maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/PowerPC/ppc64-i128-abi.ll

319 lines
11 KiB
LLVM
Raw Normal View History

[Power9] Add exploitation of non-permuting memory ops This patch corresponds to review: https://reviews.llvm.org/D19825 The new lxvx/stxvx instructions do not require the swaps to line the elements up correctly. In order to select them over the lxvd2x/lxvw4x instructions which require swaps, the patterns for the old instruction have a predicate that ensures they won't be selected on Power9 and newer CPUs. llvm-svn: 282143
2016-09-22 17:52:19 +08:00
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
[PowerPC] Emit VMX loads/stores for aligned ops to avoid adding swaps on LE Fixes PR30730. This is a re-commit of a pulled commit. The commit was pulled because some software projects contained uses of Altivec vectors that violated alignment requirements. Known issues have now been fixed. Committing on behalf of Lei Huang. Differential Revision: https://reviews.llvm.org/D26861 llvm-svn: 301892
2017-05-02 09:47:34 +08:00
; RUN: -mcpu=pwr8 < %s | FileCheck %s -check-prefix=CHECK-LE \
; RUN: --implicit-check-not xxswapd
[Power9] Add exploitation of non-permuting memory ops This patch corresponds to review: https://reviews.llvm.org/D19825 The new lxvx/stxvx instructions do not require the swaps to line the elements up correctly. In order to select them over the lxvd2x/lxvw4x instructions which require swaps, the patterns for the old instruction have a predicate that ensures they won't be selected on Power9 and newer CPUs. llvm-svn: 282143
2016-09-22 17:52:19 +08:00
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-linux-gnu \
; RUN: -mcpu=pwr8 < %s | FileCheck %s -check-prefix=CHECK-BE
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-linux-gnu \
; RUN: -mcpu=pwr8 -mattr=-vsx < %s | FileCheck %s -check-prefix=CHECK-NOVSX
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
[PowerPC] Emit VMX loads/stores for aligned ops to avoid adding swaps on LE Fixes PR30730. This is a re-commit of a pulled commit. The commit was pulled because some software projects contained uses of Altivec vectors that violated alignment requirements. Known issues have now been fixed. Committing on behalf of Lei Huang. Differential Revision: https://reviews.llvm.org/D26861 llvm-svn: 301892
2017-05-02 09:47:34 +08:00
; RUN: -mcpu=pwr8 -mattr=-vsx < %s | FileCheck %s -check-prefix=CHECK-NOVSX \
; RUN: --implicit-check-not xxswapd
[Power9] Add exploitation of non-permuting memory ops This patch corresponds to review: https://reviews.llvm.org/D19825 The new lxvx/stxvx instructions do not require the swaps to line the elements up correctly. In order to select them over the lxvd2x/lxvw4x instructions which require swaps, the patterns for the old instruction have a predicate that ensures they won't be selected on Power9 and newer CPUs. llvm-svn: 282143
2016-09-22 17:52:19 +08:00
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-linux-gnu \
; RUN: -mcpu=pwr8 -mattr=-vsx < %s | FileCheck %s -check-prefix=CHECK-BE-NOVSX
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
[PowerPC] Emit VMX loads/stores for aligned ops to avoid adding swaps on LE Fixes PR30730. This is a re-commit of a pulled commit. The commit was pulled because some software projects contained uses of Altivec vectors that violated alignment requirements. Known issues have now been fixed. Committing on behalf of Lei Huang. Differential Revision: https://reviews.llvm.org/D26861 llvm-svn: 301892
2017-05-02 09:47:34 +08:00
; RUN: -mcpu=pwr8 -mattr=-vsx < %s | \
; RUN: FileCheck %s -check-prefix=CHECK-LE-NOVSX --implicit-check-not xxswapd
[Power9] Add exploitation of non-permuting memory ops This patch corresponds to review: https://reviews.llvm.org/D19825 The new lxvx/stxvx instructions do not require the swaps to line the elements up correctly. In order to select them over the lxvd2x/lxvw4x instructions which require swaps, the patterns for the old instruction have a predicate that ensures they won't be selected on Power9 and newer CPUs. llvm-svn: 282143
2016-09-22 17:52:19 +08:00
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
[Power9] Exploit move and splat instructions for build_vector improvement This patch corresponds to review: https://reviews.llvm.org/D21135 This patch exploits the following instructions: mtvsrws lxvwsx mtvsrdd mfvsrld In order to improve some build_vector and extractelement patterns. llvm-svn: 282246
2016-09-23 21:25:31 +08:00
; RUN: -mcpu=pwr9 -ppc-vsr-nums-as-vr < %s | FileCheck %s \
; RUN: -check-prefix=CHECK-P9 --implicit-check-not xxswapd
[Power9] Add exploitation of non-permuting memory ops This patch corresponds to review: https://reviews.llvm.org/D19825 The new lxvx/stxvx instructions do not require the swaps to line the elements up correctly. In order to select them over the lxvd2x/lxvw4x instructions which require swaps, the patterns for the old instruction have a predicate that ensures they won't be selected on Power9 and newer CPUs. llvm-svn: 282143
2016-09-22 17:52:19 +08:00
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
; RUN: -mcpu=pwr9 -mattr=-vsx < %s | FileCheck %s -check-prefix=CHECK-NOVSX \
; RUN: --implicit-check-not xxswapd
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
[Power9] Exploit move and splat instructions for build_vector improvement This patch corresponds to review: https://reviews.llvm.org/D21135 This patch exploits the following instructions: mtvsrws lxvwsx mtvsrdd mfvsrld In order to improve some build_vector and extractelement patterns. llvm-svn: 282246
2016-09-23 21:25:31 +08:00
; RUN: -mcpu=pwr9 -mattr=-power9-vector -mattr=-direct-move < %s | \
[PowerPC] Emit VMX loads/stores for aligned ops to avoid adding swaps on LE Fixes PR30730. This is a re-commit of a pulled commit. The commit was pulled because some software projects contained uses of Altivec vectors that violated alignment requirements. Known issues have now been fixed. Committing on behalf of Lei Huang. Differential Revision: https://reviews.llvm.org/D26861 llvm-svn: 301892
2017-05-02 09:47:34 +08:00
; RUN: FileCheck %s -check-prefix=CHECK-LE --implicit-check-not xxswapd
This patch adds ABI support for v1i128 data type. It adds v1i128 to the appropriate register classes and checks parameter passing and return values. This is related to http://reviews.llvm.org/D9081, which will add instructions that exploit the v1i128 datatype. Phabricator review: http://reviews.llvm.org/D9475 llvm-svn: 236503
2015-05-06 00:10:44 +08:00
@x = common global <1 x i128> zeroinitializer, align 16
@y = common global <1 x i128> zeroinitializer, align 16
@a = common global i128 zeroinitializer, align 16
@b = common global i128 zeroinitializer, align 16
; VSX:
; %a is passed in register 34
This patch adds support for the vector quadword add/sub instructions introduced in POWER8: vadduqm vaddeuqm vaddcuq vaddecuq vsubuqm vsubeuqm vsubcuq vsubecuq In addition to adding the instructions themselves, it also adds support for the v1i128 type for intrinsics (Intrinsics.td, Function.cpp, and IntrinsicEmitter.cpp). http://reviews.llvm.org/D9081 llvm-svn: 238144
2015-05-25 23:49:26 +08:00
; The value of 1 is stored in the TOC.
; On LE, ensure the value of 1 is swapped before being used (using xxswapd).
This patch adds ABI support for v1i128 data type. It adds v1i128 to the appropriate register classes and checks parameter passing and return values. This is related to http://reviews.llvm.org/D9081, which will add instructions that exploit the v1i128 datatype. Phabricator review: http://reviews.llvm.org/D9475 llvm-svn: 236503
2015-05-06 00:10:44 +08:00
; VMX (no VSX):
; %a is passed in register 2
This patch adds support for the vector quadword add/sub instructions introduced in POWER8: vadduqm vaddeuqm vaddcuq vaddecuq vsubuqm vsubeuqm vsubcuq vsubecuq In addition to adding the instructions themselves, it also adds support for the v1i128 type for intrinsics (Intrinsics.td, Function.cpp, and IntrinsicEmitter.cpp). http://reviews.llvm.org/D9081 llvm-svn: 238144
2015-05-25 23:49:26 +08:00
; The value of 1 is stored in the TOC.
; No swaps are necessary when using P8 Vector instructions on LE
This patch adds ABI support for v1i128 data type. It adds v1i128 to the appropriate register classes and checks parameter passing and return values. This is related to http://reviews.llvm.org/D9081, which will add instructions that exploit the v1i128 datatype. Phabricator review: http://reviews.llvm.org/D9475 llvm-svn: 236503
2015-05-06 00:10:44 +08:00
define <1 x i128> @v1i128_increment_by_one(<1 x i128> %a) nounwind {
%tmp = add <1 x i128> %a, <i128 1>
ret <1 x i128> %tmp
This patch adds support for the vector quadword add/sub instructions introduced in POWER8: vadduqm vaddeuqm vaddcuq vaddecuq vsubuqm vsubeuqm vsubcuq vsubecuq In addition to adding the instructions themselves, it also adds support for the v1i128 type for intrinsics (Intrinsics.td, Function.cpp, and IntrinsicEmitter.cpp). http://reviews.llvm.org/D9081 llvm-svn: 238144
2015-05-25 23:49:26 +08:00
; FIXME: Seems a 128-bit literal is materialized by loading from the TOC. There
; should be a better way of doing this.
This patch adds ABI support for v1i128 data type. It adds v1i128 to the appropriate register classes and checks parameter passing and return values. This is related to http://reviews.llvm.org/D9081, which will add instructions that exploit the v1i128 datatype. Phabricator review: http://reviews.llvm.org/D9475 llvm-svn: 236503
2015-05-06 00:10:44 +08:00
; CHECK-LE-LABEL: @v1i128_increment_by_one
This patch adds support for the vector quadword add/sub instructions introduced in POWER8: vadduqm vaddeuqm vaddcuq vaddecuq vsubuqm vsubeuqm vsubcuq vsubecuq In addition to adding the instructions themselves, it also adds support for the v1i128 type for intrinsics (Intrinsics.td, Function.cpp, and IntrinsicEmitter.cpp). http://reviews.llvm.org/D9081 llvm-svn: 238144
2015-05-25 23:49:26 +08:00
; CHECK-LE: lxvd2x [[VAL:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}
; CHECK-LE: xxswapd 35, [[VAL]]
; CHECK-LE: vadduqm 2, 2, 3
This patch adds ABI support for v1i128 data type. It adds v1i128 to the appropriate register classes and checks parameter passing and return values. This is related to http://reviews.llvm.org/D9081, which will add instructions that exploit the v1i128 datatype. Phabricator review: http://reviews.llvm.org/D9475 llvm-svn: 236503
2015-05-06 00:10:44 +08:00
; CHECK-LE: blr
[Power9] Add exploitation of non-permuting memory ops This patch corresponds to review: https://reviews.llvm.org/D19825 The new lxvx/stxvx instructions do not require the swaps to line the elements up correctly. In order to select them over the lxvd2x/lxvw4x instructions which require swaps, the patterns for the old instruction have a predicate that ensures they won't be selected on Power9 and newer CPUs. llvm-svn: 282143
2016-09-22 17:52:19 +08:00
; CHECK-P9-LABEL: @v1i128_increment_by_one
[Power9] Part-word VSX integer scalar loads/stores and sign extend instructions This patch corresponds to review: https://reviews.llvm.org/D23155 This patch removes the VSHRC register class (based on D20310) and adds exploitation of the Power9 sub-word integer loads into VSX registers as well as vector sign extensions. The new instructions are useful for a few purposes: Int to Fp conversions of 1 or 2-byte values loaded from memory Building vectors of 1 or 2-byte integers with values loaded from memory Storing individual 1 or 2-byte elements from integer vectors This patch implements all of those uses. llvm-svn: 283190
2016-10-04 14:59:23 +08:00
; The below FIXME is due to the lowering for BUILD_VECTOR that will be fixed
; in a subsequent patch.
; FIXME: li [[R1:r[0-9]+]], 1
; FIXME: li [[R2:r[0-9]+]], 0
; FIXME: mtvsrdd [[V1:v[0-9]+]], [[R2]], [[R1]]
P9: D-form vector load/store. Differential Revision: https://reviews.llvm.org/D33248 llvm-svn: 303780
2017-05-25 01:50:37 +08:00
; CHECK-P9: lxv [[V1:v[0-9]+]]
[Power9] Exploit move and splat instructions for build_vector improvement This patch corresponds to review: https://reviews.llvm.org/D21135 This patch exploits the following instructions: mtvsrws lxvwsx mtvsrdd mfvsrld In order to improve some build_vector and extractelement patterns. llvm-svn: 282246
2016-09-23 21:25:31 +08:00
; CHECK-P9: vadduqm v2, v2, [[V1]]
[Power9] Add exploitation of non-permuting memory ops This patch corresponds to review: https://reviews.llvm.org/D19825 The new lxvx/stxvx instructions do not require the swaps to line the elements up correctly. In order to select them over the lxvd2x/lxvw4x instructions which require swaps, the patterns for the old instruction have a predicate that ensures they won't be selected on Power9 and newer CPUs. llvm-svn: 282143
2016-09-22 17:52:19 +08:00
; CHECK-P9: blr
This patch adds ABI support for v1i128 data type. It adds v1i128 to the appropriate register classes and checks parameter passing and return values. This is related to http://reviews.llvm.org/D9081, which will add instructions that exploit the v1i128 datatype. Phabricator review: http://reviews.llvm.org/D9475 llvm-svn: 236503
2015-05-06 00:10:44 +08:00
; CHECK-BE-LABEL: @v1i128_increment_by_one
This patch adds support for the vector quadword add/sub instructions introduced in POWER8: vadduqm vaddeuqm vaddcuq vaddecuq vsubuqm vsubeuqm vsubcuq vsubecuq In addition to adding the instructions themselves, it also adds support for the v1i128 type for intrinsics (Intrinsics.td, Function.cpp, and IntrinsicEmitter.cpp). http://reviews.llvm.org/D9081 llvm-svn: 238144
2015-05-25 23:49:26 +08:00
; CHECK-BE: lxvd2x 35, {{[0-9]+}}, {{[0-9]+}}
; CHECK-BE-NOT: xxswapd
; CHECK-BE: vadduqm 2, 2, 3
This patch adds ABI support for v1i128 data type. It adds v1i128 to the appropriate register classes and checks parameter passing and return values. This is related to http://reviews.llvm.org/D9081, which will add instructions that exploit the v1i128 datatype. Phabricator review: http://reviews.llvm.org/D9475 llvm-svn: 236503
2015-05-06 00:10:44 +08:00
; CHECK-BE-NOT: xxswapd 34, {{[0-9]+}}
; CHECK-BE: blr
; CHECK-NOVSX-LABEL: @v1i128_increment_by_one
; CHECK-NOVSX-NOT: xxswapd {{[0-9]+}}, {{[0-9]+}}
; CHECK-NOVSX-NOT: stxvd2x {{[0-9]+}}, {{[0-9]+}}, {{[0-9]+}}
This patch adds support for the vector quadword add/sub instructions introduced in POWER8: vadduqm vaddeuqm vaddcuq vaddecuq vsubuqm vsubeuqm vsubcuq vsubecuq In addition to adding the instructions themselves, it also adds support for the v1i128 type for intrinsics (Intrinsics.td, Function.cpp, and IntrinsicEmitter.cpp). http://reviews.llvm.org/D9081 llvm-svn: 238144
2015-05-25 23:49:26 +08:00
; CHECK-NOVSX: lvx [[VAL:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}
This patch adds ABI support for v1i128 data type. It adds v1i128 to the appropriate register classes and checks parameter passing and return values. This is related to http://reviews.llvm.org/D9081, which will add instructions that exploit the v1i128 datatype. Phabricator review: http://reviews.llvm.org/D9475 llvm-svn: 236503
2015-05-06 00:10:44 +08:00
; CHECK-NOVSX-NOT: lxvd2x {{[0-9]+}}, {{[0-9]+}}, {{[0-9]+}}
; CHECK-NOVSX-NOT: xxswapd {{[0-9]+}}, {{[0-9]+}}
This patch adds support for the vector quadword add/sub instructions introduced in POWER8: vadduqm vaddeuqm vaddcuq vaddecuq vsubuqm vsubeuqm vsubcuq vsubecuq In addition to adding the instructions themselves, it also adds support for the v1i128 type for intrinsics (Intrinsics.td, Function.cpp, and IntrinsicEmitter.cpp). http://reviews.llvm.org/D9081 llvm-svn: 238144
2015-05-25 23:49:26 +08:00
; CHECK-NOVSX: vadduqm 2, 2, [[VAL]]
This patch adds ABI support for v1i128 data type. It adds v1i128 to the appropriate register classes and checks parameter passing and return values. This is related to http://reviews.llvm.org/D9081, which will add instructions that exploit the v1i128 datatype. Phabricator review: http://reviews.llvm.org/D9475 llvm-svn: 236503
2015-05-06 00:10:44 +08:00
; CHECK-NOVSX: blr
}
; VSX:
; %a is passed in register 34
; %b is passed in register 35
This patch adds support for the vector quadword add/sub instructions introduced in POWER8: vadduqm vaddeuqm vaddcuq vaddecuq vsubuqm vsubeuqm vsubcuq vsubecuq In addition to adding the instructions themselves, it also adds support for the v1i128 type for intrinsics (Intrinsics.td, Function.cpp, and IntrinsicEmitter.cpp). http://reviews.llvm.org/D9081 llvm-svn: 238144
2015-05-25 23:49:26 +08:00
; No swaps are necessary when using P8 Vector instructions on LE
This patch adds ABI support for v1i128 data type. It adds v1i128 to the appropriate register classes and checks parameter passing and return values. This is related to http://reviews.llvm.org/D9081, which will add instructions that exploit the v1i128 datatype. Phabricator review: http://reviews.llvm.org/D9475 llvm-svn: 236503
2015-05-06 00:10:44 +08:00
; VMX (no VSX):
; %a is passewd in register 2
; %b is passed in register 3
; On LE, do not need to swap contents of 2 and 3 because the lvx/stvx
; instructions no not swap elements
define <1 x i128> @v1i128_increment_by_val(<1 x i128> %a, <1 x i128> %b) nounwind {
%tmp = add <1 x i128> %a, %b
ret <1 x i128> %tmp
; CHECK-LE-LABEL: @v1i128_increment_by_val
This patch adds support for the vector quadword add/sub instructions introduced in POWER8: vadduqm vaddeuqm vaddcuq vaddecuq vsubuqm vsubeuqm vsubcuq vsubecuq In addition to adding the instructions themselves, it also adds support for the v1i128 type for intrinsics (Intrinsics.td, Function.cpp, and IntrinsicEmitter.cpp). http://reviews.llvm.org/D9081 llvm-svn: 238144
2015-05-25 23:49:26 +08:00
; CHECK-LE-NOT: xxswapd
; CHECK-LE: adduqm 2, 2, 3
This patch adds ABI support for v1i128 data type. It adds v1i128 to the appropriate register classes and checks parameter passing and return values. This is related to http://reviews.llvm.org/D9081, which will add instructions that exploit the v1i128 datatype. Phabricator review: http://reviews.llvm.org/D9475 llvm-svn: 236503
2015-05-06 00:10:44 +08:00
; CHECK-LE: blr
; CHECK-BE-LABEL: @v1i128_increment_by_val
; CHECK-BE-NOT: xxswapd {{[0-9]+}}, 34
; CHECK-BE-NOT: xxswapd {{[0-9]+}}, 35
; CHECK-BE-NOT: xxswapd 34, [[RESULT]]
This patch adds support for the vector quadword add/sub instructions introduced in POWER8: vadduqm vaddeuqm vaddcuq vaddecuq vsubuqm vsubeuqm vsubcuq vsubecuq In addition to adding the instructions themselves, it also adds support for the v1i128 type for intrinsics (Intrinsics.td, Function.cpp, and IntrinsicEmitter.cpp). http://reviews.llvm.org/D9081 llvm-svn: 238144
2015-05-25 23:49:26 +08:00
; CHECK-BE: adduqm 2, 2, 3
This patch adds ABI support for v1i128 data type. It adds v1i128 to the appropriate register classes and checks parameter passing and return values. This is related to http://reviews.llvm.org/D9081, which will add instructions that exploit the v1i128 datatype. Phabricator review: http://reviews.llvm.org/D9475 llvm-svn: 236503
2015-05-06 00:10:44 +08:00
; CHECK-BE: blr
; CHECK-NOVSX-LABEL: @v1i128_increment_by_val
; CHECK-NOVSX-NOT: xxswapd 34, [[RESULT]]
This patch adds support for the vector quadword add/sub instructions introduced in POWER8: vadduqm vaddeuqm vaddcuq vaddecuq vsubuqm vsubeuqm vsubcuq vsubecuq In addition to adding the instructions themselves, it also adds support for the v1i128 type for intrinsics (Intrinsics.td, Function.cpp, and IntrinsicEmitter.cpp). http://reviews.llvm.org/D9081 llvm-svn: 238144
2015-05-25 23:49:26 +08:00
; CHECK-NOVSX: adduqm 2, 2, 3
This patch adds ABI support for v1i128 data type. It adds v1i128 to the appropriate register classes and checks parameter passing and return values. This is related to http://reviews.llvm.org/D9081, which will add instructions that exploit the v1i128 datatype. Phabricator review: http://reviews.llvm.org/D9475 llvm-svn: 236503
2015-05-06 00:10:44 +08:00
; CHECK-NOVSX: blr
}
; Little Endian (VSX and VMX):
; Lower 64-bits of %a are passed in register 3
; Upper 64-bits of %a are passed in register 4
; Increment lower 64-bits using addic (immediate value of 1)
; Increment upper 64-bits using add zero extended
; Results are placed in registers 3 and 4
; Big Endian (VSX and VMX)
; Lower 64-bits of %a are passed in register 4
; Upper 64-bits of %a are passed in register 3
; Increment lower 64-bits using addic (immediate value of 1)
; Increment upper 64-bits using add zero extended
; Results are placed in registers 3 and 4
define i128 @i128_increment_by_one(i128 %a) nounwind {
%tmp = add i128 %a, 1
ret i128 %tmp
; CHECK-LE-LABEL: @i128_increment_by_one
; CHECK-LE: addic 3, 3, 1
; CHECK-LE-NEXT: addze 4, 4
; CHECK-LE: blr
; CHECK-BE-LABEL: @i128_increment_by_one
; CHECK-BE: addic 4, 4, 1
; CHECK-BE-NEXT: addze 3, 3
; CHECK-BE: blr
; CHECK-LE-NOVSX-LABEL: @i128_increment_by_one
; CHECK-LE-NOVSX: addic 3, 3, 1
; CHECK-LE-NOVSX-NEXT: addze 4, 4
; CHECK-LE-NOVSX: blr
; CHECK-BE-NOVSX-LABEL: @i128_increment_by_one
; CHECK-BE-NOVSX: addic 4, 4, 1
; CHECK-BE-NOVSX-NEXT: addze 3, 3
; CHECK-BE-NOVSX: blr
}
; Little Endian (VSX and VMX):
; Lower 64-bits of %a are passed in register 3
; Upper 64-bits of %a are passed in register 4
; Lower 64-bits of %b are passed in register 5
; Upper 64-bits of %b are passed in register 6
; Add the lower 64-bits using addc on registers 3 and 5
; Add the upper 64-bits using adde on registers 4 and 6
; Registers 3 and 4 should hold the result
; Big Endian (VSX and VMX):
; Upper 64-bits of %a are passed in register 3
; Lower 64-bits of %a are passed in register 4
; Upper 64-bits of %b are passed in register 5
; Lower 64-bits of %b are passed in register 6
; Add the lower 64-bits using addc on registers 4 and 6
; Add the upper 64-bits using adde on registers 3 and 5
; Registers 3 and 4 should hold the result
define i128 @i128_increment_by_val(i128 %a, i128 %b) nounwind {
%tmp = add i128 %a, %b
ret i128 %tmp
; CHECK-LE-LABEL: @i128_increment_by_val
; CHECK-LE: addc 3, 3, 5
; CHECK-LE-NEXT: adde 4, 4, 6
; CHECK-LE: blr
; CHECK-BE-LABEL: @i128_increment_by_val
; CHECK-BE: addc 4, 4, 6
; CHECK-BE-NEXT: adde 3, 3, 5
; CHECK-BE: blr
; CHECK-LE-NOVSX-LABEL: @i128_increment_by_val
; CHECK-LE-NOVSX: addc 3, 3, 5
; CHECK-LE-NOVSX-NEXT: adde 4, 4, 6
; CHECK-LE-NOVSX: blr
; CHECK-BE-NOVSX-LABEL: @i128_increment_by_val
; CHECK-BE-NOVSX: addc 4, 4, 6
; CHECK-BE-NOVSX-NEXT: adde 3, 3, 5
; CHECK-BE-NOVSX: blr
}
; Callsites for the routines defined above.
; Ensure the parameters are loaded in the same order that is expected by the
; callee. See comments for individual functions above for details on registers
; used for parameters.
define <1 x i128> @call_v1i128_increment_by_one() nounwind {
%tmp = load <1 x i128>, <1 x i128>* @x, align 16
%ret = call <1 x i128> @v1i128_increment_by_one(<1 x i128> %tmp)
ret <1 x i128> %ret
; CHECK-LE-LABEL: @call_v1i128_increment_by_one
[PowerPC] Emit VMX loads/stores for aligned ops to avoid adding swaps on LE Fixes PR30730. This is a re-commit of a pulled commit. The commit was pulled because some software projects contained uses of Altivec vectors that violated alignment requirements. Known issues have now been fixed. Committing on behalf of Lei Huang. Differential Revision: https://reviews.llvm.org/D26861 llvm-svn: 301892
2017-05-02 09:47:34 +08:00
; CHECK-LE: lvx 2, {{[0-9]+}}, {{[0-9]+}}
This patch adds ABI support for v1i128 data type. It adds v1i128 to the appropriate register classes and checks parameter passing and return values. This is related to http://reviews.llvm.org/D9081, which will add instructions that exploit the v1i128 datatype. Phabricator review: http://reviews.llvm.org/D9475 llvm-svn: 236503
2015-05-06 00:10:44 +08:00
; CHECK-LE: bl v1i128_increment_by_one
; CHECK-LE: blr
[Power9] Add exploitation of non-permuting memory ops This patch corresponds to review: https://reviews.llvm.org/D19825 The new lxvx/stxvx instructions do not require the swaps to line the elements up correctly. In order to select them over the lxvd2x/lxvw4x instructions which require swaps, the patterns for the old instruction have a predicate that ensures they won't be selected on Power9 and newer CPUs. llvm-svn: 282143
2016-09-22 17:52:19 +08:00
; CHECK-P9-LABEL: @call_v1i128_increment_by_one
P9: D-form vector load/store. Differential Revision: https://reviews.llvm.org/D33248 llvm-svn: 303780
2017-05-25 01:50:37 +08:00
; CHECK-P9: lxv
[Power9] Add exploitation of non-permuting memory ops This patch corresponds to review: https://reviews.llvm.org/D19825 The new lxvx/stxvx instructions do not require the swaps to line the elements up correctly. In order to select them over the lxvd2x/lxvw4x instructions which require swaps, the patterns for the old instruction have a predicate that ensures they won't be selected on Power9 and newer CPUs. llvm-svn: 282143
2016-09-22 17:52:19 +08:00
; CHECK-P9: bl v1i128_increment_by_one
; CHECK-P9: blr
This patch adds ABI support for v1i128 data type. It adds v1i128 to the appropriate register classes and checks parameter passing and return values. This is related to http://reviews.llvm.org/D9081, which will add instructions that exploit the v1i128 datatype. Phabricator review: http://reviews.llvm.org/D9475 llvm-svn: 236503
2015-05-06 00:10:44 +08:00
; CHECK-BE-LABEL: @call_v1i128_increment_by_one
; CHECK-BE: lxvw4x 34, {{[0-9]+}}, {{[0-9]+}}
; CHECK-BE-NOT: xxswapd 34, {{[0-9]+}}
; CHECK-BE: bl v1i128_increment_by_one
; CHECK-BE: blr
; CHECK-NOVSX-LABEL: @call_v1i128_increment_by_one
; CHECK-NOVSX: lvx 2, {{[0-9]+}}, {{[0-9]+}}
; CHECK-NOVSX-NOT: xxswapd {{[0-9]+}}, {{[0-9]+}}
; CHECK-NOVSX: bl v1i128_increment_by_one
; CHECK-NOVSX: blr
}
define <1 x i128> @call_v1i128_increment_by_val() nounwind {
%tmp = load <1 x i128>, <1 x i128>* @x, align 16
%tmp2 = load <1 x i128>, <1 x i128>* @y, align 16
%ret = call <1 x i128> @v1i128_increment_by_val(<1 x i128> %tmp, <1 x i128> %tmp2)
ret <1 x i128> %ret
; CHECK-LE-LABEL: @call_v1i128_increment_by_val
[PowerPC] Emit VMX loads/stores for aligned ops to avoid adding swaps on LE Fixes PR30730. This is a re-commit of a pulled commit. The commit was pulled because some software projects contained uses of Altivec vectors that violated alignment requirements. Known issues have now been fixed. Committing on behalf of Lei Huang. Differential Revision: https://reviews.llvm.org/D26861 llvm-svn: 301892
2017-05-02 09:47:34 +08:00
; CHECK-LE: lvx 2, {{[0-9]+}}, {{[0-9]+}}
; CHECK-LE: lvx 3, {{[0-9]+}}, {{[0-9]+}}
This patch adds ABI support for v1i128 data type. It adds v1i128 to the appropriate register classes and checks parameter passing and return values. This is related to http://reviews.llvm.org/D9081, which will add instructions that exploit the v1i128 datatype. Phabricator review: http://reviews.llvm.org/D9475 llvm-svn: 236503
2015-05-06 00:10:44 +08:00
; CHECK-LE: bl v1i128_increment_by_val
; CHECK-LE: blr
[Power9] Add exploitation of non-permuting memory ops This patch corresponds to review: https://reviews.llvm.org/D19825 The new lxvx/stxvx instructions do not require the swaps to line the elements up correctly. In order to select them over the lxvd2x/lxvw4x instructions which require swaps, the patterns for the old instruction have a predicate that ensures they won't be selected on Power9 and newer CPUs. llvm-svn: 282143
2016-09-22 17:52:19 +08:00
; CHECK-P9-LABEL: @call_v1i128_increment_by_val
P9: D-form vector load/store. Differential Revision: https://reviews.llvm.org/D33248 llvm-svn: 303780
2017-05-25 01:50:37 +08:00
; CHECK-P9-DAG: lxv v2
; CHECK-P9-DAG: lxv v3
[Power9] Add exploitation of non-permuting memory ops This patch corresponds to review: https://reviews.llvm.org/D19825 The new lxvx/stxvx instructions do not require the swaps to line the elements up correctly. In order to select them over the lxvd2x/lxvw4x instructions which require swaps, the patterns for the old instruction have a predicate that ensures they won't be selected on Power9 and newer CPUs. llvm-svn: 282143
2016-09-22 17:52:19 +08:00
; CHECK-P9: bl v1i128_increment_by_val
; CHECK-P9: blr
This patch adds ABI support for v1i128 data type. It adds v1i128 to the appropriate register classes and checks parameter passing and return values. This is related to http://reviews.llvm.org/D9081, which will add instructions that exploit the v1i128 datatype. Phabricator review: http://reviews.llvm.org/D9475 llvm-svn: 236503
2015-05-06 00:10:44 +08:00
; CHECK-BE-LABEL: @call_v1i128_increment_by_val
; CHECK-BE-DAG: lxvw4x 35, {{[0-9]+}}, {{[0-9]+}}
; CHECK-BE-NOT: xxswapd 34, {{[0-9]+}}
; CHECK-BE-NOT: xxswapd 35, {{[0-9]+}}
; CHECK-BE: bl v1i128_increment_by_val
; CHECK-BE: blr
; CHECK-NOVSX-LABEL: @call_v1i128_increment_by_val
; CHECK-NOVSX-DAG: lvx 2, {{[0-9]+}}, {{[0-9]+}}
; CHECK-NOVSX-DAG: lvx 3, {{[0-9]+}}, {{[0-9]+}}
; CHECK-NOVSX-NOT: xxswapd 34, {{[0-9]+}}
; CHECK-NOVSX-NOT: xxswapd 35, {{[0-9]+}}
; CHECK-NOVSX: bl v1i128_increment_by_val
; CHECK-NOVSX: blr
}
define i128 @call_i128_increment_by_one() nounwind {
%tmp = load i128, i128* @a, align 16
%ret = call i128 @i128_increment_by_one(i128 %tmp)
ret i128 %ret
; %ret4 = call i128 @i128_increment_by_val(i128 %tmp2, i128 %tmp2)
; CHECK-LE-LABEL: @call_i128_increment_by_one
; CHECK-LE-DAG: ld 3, 0([[BASEREG:[0-9]+]])
; CHECK-LE-DAG: ld 4, 8([[BASEREG]])
; CHECK-LE: bl i128_increment_by_one
; CHECK-LE: blr
; CHECK-BE-LABEL: @call_i128_increment_by_one
; CHECK-BE-DAG: ld 3, 0([[BASEREG:[0-9]+]])
; CHECK-BE-DAG: ld 4, 8([[BASEREG]])
; CHECK-BE: bl i128_increment_by_one
; CHECK-BE: blr
; CHECK-NOVSX-LABEL: @call_i128_increment_by_one
; CHECK-NOVSX-DAG: ld 3, 0([[BASEREG:[0-9]+]])
; CHECK-NOVSX-DAG: ld 4, 8([[BASEREG]])
; CHECK-NOVSX: bl i128_increment_by_one
; CHECK-NOVSX: blr
}
define i128 @call_i128_increment_by_val() nounwind {
%tmp = load i128, i128* @a, align 16
%tmp2 = load i128, i128* @b, align 16
%ret = call i128 @i128_increment_by_val(i128 %tmp, i128 %tmp2)
ret i128 %ret
; CHECK-LE-LABEL: @call_i128_increment_by_val
; CHECK-LE-DAG: ld 3, 0([[P1BASEREG:[0-9]+]])
; CHECK-LE-DAG: ld 4, 8([[P1BASEREG]])
; CHECK-LE-DAG: ld 5, 0([[P2BASEREG:[0-9]+]])
; CHECK-LE-DAG: ld 6, 8([[P2BASEREG]])
; CHECK-LE: bl i128_increment_by_val
; CHECK-LE: blr
; CHECK-BE-LABEL: @call_i128_increment_by_val
; CHECK-BE-DAG: ld 3, 0([[P1BASEREG:[0-9]+]])
; CHECK-BE-DAG: ld 4, 8([[P1BASEREG]])
; CHECK-BE-DAG: ld 5, 0([[P2BASEREG:[0-9]+]])
; CHECK-BE-DAG: ld 6, 8([[P2BASEREG]])
; CHECK-BE: bl i128_increment_by_val
; CHECK-BE: blr
; CHECK-NOVSX-LABEL: @call_i128_increment_by_val
; CHECK-NOVSX-DAG: ld 3, 0([[P1BASEREG:[0-9]+]])
; CHECK-NOVSX-DAG: ld 4, 8([[P1BASEREG]])
; CHECK-NOVSX-DAG: ld 5, 0([[P2BASEREG:[0-9]+]])
; CHECK-NOVSX-DAG: ld 6, 8([[P2BASEREG]])
; CHECK-NOVSX: bl i128_increment_by_val
; CHECK-NOVSX: blr
}