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/Mips/msa/basic_operations_float.ll

353 lines
11 KiB
LLVM
Raw Normal View History

[mips] Use --check-prefixes where appropriate. NFC. llvm-svn: 273669
2016-06-24 20:23:17 +08:00
; RUN: llc -march=mips -mattr=+msa,+fp64 -relocation-model=pic < %s | FileCheck -check-prefixes=ALL,O32 %s
; RUN: llc -march=mipsel -mattr=+msa,+fp64 -relocation-model=pic < %s | FileCheck -check-prefixes=ALL,O32 %s
; RUN: llc -march=mips64 -target-abi=n32 -mattr=+msa,+fp64 -relocation-model=pic < %s | FileCheck -check-prefixes=ALL,N32 %s
; RUN: llc -march=mips64el -target-abi=n32 -mattr=+msa,+fp64 -relocation-model=pic < %s | FileCheck -check-prefixes=ALL,N32 %s
; RUN: llc -march=mips64 -mattr=+msa,+fp64 -relocation-model=pic < %s | FileCheck -check-prefixes=ALL,N64 %s
; RUN: llc -march=mips64el -mattr=+msa,+fp64 -relocation-model=pic < %s | FileCheck -check-prefixes=ALL,N64 %s
[mips][msa] Implemented build_vector using ldi, fill, and custom SelectionDAG nodes (VSPLAT and VSPLATD) Note: There's a later patch on my branch that re-implements this to select build_vector without the custom SelectionDAG nodes. The future patch avoids the constant-folding problems stemming from the custom node (i.e. it doesn't need to re-implement all the DAG combines related to BUILD_VECTOR). Changes to MIPS specific SelectionDAG nodes: * Added VSPLAT This is a special case of BUILD_VECTOR that covers the case the BUILD_VECTOR is a splat operation. * Added VSPLATD This is a special case of VSPLAT that handles the cases when v2i64 is legal llvm-svn: 191191
2013-09-23 20:02:46 +08:00
@v4f32 = global <4 x float> <float 0.0, float 0.0, float 0.0, float 0.0>
@v2f64 = global <2 x double> <double 0.0, double 0.0>
[mips][msa] Fix element extraction where the index is variable. Summary: This isn't supported directly so we splat the vector element and extract the most convenient copy. Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3530 llvm-svn: 207524
2014-04-29 21:31:37 +08:00
@i32 = global i32 0
[mips][msa] Added support for build_vector for v4f32 and v2f64. llvm-svn: 192699
2013-10-15 21:14:41 +08:00
@f32 = global float 0.0
@f64 = global double 0.0
[mips][msa] Implemented build_vector using ldi, fill, and custom SelectionDAG nodes (VSPLAT and VSPLATD) Note: There's a later patch on my branch that re-implements this to select build_vector without the custom SelectionDAG nodes. The future patch avoids the constant-folding problems stemming from the custom node (i.e. it doesn't need to re-implement all the DAG combines related to BUILD_VECTOR). Changes to MIPS specific SelectionDAG nodes: * Added VSPLAT This is a special case of BUILD_VECTOR that covers the case the BUILD_VECTOR is a splat operation. * Added VSPLATD This is a special case of VSPLAT that handles the cases when v2i64 is legal llvm-svn: 191191
2013-09-23 20:02:46 +08:00
define void @const_v4f32() nounwind {
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-LABEL: const_v4f32:
[mips][msa] Implemented build_vector using ldi, fill, and custom SelectionDAG nodes (VSPLAT and VSPLATD) Note: There's a later patch on my branch that re-implements this to select build_vector without the custom SelectionDAG nodes. The future patch avoids the constant-folding problems stemming from the custom node (i.e. it doesn't need to re-implement all the DAG combines related to BUILD_VECTOR). Changes to MIPS specific SelectionDAG nodes: * Added VSPLAT This is a special case of BUILD_VECTOR that covers the case the BUILD_VECTOR is a splat operation. * Added VSPLATD This is a special case of VSPLAT that handles the cases when v2i64 is legal llvm-svn: 191191
2013-09-23 20:02:46 +08:00
store volatile <4 x float> <float 0.0, float 0.0, float 0.0, float 0.0>, <4 x float>*@v4f32
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL: ldi.b [[R1:\$w[0-9]+]], 0
[mips][msa] Implemented build_vector using ldi, fill, and custom SelectionDAG nodes (VSPLAT and VSPLATD) Note: There's a later patch on my branch that re-implements this to select build_vector without the custom SelectionDAG nodes. The future patch avoids the constant-folding problems stemming from the custom node (i.e. it doesn't need to re-implement all the DAG combines related to BUILD_VECTOR). Changes to MIPS specific SelectionDAG nodes: * Added VSPLAT This is a special case of BUILD_VECTOR that covers the case the BUILD_VECTOR is a splat operation. * Added VSPLATD This is a special case of VSPLAT that handles the cases when v2i64 is legal llvm-svn: 191191
2013-09-23 20:02:46 +08:00
store volatile <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, <4 x float>*@v4f32
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL: lui [[R1:\$[0-9]+]], 16256
; ALL: fill.w [[R2:\$w[0-9]+]], [[R1]]
[mips][msa] Implemented build_vector using ldi, fill, and custom SelectionDAG nodes (VSPLAT and VSPLATD) Note: There's a later patch on my branch that re-implements this to select build_vector without the custom SelectionDAG nodes. The future patch avoids the constant-folding problems stemming from the custom node (i.e. it doesn't need to re-implement all the DAG combines related to BUILD_VECTOR). Changes to MIPS specific SelectionDAG nodes: * Added VSPLAT This is a special case of BUILD_VECTOR that covers the case the BUILD_VECTOR is a splat operation. * Added VSPLATD This is a special case of VSPLAT that handles the cases when v2i64 is legal llvm-svn: 191191
2013-09-23 20:02:46 +08:00
store volatile <4 x float> <float 1.0, float 1.0, float 1.0, float 31.0>, <4 x float>*@v4f32
[mips][msa] Test basic operations for the N32 ABI too. Summary: This required adding instruction aliases for dneg. N64 will be enabled shortly but requires additional bugfixes. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9341 llvm-svn: 236489
2015-05-05 16:48:35 +08:00
; O32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %lo($
[mips] Correct label prefixes for N32 and N64. Summary: N32 and N64 follow the standard ELF conventions (.L) whereas O32 uses its own ($). This fixes the majority of object differences between -fintegrated-as and -fno-integrated-as. Reviewers: sdardis Subscribers: dsanders, sdardis, llvm-commits Differential Revision: https://reviews.llvm.org/D22412 llvm-svn: 275967
2016-07-19 18:49:03 +08:00
; N32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
; N64: daddiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL: ld.w [[R1:\$w[0-9]+]], 0([[G_PTR]])
[mips][msa] Implemented build_vector using ldi, fill, and custom SelectionDAG nodes (VSPLAT and VSPLATD) Note: There's a later patch on my branch that re-implements this to select build_vector without the custom SelectionDAG nodes. The future patch avoids the constant-folding problems stemming from the custom node (i.e. it doesn't need to re-implement all the DAG combines related to BUILD_VECTOR). Changes to MIPS specific SelectionDAG nodes: * Added VSPLAT This is a special case of BUILD_VECTOR that covers the case the BUILD_VECTOR is a splat operation. * Added VSPLATD This is a special case of VSPLAT that handles the cases when v2i64 is legal llvm-svn: 191191
2013-09-23 20:02:46 +08:00
store volatile <4 x float> <float 65537.0, float 65537.0, float 65537.0, float 65537.0>, <4 x float>*@v4f32
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL: lui [[R1:\$[0-9]+]], 18304
; ALL: ori [[R2:\$[0-9]+]], [[R1]], 128
; ALL: fill.w [[R3:\$w[0-9]+]], [[R2]]
[mips][msa] Implemented build_vector using ldi, fill, and custom SelectionDAG nodes (VSPLAT and VSPLATD) Note: There's a later patch on my branch that re-implements this to select build_vector without the custom SelectionDAG nodes. The future patch avoids the constant-folding problems stemming from the custom node (i.e. it doesn't need to re-implement all the DAG combines related to BUILD_VECTOR). Changes to MIPS specific SelectionDAG nodes: * Added VSPLAT This is a special case of BUILD_VECTOR that covers the case the BUILD_VECTOR is a splat operation. * Added VSPLATD This is a special case of VSPLAT that handles the cases when v2i64 is legal llvm-svn: 191191
2013-09-23 20:02:46 +08:00
store volatile <4 x float> <float 1.0, float 2.0, float 1.0, float 2.0>, <4 x float>*@v4f32
[mips][msa] Test basic operations for the N32 ABI too. Summary: This required adding instruction aliases for dneg. N64 will be enabled shortly but requires additional bugfixes. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9341 llvm-svn: 236489
2015-05-05 16:48:35 +08:00
; O32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %lo($
[mips] Correct label prefixes for N32 and N64. Summary: N32 and N64 follow the standard ELF conventions (.L) whereas O32 uses its own ($). This fixes the majority of object differences between -fintegrated-as and -fno-integrated-as. Reviewers: sdardis Subscribers: dsanders, sdardis, llvm-commits Differential Revision: https://reviews.llvm.org/D22412 llvm-svn: 275967
2016-07-19 18:49:03 +08:00
; N32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
; N64: daddiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL: ld.w [[R1:\$w[0-9]+]], 0([[G_PTR]])
[mips][msa] Implemented build_vector using ldi, fill, and custom SelectionDAG nodes (VSPLAT and VSPLATD) Note: There's a later patch on my branch that re-implements this to select build_vector without the custom SelectionDAG nodes. The future patch avoids the constant-folding problems stemming from the custom node (i.e. it doesn't need to re-implement all the DAG combines related to BUILD_VECTOR). Changes to MIPS specific SelectionDAG nodes: * Added VSPLAT This is a special case of BUILD_VECTOR that covers the case the BUILD_VECTOR is a splat operation. * Added VSPLATD This is a special case of VSPLAT that handles the cases when v2i64 is legal llvm-svn: 191191
2013-09-23 20:02:46 +08:00
store volatile <4 x float> <float 3.0, float 4.0, float 5.0, float 6.0>, <4 x float>*@v4f32
[mips][msa] Test basic operations for the N32 ABI too. Summary: This required adding instruction aliases for dneg. N64 will be enabled shortly but requires additional bugfixes. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9341 llvm-svn: 236489
2015-05-05 16:48:35 +08:00
; O32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %lo($
[mips] Correct label prefixes for N32 and N64. Summary: N32 and N64 follow the standard ELF conventions (.L) whereas O32 uses its own ($). This fixes the majority of object differences between -fintegrated-as and -fno-integrated-as. Reviewers: sdardis Subscribers: dsanders, sdardis, llvm-commits Differential Revision: https://reviews.llvm.org/D22412 llvm-svn: 275967
2016-07-19 18:49:03 +08:00
; N32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
; N64: daddiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL: ld.w [[R1:\$w[0-9]+]], 0([[G_PTR]])
[mips][msa] Implemented build_vector using ldi, fill, and custom SelectionDAG nodes (VSPLAT and VSPLATD) Note: There's a later patch on my branch that re-implements this to select build_vector without the custom SelectionDAG nodes. The future patch avoids the constant-folding problems stemming from the custom node (i.e. it doesn't need to re-implement all the DAG combines related to BUILD_VECTOR). Changes to MIPS specific SelectionDAG nodes: * Added VSPLAT This is a special case of BUILD_VECTOR that covers the case the BUILD_VECTOR is a splat operation. * Added VSPLATD This is a special case of VSPLAT that handles the cases when v2i64 is legal llvm-svn: 191191
2013-09-23 20:02:46 +08:00
ret void
}
define void @const_v2f64() nounwind {
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-LABEL: const_v2f64:
[mips][msa] Implemented build_vector using ldi, fill, and custom SelectionDAG nodes (VSPLAT and VSPLATD) Note: There's a later patch on my branch that re-implements this to select build_vector without the custom SelectionDAG nodes. The future patch avoids the constant-folding problems stemming from the custom node (i.e. it doesn't need to re-implement all the DAG combines related to BUILD_VECTOR). Changes to MIPS specific SelectionDAG nodes: * Added VSPLAT This is a special case of BUILD_VECTOR that covers the case the BUILD_VECTOR is a splat operation. * Added VSPLATD This is a special case of VSPLAT that handles the cases when v2i64 is legal llvm-svn: 191191
2013-09-23 20:02:46 +08:00
store volatile <2 x double> <double 0.0, double 0.0>, <2 x double>*@v2f64
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL: ldi.b [[R1:\$w[0-9]+]], 0
[mips][msa] Implemented build_vector using ldi, fill, and custom SelectionDAG nodes (VSPLAT and VSPLATD) Note: There's a later patch on my branch that re-implements this to select build_vector without the custom SelectionDAG nodes. The future patch avoids the constant-folding problems stemming from the custom node (i.e. it doesn't need to re-implement all the DAG combines related to BUILD_VECTOR). Changes to MIPS specific SelectionDAG nodes: * Added VSPLAT This is a special case of BUILD_VECTOR that covers the case the BUILD_VECTOR is a splat operation. * Added VSPLATD This is a special case of VSPLAT that handles the cases when v2i64 is legal llvm-svn: 191191
2013-09-23 20:02:46 +08:00
store volatile <2 x double> <double 72340172838076673.0, double 72340172838076673.0>, <2 x double>*@v2f64
[mips][msa] Test basic operations for the N32 ABI too. Summary: This required adding instruction aliases for dneg. N64 will be enabled shortly but requires additional bugfixes. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9341 llvm-svn: 236489
2015-05-05 16:48:35 +08:00
; O32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %lo($
[mips] Correct label prefixes for N32 and N64. Summary: N32 and N64 follow the standard ELF conventions (.L) whereas O32 uses its own ($). This fixes the majority of object differences between -fintegrated-as and -fno-integrated-as. Reviewers: sdardis Subscribers: dsanders, sdardis, llvm-commits Differential Revision: https://reviews.llvm.org/D22412 llvm-svn: 275967
2016-07-19 18:49:03 +08:00
; N32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
; N64: daddiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL: ld.d [[R1:\$w[0-9]+]], 0([[G_PTR]])
[mips][msa] Implemented build_vector using ldi, fill, and custom SelectionDAG nodes (VSPLAT and VSPLATD) Note: There's a later patch on my branch that re-implements this to select build_vector without the custom SelectionDAG nodes. The future patch avoids the constant-folding problems stemming from the custom node (i.e. it doesn't need to re-implement all the DAG combines related to BUILD_VECTOR). Changes to MIPS specific SelectionDAG nodes: * Added VSPLAT This is a special case of BUILD_VECTOR that covers the case the BUILD_VECTOR is a splat operation. * Added VSPLATD This is a special case of VSPLAT that handles the cases when v2i64 is legal llvm-svn: 191191
2013-09-23 20:02:46 +08:00
store volatile <2 x double> <double 281479271743489.0, double 281479271743489.0>, <2 x double>*@v2f64
[mips][msa] Test basic operations for the N32 ABI too. Summary: This required adding instruction aliases for dneg. N64 will be enabled shortly but requires additional bugfixes. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9341 llvm-svn: 236489
2015-05-05 16:48:35 +08:00
; O32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %lo($
[mips] Correct label prefixes for N32 and N64. Summary: N32 and N64 follow the standard ELF conventions (.L) whereas O32 uses its own ($). This fixes the majority of object differences between -fintegrated-as and -fno-integrated-as. Reviewers: sdardis Subscribers: dsanders, sdardis, llvm-commits Differential Revision: https://reviews.llvm.org/D22412 llvm-svn: 275967
2016-07-19 18:49:03 +08:00
; N32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
; N64: daddiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL: ld.d [[R1:\$w[0-9]+]], 0([[G_PTR]])
[mips][msa] Implemented build_vector using ldi, fill, and custom SelectionDAG nodes (VSPLAT and VSPLATD) Note: There's a later patch on my branch that re-implements this to select build_vector without the custom SelectionDAG nodes. The future patch avoids the constant-folding problems stemming from the custom node (i.e. it doesn't need to re-implement all the DAG combines related to BUILD_VECTOR). Changes to MIPS specific SelectionDAG nodes: * Added VSPLAT This is a special case of BUILD_VECTOR that covers the case the BUILD_VECTOR is a splat operation. * Added VSPLATD This is a special case of VSPLAT that handles the cases when v2i64 is legal llvm-svn: 191191
2013-09-23 20:02:46 +08:00
store volatile <2 x double> <double 4294967297.0, double 4294967297.0>, <2 x double>*@v2f64
[mips][msa] Test basic operations for the N32 ABI too. Summary: This required adding instruction aliases for dneg. N64 will be enabled shortly but requires additional bugfixes. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9341 llvm-svn: 236489
2015-05-05 16:48:35 +08:00
; O32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %lo($
[mips] Correct label prefixes for N32 and N64. Summary: N32 and N64 follow the standard ELF conventions (.L) whereas O32 uses its own ($). This fixes the majority of object differences between -fintegrated-as and -fno-integrated-as. Reviewers: sdardis Subscribers: dsanders, sdardis, llvm-commits Differential Revision: https://reviews.llvm.org/D22412 llvm-svn: 275967
2016-07-19 18:49:03 +08:00
; N32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
; N64: daddiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL: ld.d [[R1:\$w[0-9]+]], 0([[G_PTR]])
[mips][msa] Implemented build_vector using ldi, fill, and custom SelectionDAG nodes (VSPLAT and VSPLATD) Note: There's a later patch on my branch that re-implements this to select build_vector without the custom SelectionDAG nodes. The future patch avoids the constant-folding problems stemming from the custom node (i.e. it doesn't need to re-implement all the DAG combines related to BUILD_VECTOR). Changes to MIPS specific SelectionDAG nodes: * Added VSPLAT This is a special case of BUILD_VECTOR that covers the case the BUILD_VECTOR is a splat operation. * Added VSPLATD This is a special case of VSPLAT that handles the cases when v2i64 is legal llvm-svn: 191191
2013-09-23 20:02:46 +08:00
store volatile <2 x double> <double 1.0, double 1.0>, <2 x double>*@v2f64
[mips][msa] Test basic operations for the N32 ABI too. Summary: This required adding instruction aliases for dneg. N64 will be enabled shortly but requires additional bugfixes. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9341 llvm-svn: 236489
2015-05-05 16:48:35 +08:00
; O32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %lo($
[mips] Correct label prefixes for N32 and N64. Summary: N32 and N64 follow the standard ELF conventions (.L) whereas O32 uses its own ($). This fixes the majority of object differences between -fintegrated-as and -fno-integrated-as. Reviewers: sdardis Subscribers: dsanders, sdardis, llvm-commits Differential Revision: https://reviews.llvm.org/D22412 llvm-svn: 275967
2016-07-19 18:49:03 +08:00
; N32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
; N64: daddiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL: ld.d [[R1:\$w[0-9]+]], 0([[G_PTR]])
[mips][msa] Implemented build_vector using ldi, fill, and custom SelectionDAG nodes (VSPLAT and VSPLATD) Note: There's a later patch on my branch that re-implements this to select build_vector without the custom SelectionDAG nodes. The future patch avoids the constant-folding problems stemming from the custom node (i.e. it doesn't need to re-implement all the DAG combines related to BUILD_VECTOR). Changes to MIPS specific SelectionDAG nodes: * Added VSPLAT This is a special case of BUILD_VECTOR that covers the case the BUILD_VECTOR is a splat operation. * Added VSPLATD This is a special case of VSPLAT that handles the cases when v2i64 is legal llvm-svn: 191191
2013-09-23 20:02:46 +08:00
store volatile <2 x double> <double 1.0, double 31.0>, <2 x double>*@v2f64
[mips][msa] Test basic operations for the N32 ABI too. Summary: This required adding instruction aliases for dneg. N64 will be enabled shortly but requires additional bugfixes. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9341 llvm-svn: 236489
2015-05-05 16:48:35 +08:00
; O32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %lo($
[mips] Correct label prefixes for N32 and N64. Summary: N32 and N64 follow the standard ELF conventions (.L) whereas O32 uses its own ($). This fixes the majority of object differences between -fintegrated-as and -fno-integrated-as. Reviewers: sdardis Subscribers: dsanders, sdardis, llvm-commits Differential Revision: https://reviews.llvm.org/D22412 llvm-svn: 275967
2016-07-19 18:49:03 +08:00
; N32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
; N64: daddiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL: ld.d [[R1:\$w[0-9]+]], 0([[G_PTR]])
[mips][msa] Implemented build_vector using ldi, fill, and custom SelectionDAG nodes (VSPLAT and VSPLATD) Note: There's a later patch on my branch that re-implements this to select build_vector without the custom SelectionDAG nodes. The future patch avoids the constant-folding problems stemming from the custom node (i.e. it doesn't need to re-implement all the DAG combines related to BUILD_VECTOR). Changes to MIPS specific SelectionDAG nodes: * Added VSPLAT This is a special case of BUILD_VECTOR that covers the case the BUILD_VECTOR is a splat operation. * Added VSPLATD This is a special case of VSPLAT that handles the cases when v2i64 is legal llvm-svn: 191191
2013-09-23 20:02:46 +08:00
store volatile <2 x double> <double 3.0, double 4.0>, <2 x double>*@v2f64
[mips][msa] Test basic operations for the N32 ABI too. Summary: This required adding instruction aliases for dneg. N64 will be enabled shortly but requires additional bugfixes. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9341 llvm-svn: 236489
2015-05-05 16:48:35 +08:00
; O32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %lo($
[mips] Correct label prefixes for N32 and N64. Summary: N32 and N64 follow the standard ELF conventions (.L) whereas O32 uses its own ($). This fixes the majority of object differences between -fintegrated-as and -fno-integrated-as. Reviewers: sdardis Subscribers: dsanders, sdardis, llvm-commits Differential Revision: https://reviews.llvm.org/D22412 llvm-svn: 275967
2016-07-19 18:49:03 +08:00
; N32: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
; N64: daddiu [[G_PTR:\$[0-9]+]], {{.*}}, %got_ofst(.L
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL: ld.d [[R1:\$w[0-9]+]], 0([[G_PTR]])
[mips][msa] Implemented build_vector using ldi, fill, and custom SelectionDAG nodes (VSPLAT and VSPLATD) Note: There's a later patch on my branch that re-implements this to select build_vector without the custom SelectionDAG nodes. The future patch avoids the constant-folding problems stemming from the custom node (i.e. it doesn't need to re-implement all the DAG combines related to BUILD_VECTOR). Changes to MIPS specific SelectionDAG nodes: * Added VSPLAT This is a special case of BUILD_VECTOR that covers the case the BUILD_VECTOR is a splat operation. * Added VSPLATD This is a special case of VSPLAT that handles the cases when v2i64 is legal llvm-svn: 191191
2013-09-23 20:02:46 +08:00
ret void
}
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
[mips][msa] Added support for build_vector for v4f32 and v2f64. llvm-svn: 192699
2013-10-15 21:14:41 +08:00
define void @nonconst_v4f32() nounwind {
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-LABEL: nonconst_v4f32:
[mips][msa] Added support for build_vector for v4f32 and v2f64. llvm-svn: 192699
2013-10-15 21:14:41 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%1 = load float , float *@f32
[mips][msa] Added support for build_vector for v4f32 and v2f64. llvm-svn: 192699
2013-10-15 21:14:41 +08:00
%2 = insertelement <4 x float> undef, float %1, i32 0
%3 = insertelement <4 x float> %2, float %1, i32 1
%4 = insertelement <4 x float> %3, float %1, i32 2
%5 = insertelement <4 x float> %4, float %1, i32 3
store volatile <4 x float> %5, <4 x float>*@v4f32
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL: lwc1 $f[[R1:[0-9]+]], 0(
; ALL: splati.w [[R2:\$w[0-9]+]], $w[[R1]]
[mips][msa] Added support for build_vector for v4f32 and v2f64. llvm-svn: 192699
2013-10-15 21:14:41 +08:00
ret void
}
define void @nonconst_v2f64() nounwind {
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-LABEL: nonconst_v2f64:
[mips][msa] Added support for build_vector for v4f32 and v2f64. llvm-svn: 192699
2013-10-15 21:14:41 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%1 = load double , double *@f64
[mips][msa] Added support for build_vector for v4f32 and v2f64. llvm-svn: 192699
2013-10-15 21:14:41 +08:00
%2 = insertelement <2 x double> undef, double %1, i32 0
%3 = insertelement <2 x double> %2, double %1, i32 1
store volatile <2 x double> %3, <2 x double>*@v2f64
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL: ldc1 $f[[R1:[0-9]+]], 0(
; ALL: splati.d [[R2:\$w[0-9]+]], $w[[R1]]
[mips][msa] Added support for build_vector for v4f32 and v2f64. llvm-svn: 192699
2013-10-15 21:14:41 +08:00
ret void
}
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
define float @extract_v4f32() nounwind {
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-LABEL: extract_v4f32:
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%1 = load <4 x float>, <4 x float>* @v4f32
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: ld.w [[R1:\$w[0-9]+]],
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
%2 = fadd <4 x float> %1, %1
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: fadd.w [[R2:\$w[0-9]+]], [[R1]], [[R1]]
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
%3 = extractelement <4 x float> %2, i32 1
; Element 1 can be obtained by splatting it across the vector and extracting
; $w0:sub_lo
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: splati.w $w0, [[R1]][1]
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
ret float %3
}
define float @extract_v4f32_elt0() nounwind {
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-LABEL: extract_v4f32_elt0:
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%1 = load <4 x float>, <4 x float>* @v4f32
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: ld.w [[R1:\$w[0-9]+]],
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
%2 = fadd <4 x float> %1, %1
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: fadd.w $w0, [[R1]], [[R1]]
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
%3 = extractelement <4 x float> %2, i32 0
; Element 0 can be obtained by extracting $w0:sub_lo ($f0)
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-NOT: copy_u.w
; ALL-NOT: mtc1
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
ret float %3
}
[mips][msa] Correct the behaviour of the COPY_FW pseudo on lanes 2 and 3. Summary: Previously, attempting to extract lanes 2 and 3 would actually extract lane 1. The MSA CodeGen tests only covered lanes 0 and 1. Differential Revision: http://llvm-reviews.chandlerc.com/D2935 llvm-svn: 202848
2014-03-04 21:54:30 +08:00
define float @extract_v4f32_elt2() nounwind {
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-LABEL: extract_v4f32_elt2:
[mips][msa] Correct the behaviour of the COPY_FW pseudo on lanes 2 and 3. Summary: Previously, attempting to extract lanes 2 and 3 would actually extract lane 1. The MSA CodeGen tests only covered lanes 0 and 1. Differential Revision: http://llvm-reviews.chandlerc.com/D2935 llvm-svn: 202848
2014-03-04 21:54:30 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%1 = load <4 x float>, <4 x float>* @v4f32
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: ld.w [[R1:\$w[0-9]+]],
[mips][msa] Correct the behaviour of the COPY_FW pseudo on lanes 2 and 3. Summary: Previously, attempting to extract lanes 2 and 3 would actually extract lane 1. The MSA CodeGen tests only covered lanes 0 and 1. Differential Revision: http://llvm-reviews.chandlerc.com/D2935 llvm-svn: 202848
2014-03-04 21:54:30 +08:00
%2 = fadd <4 x float> %1, %1
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: fadd.w [[R2:\$w[0-9]+]], [[R1]], [[R1]]
[mips][msa] Correct the behaviour of the COPY_FW pseudo on lanes 2 and 3. Summary: Previously, attempting to extract lanes 2 and 3 would actually extract lane 1. The MSA CodeGen tests only covered lanes 0 and 1. Differential Revision: http://llvm-reviews.chandlerc.com/D2935 llvm-svn: 202848
2014-03-04 21:54:30 +08:00
%3 = extractelement <4 x float> %2, i32 2
; Element 2 can be obtained by splatting it across the vector and extracting
; $w0:sub_lo
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: splati.w $w0, [[R1]][2]
[mips][msa] Correct the behaviour of the COPY_FW pseudo on lanes 2 and 3. Summary: Previously, attempting to extract lanes 2 and 3 would actually extract lane 1. The MSA CodeGen tests only covered lanes 0 and 1. Differential Revision: http://llvm-reviews.chandlerc.com/D2935 llvm-svn: 202848
2014-03-04 21:54:30 +08:00
ret float %3
}
[mips][msa] Fix element extraction where the index is variable. Summary: This isn't supported directly so we splat the vector element and extract the most convenient copy. Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3530 llvm-svn: 207524
2014-04-29 21:31:37 +08:00
define float @extract_v4f32_vidx() nounwind {
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-LABEL: extract_v4f32_vidx:
[mips][msa] Fix element extraction where the index is variable. Summary: This isn't supported directly so we splat the vector element and extract the most convenient copy. Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3530 llvm-svn: 207524
2014-04-29 21:31:37 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%1 = load <4 x float>, <4 x float>* @v4f32
[mips][msa] Test basic operations for the N32 ABI too. Summary: This required adding instruction aliases for dneg. N64 will be enabled shortly but requires additional bugfixes. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9341 llvm-svn: 236489
2015-05-05 16:48:35 +08:00
; O32-DAG: lw [[PTR_V:\$[0-9]+]], %got(v4f32)(
; N32-DAG: lw [[PTR_V:\$[0-9]+]], %got_disp(v4f32)(
; N64-DAG: ld [[PTR_V:\$[0-9]+]], %got_disp(v4f32)(
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: ld.w [[R1:\$w[0-9]+]], 0([[PTR_V]])
[mips][msa] Fix element extraction where the index is variable. Summary: This isn't supported directly so we splat the vector element and extract the most convenient copy. Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3530 llvm-svn: 207524
2014-04-29 21:31:37 +08:00
%2 = fadd <4 x float> %1, %1
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: fadd.w [[R2:\$w[0-9]+]], [[R1]], [[R1]]
[mips][msa] Fix element extraction where the index is variable. Summary: This isn't supported directly so we splat the vector element and extract the most convenient copy. Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3530 llvm-svn: 207524
2014-04-29 21:31:37 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%3 = load i32, i32* @i32
[mips][msa] Test basic operations for the N32 ABI too. Summary: This required adding instruction aliases for dneg. N64 will be enabled shortly but requires additional bugfixes. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9341 llvm-svn: 236489
2015-05-05 16:48:35 +08:00
; O32-DAG: lw [[PTR_I:\$[0-9]+]], %got(i32)(
; N32-DAG: lw [[PTR_I:\$[0-9]+]], %got_disp(i32)(
; N64-DAG: ld [[PTR_I:\$[0-9]+]], %got_disp(i32)(
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: lw [[IDX:\$[0-9]+]], 0([[PTR_I]])
[mips][msa] Fix element extraction where the index is variable. Summary: This isn't supported directly so we splat the vector element and extract the most convenient copy. Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3530 llvm-svn: 207524
2014-04-29 21:31:37 +08:00
%4 = extractelement <4 x float> %2, i32 %3
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: splat.w $w0, [[R1]]{{\[}}[[IDX]]]
[mips][msa] Fix element extraction where the index is variable. Summary: This isn't supported directly so we splat the vector element and extract the most convenient copy. Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3530 llvm-svn: 207524
2014-04-29 21:31:37 +08:00
ret float %4
}
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
define double @extract_v2f64() nounwind {
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-LABEL: extract_v2f64:
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%1 = load <2 x double>, <2 x double>* @v2f64
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: ld.d [[R1:\$w[0-9]+]],
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
%2 = fadd <2 x double> %1, %1
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: fadd.d [[R2:\$w[0-9]+]], [[R1]], [[R1]]
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
%3 = extractelement <2 x double> %2, i32 1
; Element 1 can be obtained by splatting it across the vector and extracting
; $w0:sub_64
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: splati.d $w0, [[R1]][1]
; ALL-NOT: copy_u.w
; ALL-NOT: mtc1
; ALL-NOT: mthc1
; ALL-NOT: sll
; ALL-NOT: sra
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
ret double %3
}
define double @extract_v2f64_elt0() nounwind {
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-LABEL: extract_v2f64_elt0:
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%1 = load <2 x double>, <2 x double>* @v2f64
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: ld.d [[R1:\$w[0-9]+]],
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
%2 = fadd <2 x double> %1, %1
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: fadd.d $w0, [[R1]], [[R1]]
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
%3 = extractelement <2 x double> %2, i32 0
; Element 0 can be obtained by extracting $w0:sub_64 ($f0)
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-NOT: copy_u.w
; ALL-NOT: mtc1
; ALL-NOT: mthc1
; ALL-NOT: sll
; ALL-NOT: sra
[mips][msa] Implemented extract_vector_elt for v4f32 or v2f64 For v4f32 and v2f64, EXTRACT_VECTOR_ELT is matched by a pseudo-insn which may be expanded to subregister copies and/or instructions as appropriate. llvm-svn: 191514
2013-09-27 20:17:32 +08:00
ret double %3
}
[mips][msa] Implemented insert_vector_elt for v4f32 and v2f64. For v4f32 and v2f64, INSERT_VECTOR_ELT is matched by a pseudo-insn which is later expanded to appropriate insve.[wd] insns. llvm-svn: 191515
2013-09-27 20:31:32 +08:00
[mips][msa] Fix element extraction where the index is variable. Summary: This isn't supported directly so we splat the vector element and extract the most convenient copy. Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3530 llvm-svn: 207524
2014-04-29 21:31:37 +08:00
define double @extract_v2f64_vidx() nounwind {
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-LABEL: extract_v2f64_vidx:
[mips][msa] Fix element extraction where the index is variable. Summary: This isn't supported directly so we splat the vector element and extract the most convenient copy. Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3530 llvm-svn: 207524
2014-04-29 21:31:37 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%1 = load <2 x double>, <2 x double>* @v2f64
[mips][msa] Test basic operations for the N32 ABI too. Summary: This required adding instruction aliases for dneg. N64 will be enabled shortly but requires additional bugfixes. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9341 llvm-svn: 236489
2015-05-05 16:48:35 +08:00
; O32-DAG: lw [[PTR_V:\$[0-9]+]], %got(v2f64)(
; N32-DAG: lw [[PTR_V:\$[0-9]+]], %got_disp(v2f64)(
; N64-DAG: ld [[PTR_V:\$[0-9]+]], %got_disp(v2f64)(
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: ld.d [[R1:\$w[0-9]+]], 0([[PTR_V]])
[mips][msa] Fix element extraction where the index is variable. Summary: This isn't supported directly so we splat the vector element and extract the most convenient copy. Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3530 llvm-svn: 207524
2014-04-29 21:31:37 +08:00
%2 = fadd <2 x double> %1, %1
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: fadd.d [[R2:\$w[0-9]+]], [[R1]], [[R1]]
[mips][msa] Fix element extraction where the index is variable. Summary: This isn't supported directly so we splat the vector element and extract the most convenient copy. Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3530 llvm-svn: 207524
2014-04-29 21:31:37 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%3 = load i32, i32* @i32
[mips][msa] Test basic operations for the N32 ABI too. Summary: This required adding instruction aliases for dneg. N64 will be enabled shortly but requires additional bugfixes. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9341 llvm-svn: 236489
2015-05-05 16:48:35 +08:00
; O32-DAG: lw [[PTR_I:\$[0-9]+]], %got(i32)(
; N32-DAG: lw [[PTR_I:\$[0-9]+]], %got_disp(i32)(
; N64-DAG: ld [[PTR_I:\$[0-9]+]], %got_disp(i32)(
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: lw [[IDX:\$[0-9]+]], 0([[PTR_I]])
[mips][msa] Fix element extraction where the index is variable. Summary: This isn't supported directly so we splat the vector element and extract the most convenient copy. Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3530 llvm-svn: 207524
2014-04-29 21:31:37 +08:00
%4 = extractelement <2 x double> %2, i32 %3
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: splat.d $w0, [[R1]]{{\[}}[[IDX]]]
[mips][msa] Fix element extraction where the index is variable. Summary: This isn't supported directly so we splat the vector element and extract the most convenient copy. Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3530 llvm-svn: 207524
2014-04-29 21:31:37 +08:00
ret double %4
}
[mips][msa] Implemented insert_vector_elt for v4f32 and v2f64. For v4f32 and v2f64, INSERT_VECTOR_ELT is matched by a pseudo-insn which is later expanded to appropriate insve.[wd] insns. llvm-svn: 191515
2013-09-27 20:31:32 +08:00
define void @insert_v4f32(float %a) nounwind {
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-LABEL: insert_v4f32:
[mips][msa] Implemented insert_vector_elt for v4f32 and v2f64. For v4f32 and v2f64, INSERT_VECTOR_ELT is matched by a pseudo-insn which is later expanded to appropriate insve.[wd] insns. llvm-svn: 191515
2013-09-27 20:31:32 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%1 = load <4 x float>, <4 x float>* @v4f32
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: ld.w [[R1:\$w[0-9]+]],
[mips][msa] Implemented insert_vector_elt for v4f32 and v2f64. For v4f32 and v2f64, INSERT_VECTOR_ELT is matched by a pseudo-insn which is later expanded to appropriate insve.[wd] insns. llvm-svn: 191515
2013-09-27 20:31:32 +08:00
%2 = insertelement <4 x float> %1, float %a, i32 1
; float argument passed in $f12
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: insve.w [[R1]][1], $w12[0]
[mips][msa] Implemented insert_vector_elt for v4f32 and v2f64. For v4f32 and v2f64, INSERT_VECTOR_ELT is matched by a pseudo-insn which is later expanded to appropriate insve.[wd] insns. llvm-svn: 191515
2013-09-27 20:31:32 +08:00
store <4 x float> %2, <4 x float>* @v4f32
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: st.w [[R1]]
[mips][msa] Implemented insert_vector_elt for v4f32 and v2f64. For v4f32 and v2f64, INSERT_VECTOR_ELT is matched by a pseudo-insn which is later expanded to appropriate insve.[wd] insns. llvm-svn: 191515
2013-09-27 20:31:32 +08:00
ret void
}
define void @insert_v2f64(double %a) nounwind {
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-LABEL: insert_v2f64:
[mips][msa] Implemented insert_vector_elt for v4f32 and v2f64. For v4f32 and v2f64, INSERT_VECTOR_ELT is matched by a pseudo-insn which is later expanded to appropriate insve.[wd] insns. llvm-svn: 191515
2013-09-27 20:31:32 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%1 = load <2 x double>, <2 x double>* @v2f64
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: ld.d [[R1:\$w[0-9]+]],
[mips][msa] Implemented insert_vector_elt for v4f32 and v2f64. For v4f32 and v2f64, INSERT_VECTOR_ELT is matched by a pseudo-insn which is later expanded to appropriate insve.[wd] insns. llvm-svn: 191515
2013-09-27 20:31:32 +08:00
%2 = insertelement <2 x double> %1, double %a, i32 1
; double argument passed in $f12
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: insve.d [[R1]][1], $w12[0]
[mips][msa] Implemented insert_vector_elt for v4f32 and v2f64. For v4f32 and v2f64, INSERT_VECTOR_ELT is matched by a pseudo-insn which is later expanded to appropriate insve.[wd] insns. llvm-svn: 191515
2013-09-27 20:31:32 +08:00
store <2 x double> %2, <2 x double>* @v2f64
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: st.d [[R1]]
[mips][msa] Implemented insert_vector_elt for v4f32 and v2f64. For v4f32 and v2f64, INSERT_VECTOR_ELT is matched by a pseudo-insn which is later expanded to appropriate insve.[wd] insns. llvm-svn: 191515
2013-09-27 20:31:32 +08:00
ret void
}
[mips][msa] Fix vector insertions where the index is variable Summary: This isn't supported directly so we rotate the vector by the desired number of elements, insert to element zero, then rotate back. The i64 case generates rather poor code on MIPS32. There is an obvious optimisation to be made in future (do both insert.w's inside a shared rotate/unrotate sequence) but for now it's sufficient to select valid code instead of aborting. Depends on D3536 Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3537 llvm-svn: 207640
2014-04-30 20:09:32 +08:00
define void @insert_v4f32_vidx(float %a) nounwind {
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-LABEL: insert_v4f32_vidx:
[mips][msa] Fix vector insertions where the index is variable Summary: This isn't supported directly so we rotate the vector by the desired number of elements, insert to element zero, then rotate back. The i64 case generates rather poor code on MIPS32. There is an obvious optimisation to be made in future (do both insert.w's inside a shared rotate/unrotate sequence) but for now it's sufficient to select valid code instead of aborting. Depends on D3536 Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3537 llvm-svn: 207640
2014-04-30 20:09:32 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%1 = load <4 x float>, <4 x float>* @v4f32
[mips][msa] Test basic operations for the N32 ABI too. Summary: This required adding instruction aliases for dneg. N64 will be enabled shortly but requires additional bugfixes. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9341 llvm-svn: 236489
2015-05-05 16:48:35 +08:00
; O32-DAG: lw [[PTR_V:\$[0-9]+]], %got(v4f32)(
; N32-DAG: lw [[PTR_V:\$[0-9]+]], %got_disp(v4f32)(
; N64-DAG: ld [[PTR_V:\$[0-9]+]], %got_disp(v4f32)(
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: ld.w [[R1:\$w[0-9]+]], 0([[PTR_V]])
[mips][msa] Fix vector insertions where the index is variable Summary: This isn't supported directly so we rotate the vector by the desired number of elements, insert to element zero, then rotate back. The i64 case generates rather poor code on MIPS32. There is an obvious optimisation to be made in future (do both insert.w's inside a shared rotate/unrotate sequence) but for now it's sufficient to select valid code instead of aborting. Depends on D3536 Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3537 llvm-svn: 207640
2014-04-30 20:09:32 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%2 = load i32, i32* @i32
[mips][msa] Test basic operations for the N32 ABI too. Summary: This required adding instruction aliases for dneg. N64 will be enabled shortly but requires additional bugfixes. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9341 llvm-svn: 236489
2015-05-05 16:48:35 +08:00
; O32-DAG: lw [[PTR_I:\$[0-9]+]], %got(i32)(
; N32-DAG: lw [[PTR_I:\$[0-9]+]], %got_disp(i32)(
; N64-DAG: ld [[PTR_I:\$[0-9]+]], %got_disp(i32)(
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: lw [[IDX:\$[0-9]+]], 0([[PTR_I]])
[mips][msa] Fix vector insertions where the index is variable Summary: This isn't supported directly so we rotate the vector by the desired number of elements, insert to element zero, then rotate back. The i64 case generates rather poor code on MIPS32. There is an obvious optimisation to be made in future (do both insert.w's inside a shared rotate/unrotate sequence) but for now it's sufficient to select valid code instead of aborting. Depends on D3536 Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3537 llvm-svn: 207640
2014-04-30 20:09:32 +08:00
%3 = insertelement <4 x float> %1, float %a, i32 %2
; float argument passed in $f12
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: sll [[BIDX:\$[0-9]+]], [[IDX]], 2
; ALL-DAG: sld.b [[R1]], [[R1]]{{\[}}[[BIDX]]]
; ALL-DAG: insve.w [[R1]][0], $w12[0]
; ALL-DAG: neg [[NIDX:\$[0-9]+]], [[BIDX]]
; ALL-DAG: sld.b [[R1]], [[R1]]{{\[}}[[NIDX]]]
[mips][msa] Fix vector insertions where the index is variable Summary: This isn't supported directly so we rotate the vector by the desired number of elements, insert to element zero, then rotate back. The i64 case generates rather poor code on MIPS32. There is an obvious optimisation to be made in future (do both insert.w's inside a shared rotate/unrotate sequence) but for now it's sufficient to select valid code instead of aborting. Depends on D3536 Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3537 llvm-svn: 207640
2014-04-30 20:09:32 +08:00
store <4 x float> %3, <4 x float>* @v4f32
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: st.w [[R1]]
[mips][msa] Fix vector insertions where the index is variable Summary: This isn't supported directly so we rotate the vector by the desired number of elements, insert to element zero, then rotate back. The i64 case generates rather poor code on MIPS32. There is an obvious optimisation to be made in future (do both insert.w's inside a shared rotate/unrotate sequence) but for now it's sufficient to select valid code instead of aborting. Depends on D3536 Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3537 llvm-svn: 207640
2014-04-30 20:09:32 +08:00
ret void
}
define void @insert_v2f64_vidx(double %a) nounwind {
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-LABEL: insert_v2f64_vidx:
[mips][msa] Fix vector insertions where the index is variable Summary: This isn't supported directly so we rotate the vector by the desired number of elements, insert to element zero, then rotate back. The i64 case generates rather poor code on MIPS32. There is an obvious optimisation to be made in future (do both insert.w's inside a shared rotate/unrotate sequence) but for now it's sufficient to select valid code instead of aborting. Depends on D3536 Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3537 llvm-svn: 207640
2014-04-30 20:09:32 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%1 = load <2 x double>, <2 x double>* @v2f64
[mips][msa] Test basic operations for the N32 ABI too. Summary: This required adding instruction aliases for dneg. N64 will be enabled shortly but requires additional bugfixes. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9341 llvm-svn: 236489
2015-05-05 16:48:35 +08:00
; O32-DAG: lw [[PTR_V:\$[0-9]+]], %got(v2f64)(
; N32-DAG: lw [[PTR_V:\$[0-9]+]], %got_disp(v2f64)(
; N64-DAG: ld [[PTR_V:\$[0-9]+]], %got_disp(v2f64)(
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: ld.d [[R1:\$w[0-9]+]], 0([[PTR_V]])
[mips][msa] Fix vector insertions where the index is variable Summary: This isn't supported directly so we rotate the vector by the desired number of elements, insert to element zero, then rotate back. The i64 case generates rather poor code on MIPS32. There is an obvious optimisation to be made in future (do both insert.w's inside a shared rotate/unrotate sequence) but for now it's sufficient to select valid code instead of aborting. Depends on D3536 Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3537 llvm-svn: 207640
2014-04-30 20:09:32 +08:00
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%2 = load i32, i32* @i32
[mips][msa] Test basic operations for the N32 ABI too. Summary: This required adding instruction aliases for dneg. N64 will be enabled shortly but requires additional bugfixes. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9341 llvm-svn: 236489
2015-05-05 16:48:35 +08:00
; O32-DAG: lw [[PTR_I:\$[0-9]+]], %got(i32)(
; N32-DAG: lw [[PTR_I:\$[0-9]+]], %got_disp(i32)(
; N64-DAG: ld [[PTR_I:\$[0-9]+]], %got_disp(i32)(
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: lw [[IDX:\$[0-9]+]], 0([[PTR_I]])
[mips][msa] Fix vector insertions where the index is variable Summary: This isn't supported directly so we rotate the vector by the desired number of elements, insert to element zero, then rotate back. The i64 case generates rather poor code on MIPS32. There is an obvious optimisation to be made in future (do both insert.w's inside a shared rotate/unrotate sequence) but for now it's sufficient to select valid code instead of aborting. Depends on D3536 Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3537 llvm-svn: 207640
2014-04-30 20:09:32 +08:00
%3 = insertelement <2 x double> %1, double %a, i32 %2
; double argument passed in $f12
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: sll [[BIDX:\$[0-9]+]], [[IDX]], 3
; ALL-DAG: sld.b [[R1]], [[R1]]{{\[}}[[BIDX]]]
; ALL-DAG: insve.d [[R1]][0], $w12[0]
; ALL-DAG: neg [[NIDX:\$[0-9]+]], [[BIDX]]
; ALL-DAG: sld.b [[R1]], [[R1]]{{\[}}[[NIDX]]]
[mips][msa] Fix vector insertions where the index is variable Summary: This isn't supported directly so we rotate the vector by the desired number of elements, insert to element zero, then rotate back. The i64 case generates rather poor code on MIPS32. There is an obvious optimisation to be made in future (do both insert.w's inside a shared rotate/unrotate sequence) but for now it's sufficient to select valid code instead of aborting. Depends on D3536 Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3537 llvm-svn: 207640
2014-04-30 20:09:32 +08:00
store <2 x double> %3, <2 x double>* @v2f64
[mips][msa] Rename main check prefix to 'ALL' in basic operations tests. NFC Summary: The majority of the checks are subtarget independent. The few that aren't will be corrected shortly. Reviewers: vkalintiris Reviewed By: vkalintiris Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9340 llvm-svn: 236220
2015-04-30 17:57:37 +08:00
; ALL-DAG: st.d [[R1]]
[mips][msa] Fix vector insertions where the index is variable Summary: This isn't supported directly so we rotate the vector by the desired number of elements, insert to element zero, then rotate back. The i64 case generates rather poor code on MIPS32. There is an obvious optimisation to be made in future (do both insert.w's inside a shared rotate/unrotate sequence) but for now it's sufficient to select valid code instead of aborting. Depends on D3536 Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://reviews.llvm.org/D3537 llvm-svn: 207640
2014-04-30 20:09:32 +08:00
ret void
}