S1]], i32 0, i32 0
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[ARRAYIDX7:%.*]] = getelementptr inbounds [4 x <2 x i64>], [4 x <2 x i64>]* [[VAL6]], i64 0, i64 3
// CHECK: [[TMP9:%.*]] = load <2 x i64>, <2 x i64>* [[ARRAYIDX7]], align 16
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP10:%.*]] = bitcast <2 x i64> [[TMP9]] to <16 x i8>
// CHECK: [[TMP11:%.*]] = bitcast <16 x i8> [[TMP4]] to <2 x i64>
// CHECK: [[TMP12:%.*]] = bitcast <16 x i8> [[TMP6]] to <2 x i64>
// CHECK: [[TMP13:%.*]] = bitcast <16 x i8> [[TMP8]] to <2 x i64>
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[TMP14:%.*]] = bitcast <16 x i8> [[TMP10]] to <2 x i64>
// CHECK: call void @llvm.aarch64.neon.st4.v2i64.p0i8(<2 x i64> [[TMP11]], <2 x i64> [[TMP12]], <2 x i64> [[TMP13]], <2 x i64> [[TMP14]], i8* [[TMP2]])
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: ret void
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
void test_vst4q_p64(poly64_t * ptr, poly64x2x4_t val) {
return vst4q_p64(ptr, val);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <1 x i64> @test_vext_p64(<1 x i64> %a, <1 x i64> %b) #0 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP0:%.*]] = bitcast <1 x i64> %a to <8 x i8>
// CHECK: [[TMP1:%.*]] = bitcast <1 x i64> %b to <8 x i8>
// CHECK: [[TMP2:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x i64>
// CHECK: [[TMP3:%.*]] = bitcast <8 x i8> [[TMP1]] to <1 x i64>
// CHECK: [[VEXT:%.*]] = shufflevector <1 x i64> [[TMP2]], <1 x i64> [[TMP3]], <1 x i32> zeroinitializer
// CHECK: ret <1 x i64> [[VEXT]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x1_t test_vext_p64(poly64x1_t a, poly64x1_t b) {
return vext_u64(a, b, 0);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vextq_p64(<2 x i64> %a, <2 x i64> %b) #1 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP0:%.*]] = bitcast <2 x i64> %a to <16 x i8>
// CHECK: [[TMP1:%.*]] = bitcast <2 x i64> %b to <16 x i8>
// CHECK: [[TMP2:%.*]] = bitcast <16 x i8> [[TMP0]] to <2 x i64>
// CHECK: [[TMP3:%.*]] = bitcast <16 x i8> [[TMP1]] to <2 x i64>
// CHECK: [[VEXT:%.*]] = shufflevector <2 x i64> [[TMP2]], <2 x i64> [[TMP3]], <2 x i32> <i32 1, i32 2>
// CHECK: ret <2 x i64> [[VEXT]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2_t test_vextq_p64(poly64x2_t a, poly64x2_t b) {
return vextq_p64(a, b, 1);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vzip1q_p64(<2 x i64> %a, <2 x i64> %b) #1 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[SHUFFLE_I:%.*]] = shufflevector <2 x i64> %a, <2 x i64> %b, <2 x i32> <i32 0, i32 2>
// CHECK: ret <2 x i64> [[SHUFFLE_I]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2_t test_vzip1q_p64(poly64x2_t a, poly64x2_t b) {
return vzip1q_p64(a, b);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vzip2q_p64(<2 x i64> %a, <2 x i64> %b) #1 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[SHUFFLE_I:%.*]] = shufflevector <2 x i64> %a, <2 x i64> %b, <2 x i32> <i32 1, i32 3>
// CHECK: ret <2 x i64> [[SHUFFLE_I]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2_t test_vzip2q_p64(poly64x2_t a, poly64x2_t b) {
return vzip2q_u64(a, b);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vuzp1q_p64(<2 x i64> %a, <2 x i64> %b) #1 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[SHUFFLE_I:%.*]] = shufflevector <2 x i64> %a, <2 x i64> %b, <2 x i32> <i32 0, i32 2>
// CHECK: ret <2 x i64> [[SHUFFLE_I]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2_t test_vuzp1q_p64(poly64x2_t a, poly64x2_t b) {
return vuzp1q_p64(a, b);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vuzp2q_p64(<2 x i64> %a, <2 x i64> %b) #1 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[SHUFFLE_I:%.*]] = shufflevector <2 x i64> %a, <2 x i64> %b, <2 x i32> <i32 1, i32 3>
// CHECK: ret <2 x i64> [[SHUFFLE_I]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2_t test_vuzp2q_p64(poly64x2_t a, poly64x2_t b) {
return vuzp2q_u64(a, b);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vtrn1q_p64(<2 x i64> %a, <2 x i64> %b) #1 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[SHUFFLE_I:%.*]] = shufflevector <2 x i64> %a, <2 x i64> %b, <2 x i32> <i32 0, i32 2>
// CHECK: ret <2 x i64> [[SHUFFLE_I]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2_t test_vtrn1q_p64(poly64x2_t a, poly64x2_t b) {
return vtrn1q_p64(a, b);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vtrn2q_p64(<2 x i64> %a, <2 x i64> %b) #1 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[SHUFFLE_I:%.*]] = shufflevector <2 x i64> %a, <2 x i64> %b, <2 x i32> <i32 1, i32 3>
// CHECK: ret <2 x i64> [[SHUFFLE_I]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2_t test_vtrn2q_p64(poly64x2_t a, poly64x2_t b) {
return vtrn2q_u64(a, b);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <1 x i64> @test_vsri_n_p64(<1 x i64> %a, <1 x i64> %b) #0 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP0:%.*]] = bitcast <1 x i64> %a to <8 x i8>
// CHECK: [[TMP1:%.*]] = bitcast <1 x i64> %b to <8 x i8>
// CHECK: [[VSRI_N:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x i64>
// CHECK: [[VSRI_N1:%.*]] = bitcast <8 x i8> [[TMP1]] to <1 x i64>
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[VSRI_N2:%.*]] = call <1 x i64> @llvm.aarch64.neon.vsri.v1i64(<1 x i64> [[VSRI_N]], <1 x i64> [[VSRI_N1]], i32 33)
// CHECK: ret <1 x i64> [[VSRI_N2]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x1_t test_vsri_n_p64(poly64x1_t a, poly64x1_t b) {
return vsri_n_p64(a, b, 33);
}
Revert "[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition" This reverts commit 789a46f2d742e11edaade28cb59a0f4d2a1d770e. Accidentally committed.
2020-02-04 02:09:39 +08:00
// CHECK-LABEL: define <2 x i64> @test_vsriq_n_p64(<2 x i64> %a, <2 x i64> %b) #1 {
ARM & AArch64: convert asm tests to LLVM IR and restrict optimizations. This is mostly a one-time autoconversion of tests that checked assembly after "-Owhatever" compiles to only run "opt -mem2reg" and check the assembly. This should make them much more stable to changes in LLVM so they won't break on unrelated changes. "opt -mem2reg" is a compromise designed to increase the readability of tests that check dataflow, while minimizing dependency on LLVM. Hopefully mem2reg is stable enough that no surpises will come along. Should address http://llvm.org/PR26815. llvm-svn: 263048
2016-03-10 02:54:42 +08:00
// CHECK: [[TMP0:%.*]] = bitcast <2 x i64> %a to <16 x i8>
// CHECK: [[TMP1:%.*]] = bitcast <2 x i64> %b to <16 x i8>
// CHECK: [[VSRI_N:%.*]] = bitcast <16 x i8> [[TMP0]] to <2 x i64>
// CHECK: [[VSRI_N1:%.*]] = bitcast <16 x i8> [[TMP1]] to <2 x i64>
ARM & AArch64: fix IR-converted tests. My script was converting %a0 to [[A]]0 if it had seen %a defined before %a0. Oops. llvm-svn: 263056
2016-03-10 04:06:10 +08:00
// CHECK: [[VSRI_N2:%.*]] = call <2 x i64> @llvm.aarch64.neon.vsri.v2i64(<2 x i64> [[VSRI_N]], <2 x i64> [[VSRI_N1]], i32 64)
// CHECK: ret <2 x i64> [[VSRI_N2]]
Add test case for AArch64 NEON poly64 intrinsic. llvm-svn: 194674
2013-11-14 14:49:00 +08:00
poly64x2_t test_vsriq_n_p64(poly64x2_t a, poly64x2_t b) {
return vsriq_n_p64(a, b, 64);
}
[CodeGen] Update min-legal-vector width based on function argument and return types This is a continuation of my patches to inform the X86 backend about what the largest IR types are in the function so that we can restrict the backend type legalizer to prevent 512-bit vectors on SKX when -mprefer-vector-width=256 is specified if no explicit 512 bit vectors were specified by the user. This patch updates the vector width based on the argument and return types of the current function and from the types of any functions it calls. This is intended to make sure the backend type legalizer doesn't disturb any types that are required for ABI. Differential Revision: https://reviews.llvm.org/D52441 llvm-svn: 345168
2018-10-25 01:42:17 +08:00
// CHECK: attributes #0 ={{.*}}"min-legal-vector-width"="64"
// CHECK: attributes #1 ={{.*}}"min-legal-vector-width"="128"
[CodeGen] Always emit the 'min-legal-vector-width' attribute even when the value is 0. The X86 backend will need to see the attribute to make decisions. If it isn't present the backend will have to assume large vectors may be present. llvm-svn: 345237
2018-10-25 13:04:35 +08:00
// CHECK: attributes #2 ={{.*}}"min-legal-vector-width"="0"