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/SPARC/32abi.ll

250 lines
7.7 KiB
LLVM
Raw Normal View History

[Sparc] Add Soft Float support This change adds support for software floating point operations for Sparc targets. This is the first in a set of patches to enable software floating point on Sparc. The next patch will enable the option to be used with Clang. Differential Revision: http://reviews.llvm.org/D19265 llvm-svn: 269892
2016-05-18 17:14:13 +08:00
; RUN: llc < %s -march=sparc -disable-sparc-delay-filler -disable-sparc-leaf-proc | FileCheck %s --check-prefix=CHECK --check-prefix=HARD --check-prefix=CHECK-BE
; RUN: llc < %s -march=sparcel -disable-sparc-delay-filler -disable-sparc-leaf-proc | FileCheck %s --check-prefix=CHECK --check-prefix=HARD --check-prefix=CHECK-LE
; RUN: llc < %s -march=sparc -disable-sparc-delay-filler -disable-sparc-leaf-proc -mattr=soft-float | FileCheck %s --check-prefix=CHECK --check-prefix=SOFT --check-prefix=CHECK-BE
[Sparc] Fix handling of double incoming arguments on sparc little-endian. On SparcV8, doubles get passed in two 32-bit integer registers. The call code was already handling endianness correctly, but the incoming argument code was not -- it got the two halves in opposite order. Also remove some dead code in LowerFormalArguments_32 to handle less-than-32bit values, which can't actually happen. Finally, add some test cases for the 32-bit calling convention, cribbed from the 64abi.ll test, and run for both big and little-endian. llvm-svn: 255668
2015-12-16 03:23:12 +08:00
; CHECK-LABEL: intarg:
; The save/restore frame is not strictly necessary here, but we would need to
; refer to %o registers instead.
; CHECK: save %sp, -96, %sp
; CHECK: ld [%fp+96], [[R2:%[gilo][0-7]]]
; CHECK: ld [%fp+92], [[R1:%[gilo][0-7]]]
; CHECK: stb %i0, [%i4]
; CHECK: stb %i1, [%i4]
; CHECK: sth %i2, [%i4]
; CHECK: st %i3, [%i4]
; CHECK: st %i4, [%i4]
; CHECK: st %i5, [%i4]
; CHECK: st [[R1]], [%i4]
; CHECK: st [[R2]], [%i4]
; CHECK: restore
define void @intarg(i8 %a0, ; %i0
i8 %a1, ; %i1
i16 %a2, ; %i2
i32 %a3, ; %i3
i8* %a4, ; %i4
i32 %a5, ; %i5
i32 signext %a6, ; [%fp+92]
i8* %a7) { ; [%fp+96]
Elide stores which are overwritten without being observed. Summary: In SelectionDAG, when a store is immediately chained to another store to the same address, elide the first store as it has no observable effects. This is causes small improvements dealing with intrinsics lowered to stores. Test notes: * Many testcases overwrite store addresses multiple times and needed minor changes, mainly making stores volatile to prevent the optimization from optimizing the test away. * Many X86 test cases optimized out instructions associated with associated with va_start. * Note that test_splat in CodeGen/AArch64/misched-stp.ll no longer has dependencies to check and can probably be removed and potentially replaced with another test. Reviewers: rnk, john.brawn Subscribers: aemerson, rengolin, qcolombet, jyknight, nemanjai, nhaehnle, javed.absar, llvm-commits Differential Revision: https://reviews.llvm.org/D33206 llvm-svn: 303198
2017-05-17 03:43:56 +08:00
store volatile i8 %a0, i8* %a4
store volatile i8 %a1, i8* %a4
[Sparc] Fix handling of double incoming arguments on sparc little-endian. On SparcV8, doubles get passed in two 32-bit integer registers. The call code was already handling endianness correctly, but the incoming argument code was not -- it got the two halves in opposite order. Also remove some dead code in LowerFormalArguments_32 to handle less-than-32bit values, which can't actually happen. Finally, add some test cases for the 32-bit calling convention, cribbed from the 64abi.ll test, and run for both big and little-endian. llvm-svn: 255668
2015-12-16 03:23:12 +08:00
%p16 = bitcast i8* %a4 to i16*
Elide stores which are overwritten without being observed. Summary: In SelectionDAG, when a store is immediately chained to another store to the same address, elide the first store as it has no observable effects. This is causes small improvements dealing with intrinsics lowered to stores. Test notes: * Many testcases overwrite store addresses multiple times and needed minor changes, mainly making stores volatile to prevent the optimization from optimizing the test away. * Many X86 test cases optimized out instructions associated with associated with va_start. * Note that test_splat in CodeGen/AArch64/misched-stp.ll no longer has dependencies to check and can probably be removed and potentially replaced with another test. Reviewers: rnk, john.brawn Subscribers: aemerson, rengolin, qcolombet, jyknight, nemanjai, nhaehnle, javed.absar, llvm-commits Differential Revision: https://reviews.llvm.org/D33206 llvm-svn: 303198
2017-05-17 03:43:56 +08:00
store volatile i16 %a2, i16* %p16
[Sparc] Fix handling of double incoming arguments on sparc little-endian. On SparcV8, doubles get passed in two 32-bit integer registers. The call code was already handling endianness correctly, but the incoming argument code was not -- it got the two halves in opposite order. Also remove some dead code in LowerFormalArguments_32 to handle less-than-32bit values, which can't actually happen. Finally, add some test cases for the 32-bit calling convention, cribbed from the 64abi.ll test, and run for both big and little-endian. llvm-svn: 255668
2015-12-16 03:23:12 +08:00
%p32 = bitcast i8* %a4 to i32*
Elide stores which are overwritten without being observed. Summary: In SelectionDAG, when a store is immediately chained to another store to the same address, elide the first store as it has no observable effects. This is causes small improvements dealing with intrinsics lowered to stores. Test notes: * Many testcases overwrite store addresses multiple times and needed minor changes, mainly making stores volatile to prevent the optimization from optimizing the test away. * Many X86 test cases optimized out instructions associated with associated with va_start. * Note that test_splat in CodeGen/AArch64/misched-stp.ll no longer has dependencies to check and can probably be removed and potentially replaced with another test. Reviewers: rnk, john.brawn Subscribers: aemerson, rengolin, qcolombet, jyknight, nemanjai, nhaehnle, javed.absar, llvm-commits Differential Revision: https://reviews.llvm.org/D33206 llvm-svn: 303198
2017-05-17 03:43:56 +08:00
store volatile i32 %a3, i32* %p32
[Sparc] Fix handling of double incoming arguments on sparc little-endian. On SparcV8, doubles get passed in two 32-bit integer registers. The call code was already handling endianness correctly, but the incoming argument code was not -- it got the two halves in opposite order. Also remove some dead code in LowerFormalArguments_32 to handle less-than-32bit values, which can't actually happen. Finally, add some test cases for the 32-bit calling convention, cribbed from the 64abi.ll test, and run for both big and little-endian. llvm-svn: 255668
2015-12-16 03:23:12 +08:00
%pp = bitcast i8* %a4 to i8**
Elide stores which are overwritten without being observed. Summary: In SelectionDAG, when a store is immediately chained to another store to the same address, elide the first store as it has no observable effects. This is causes small improvements dealing with intrinsics lowered to stores. Test notes: * Many testcases overwrite store addresses multiple times and needed minor changes, mainly making stores volatile to prevent the optimization from optimizing the test away. * Many X86 test cases optimized out instructions associated with associated with va_start. * Note that test_splat in CodeGen/AArch64/misched-stp.ll no longer has dependencies to check and can probably be removed and potentially replaced with another test. Reviewers: rnk, john.brawn Subscribers: aemerson, rengolin, qcolombet, jyknight, nemanjai, nhaehnle, javed.absar, llvm-commits Differential Revision: https://reviews.llvm.org/D33206 llvm-svn: 303198
2017-05-17 03:43:56 +08:00
store volatile i8* %a4, i8** %pp
store volatile i32 %a5, i32* %p32
store volatile i32 %a6, i32* %p32
store volatile i8* %a7, i8** %pp
[Sparc] Fix handling of double incoming arguments on sparc little-endian. On SparcV8, doubles get passed in two 32-bit integer registers. The call code was already handling endianness correctly, but the incoming argument code was not -- it got the two halves in opposite order. Also remove some dead code in LowerFormalArguments_32 to handle less-than-32bit values, which can't actually happen. Finally, add some test cases for the 32-bit calling convention, cribbed from the 64abi.ll test, and run for both big and little-endian. llvm-svn: 255668
2015-12-16 03:23:12 +08:00
ret void
}
; CHECK-LABEL: call_intarg:
; CHECK: save %sp, -104, %sp
; Use %o0-%o5 for outgoing arguments
; CHECK: mov 5, %o5
; CHECK: st %i0, [%sp+92]
; CHECK: call intarg
; CHECK-NOT: add %sp
; CHECK: restore
define void @call_intarg(i32 %i0, i8* %i1) {
call void @intarg(i8 0, i8 1, i16 2, i32 3, i8* undef, i32 5, i32 %i0, i8* %i1)
ret void
}
;; Verify doubles starting with an even reg, starting with an odd reg,
;; straddling the boundary of regs and mem, and floats in regs and mem.
;
; CHECK-LABEL: floatarg:
[Sparc] Add Soft Float support This change adds support for software floating point operations for Sparc targets. This is the first in a set of patches to enable software floating point on Sparc. The next patch will enable the option to be used with Clang. Differential Revision: http://reviews.llvm.org/D19265 llvm-svn: 269892
2016-05-18 17:14:13 +08:00
; HARD: save %sp, -120, %sp
; HARD: mov %i5, %g2
; HARD-NEXT: ld [%fp+92], %g3
; HARD-NEXT: mov %i4, %i5
VirtRegMap: Replace some identity copies with KILL instructions. An identity COPY like this: %AL = COPY %AL, %EAX<imp-def> has no semantic effect, but encodes liveness information: Further users of %EAX only depend on this instruction even though it does not define the full register. Replace the COPY with a KILL instruction in those cases to maintain this liveness information. (This reverts a small part of r238588 but this time adds a comment explaining why a KILL instruction is useful). llvm-svn: 274952
2016-07-09 08:19:07 +08:00
; HARD-NEXT: ! kill
[Sparc] Add Soft Float support This change adds support for software floating point operations for Sparc targets. This is the first in a set of patches to enable software floating point on Sparc. The next patch will enable the option to be used with Clang. Differential Revision: http://reviews.llvm.org/D19265 llvm-svn: 269892
2016-05-18 17:14:13 +08:00
; HARD-NEXT: std %g2, [%fp+-24]
; HARD-NEXT: mov %i3, %i4
; HARD-NEXT: std %i4, [%fp+-16]
VirtRegMap: Replace some identity copies with KILL instructions. An identity COPY like this: %AL = COPY %AL, %EAX<imp-def> has no semantic effect, but encodes liveness information: Further users of %EAX only depend on this instruction even though it does not define the full register. Replace the COPY with a KILL instruction in those cases to maintain this liveness information. (This reverts a small part of r238588 but this time adds a comment explaining why a KILL instruction is useful). llvm-svn: 274952
2016-07-09 08:19:07 +08:00
; HARD-NEXT: ! kill
[Sparc] Add Soft Float support This change adds support for software floating point operations for Sparc targets. This is the first in a set of patches to enable software floating point on Sparc. The next patch will enable the option to be used with Clang. Differential Revision: http://reviews.llvm.org/D19265 llvm-svn: 269892
2016-05-18 17:14:13 +08:00
; HARD-NEXT: std %i0, [%fp+-8]
; HARD-NEXT: st %i2, [%fp+-28]
; HARD-NEXT: ld [%fp+104], %f0
; HARD-NEXT: ldd [%fp+96], %f2
; HARD-NEXT: ld [%fp+-28], %f1
; HARD-NEXT: ldd [%fp+-8], %f4
; HARD-NEXT: ldd [%fp+-16], %f6
; HARD-NEXT: ldd [%fp+-24], %f8
; HARD-NEXT: fstod %f1, %f10
; HARD-NEXT: faddd %f4, %f10, %f4
; HARD-NEXT: faddd %f6, %f4, %f4
; HARD-NEXT: faddd %f8, %f4, %f4
; HARD-NEXT: faddd %f2, %f4, %f2
; HARD-NEXT: fstod %f0, %f0
; HARD-NEXT: faddd %f0, %f2, %f0
; SOFT: save %sp, -96, %sp
; SOFT: ld [%fp+104], %l0
; SOFT-NEXT: ld [%fp+96], %l1
; SOFT-NEXT: ld [%fp+100], %l2
; SOFT-NEXT: ld [%fp+92], %l3
; SOFT-NEXT: mov %i2, %o0
; SOFT-NEXT: call __extendsfdf2
; SOFT-NEXT: nop
[Sparc] Return true in enableMultipleCopyHints(). Enable multiple COPY hints to eliminate more COPYs during register allocation. Note that this is something all targets should do, see https://reviews.llvm.org/D38128. Review: James Y Knight llvm-svn: 326028
2018-02-24 16:24:31 +08:00
; SOFT-NEXT: mov %o0, %o2
; SOFT-NEXT: mov %o1, %o3
[Sparc] Add Soft Float support This change adds support for software floating point operations for Sparc targets. This is the first in a set of patches to enable software floating point on Sparc. The next patch will enable the option to be used with Clang. Differential Revision: http://reviews.llvm.org/D19265 llvm-svn: 269892
2016-05-18 17:14:13 +08:00
; SOFT-NEXT: mov %i0, %o0
; SOFT-NEXT: mov %i1, %o1
; SOFT-NEXT: call __adddf3
; SOFT-NEXT: nop
[Sparc] Return true in enableMultipleCopyHints(). Enable multiple COPY hints to eliminate more COPYs during register allocation. Note that this is something all targets should do, see https://reviews.llvm.org/D38128. Review: James Y Knight llvm-svn: 326028
2018-02-24 16:24:31 +08:00
; SOFT-NEXT: mov %o0, %o2
; SOFT-NEXT: mov %o1, %o3
[Sparc] Add Soft Float support This change adds support for software floating point operations for Sparc targets. This is the first in a set of patches to enable software floating point on Sparc. The next patch will enable the option to be used with Clang. Differential Revision: http://reviews.llvm.org/D19265 llvm-svn: 269892
2016-05-18 17:14:13 +08:00
; SOFT-NEXT: mov %i3, %o0
; SOFT-NEXT: mov %i4, %o1
; SOFT-NEXT: call __adddf3
; SOFT-NEXT: nop
[Sparc] Return true in enableMultipleCopyHints(). Enable multiple COPY hints to eliminate more COPYs during register allocation. Note that this is something all targets should do, see https://reviews.llvm.org/D38128. Review: James Y Knight llvm-svn: 326028
2018-02-24 16:24:31 +08:00
; SOFT-NEXT: mov %o0, %o2
; SOFT-NEXT: mov %o1, %o3
[Sparc] Add Soft Float support This change adds support for software floating point operations for Sparc targets. This is the first in a set of patches to enable software floating point on Sparc. The next patch will enable the option to be used with Clang. Differential Revision: http://reviews.llvm.org/D19265 llvm-svn: 269892
2016-05-18 17:14:13 +08:00
; SOFT-NEXT: mov %i5, %o0
; SOFT-NEXT: mov %l3, %o1
; SOFT-NEXT: call __adddf3
; SOFT-NEXT: nop
[Sparc] Return true in enableMultipleCopyHints(). Enable multiple COPY hints to eliminate more COPYs during register allocation. Note that this is something all targets should do, see https://reviews.llvm.org/D38128. Review: James Y Knight llvm-svn: 326028
2018-02-24 16:24:31 +08:00
; SOFT-NEXT: mov %o0, %o2
; SOFT-NEXT: mov %o1, %o3
[Sparc] Add Soft Float support This change adds support for software floating point operations for Sparc targets. This is the first in a set of patches to enable software floating point on Sparc. The next patch will enable the option to be used with Clang. Differential Revision: http://reviews.llvm.org/D19265 llvm-svn: 269892
2016-05-18 17:14:13 +08:00
; SOFT-NEXT: mov %l1, %o0
; SOFT-NEXT: mov %l2, %o1
; SOFT-NEXT: call __adddf3
; SOFT-NEXT: nop
; SOFT-NEXT: mov %o0, %i0
; SOFT-NEXT: mov %o1, %i1
; SOFT-NEXT: mov %l0, %o0
; SOFT-NEXT: call __extendsfdf2
; SOFT-NEXT: nop
; SOFT-NEXT: mov %i0, %o2
; SOFT-NEXT: mov %i1, %o3
; SOFT-NEXT: call __adddf3
; SOFT-NEXT: nop
; SOFT-NEXT: mov %o0, %i0
; SOFT-NEXT: mov %o1, %i1
; CHECK: restore
[Sparc] Fix handling of double incoming arguments on sparc little-endian. On SparcV8, doubles get passed in two 32-bit integer registers. The call code was already handling endianness correctly, but the incoming argument code was not -- it got the two halves in opposite order. Also remove some dead code in LowerFormalArguments_32 to handle less-than-32bit values, which can't actually happen. Finally, add some test cases for the 32-bit calling convention, cribbed from the 64abi.ll test, and run for both big and little-endian. llvm-svn: 255668
2015-12-16 03:23:12 +08:00
define double @floatarg(double %a0, ; %i0,%i1
float %a1, ; %i2
double %a2, ; %i3, %i4
double %a3, ; %i5, [%fp+92] (using 4 bytes)
double %a4, ; [%fp+96] (using 8 bytes)
float %a5) { ; [%fp+104] (using 4 bytes)
%d1 = fpext float %a1 to double
%s1 = fadd double %a0, %d1
%s2 = fadd double %a2, %s1
%s3 = fadd double %a3, %s2
%s4 = fadd double %a4, %s3
%d5 = fpext float %a5 to double
%s5 = fadd double %d5, %s4
ret double %s5
}
; CHECK-LABEL: call_floatarg:
[Sparc] Add Soft Float support This change adds support for software floating point operations for Sparc targets. This is the first in a set of patches to enable software floating point on Sparc. The next patch will enable the option to be used with Clang. Differential Revision: http://reviews.llvm.org/D19265 llvm-svn: 269892
2016-05-18 17:14:13 +08:00
; HARD: save %sp, -112, %sp
; HARD: mov %i2, %o1
; HARD-NEXT: mov %i1, %o0
; HARD-NEXT: st %i0, [%sp+104]
; HARD-NEXT: std %o0, [%sp+96]
; HARD-NEXT: st %o1, [%sp+92]
; HARD-NEXT: mov %i0, %o2
Re-enable "[MachineCopyPropagation] Extend pass to do COPY source forwarding" Re-enable commit r323991 now that r325931 has been committed to make MachineOperand::isRenamable() check more conservative w.r.t. code changes and opt-in on a per-target basis. llvm-svn: 326208
2018-02-28 00:59:10 +08:00
; HARD-NEXT: mov %i1, %o3
[Sparc] Add Soft Float support This change adds support for software floating point operations for Sparc targets. This is the first in a set of patches to enable software floating point on Sparc. The next patch will enable the option to be used with Clang. Differential Revision: http://reviews.llvm.org/D19265 llvm-svn: 269892
2016-05-18 17:14:13 +08:00
; HARD-NEXT: mov %o1, %o4
Re-enable "[MachineCopyPropagation] Extend pass to do COPY source forwarding" Re-enable commit r323991 now that r325931 has been committed to make MachineOperand::isRenamable() check more conservative w.r.t. code changes and opt-in on a per-target basis. llvm-svn: 326208
2018-02-28 00:59:10 +08:00
; HARD-NEXT: mov %i1, %o5
[Sparc] Add Soft Float support This change adds support for software floating point operations for Sparc targets. This is the first in a set of patches to enable software floating point on Sparc. The next patch will enable the option to be used with Clang. Differential Revision: http://reviews.llvm.org/D19265 llvm-svn: 269892
2016-05-18 17:14:13 +08:00
; HARD-NEXT: call floatarg
; HARD: std %f0, [%i4]
; SOFT: st %i0, [%sp+104]
; SOFT-NEXT: st %i2, [%sp+100]
; SOFT-NEXT: st %i1, [%sp+96]
; SOFT-NEXT: st %i2, [%sp+92]
; SOFT-NEXT: mov %i1, %o0
; SOFT-NEXT: mov %i2, %o1
; SOFT-NEXT: mov %i0, %o2
; SOFT-NEXT: mov %i1, %o3
; SOFT-NEXT: mov %i2, %o4
; SOFT-NEXT: mov %i1, %o5
; SOFT-NEXT: call floatarg
; SOFT: std %o0, [%i4]
[Sparc] Fix handling of double incoming arguments on sparc little-endian. On SparcV8, doubles get passed in two 32-bit integer registers. The call code was already handling endianness correctly, but the incoming argument code was not -- it got the two halves in opposite order. Also remove some dead code in LowerFormalArguments_32 to handle less-than-32bit values, which can't actually happen. Finally, add some test cases for the 32-bit calling convention, cribbed from the 64abi.ll test, and run for both big and little-endian. llvm-svn: 255668
2015-12-16 03:23:12 +08:00
; CHECK: restore
define void @call_floatarg(float %f1, double %d2, float %f5, double *%p) {
%r = call double @floatarg(double %d2, float %f1, double %d2, double %d2,
double %d2, float %f1)
store double %r, double* %p
ret void
}
;; i64 arguments should effectively work the same as double: split
;; into two locations. This is different for little-endian vs big
;; endian, since the 64-bit math needs to be split
; CHECK-LABEL: i64arg:
; CHECK: save %sp, -96, %sp
[DAGCombiner] Set the right SDLoc on a newly-created zextload (1/N) Setting the right SDLoc on a newly-created zextload fixes a line table bug which resulted in non-linear stepping behavior. Several backend tests contained CHECK lines which relied on the IROrder inherited from the wrong SDLoc. This patch breaks that dependence where feasbile and regenerates test cases where not. In some cases, changing a node's IROrder may alter register allocation and spill behavior. This can affect performance. I have chosen not to prevent this by applying a "known good" IROrder to SDLocs, as this may hide a more general bug in the scheduler, or cause regressions on other test inputs. rdar://33755881, Part of: llvm.org/PR37262 Differential Revision: https://reviews.llvm.org/D45995 llvm-svn: 331300
2018-05-02 03:26:15 +08:00
; CHECK-BE: ld [%fp+104], %g2
; CHECK-BE-NEXT: ld [%fp+100], %g3
; CHECK-BE-NEXT: ld [%fp+96], %g4
; CHECK-BE-NEXT: ld [%fp+92], %l0
[Sparc] Fix handling of double incoming arguments on sparc little-endian. On SparcV8, doubles get passed in two 32-bit integer registers. The call code was already handling endianness correctly, but the incoming argument code was not -- it got the two halves in opposite order. Also remove some dead code in LowerFormalArguments_32 to handle less-than-32bit values, which can't actually happen. Finally, add some test cases for the 32-bit calling convention, cribbed from the 64abi.ll test, and run for both big and little-endian. llvm-svn: 255668
2015-12-16 03:23:12 +08:00
; CHECK-BE-NEXT: addcc %i1, %i2, %i1
; CHECK-BE-NEXT: addxcc %i0, 0, %i0
; CHECK-BE-NEXT: addcc %i4, %i1, %i1
; CHECK-BE-NEXT: addxcc %i3, %i0, %i0
[DAGCombiner] Set the right SDLoc on a newly-created zextload (1/N) Setting the right SDLoc on a newly-created zextload fixes a line table bug which resulted in non-linear stepping behavior. Several backend tests contained CHECK lines which relied on the IROrder inherited from the wrong SDLoc. This patch breaks that dependence where feasbile and regenerates test cases where not. In some cases, changing a node's IROrder may alter register allocation and spill behavior. This can affect performance. I have chosen not to prevent this by applying a "known good" IROrder to SDLocs, as this may hide a more general bug in the scheduler, or cause regressions on other test inputs. rdar://33755881, Part of: llvm.org/PR37262 Differential Revision: https://reviews.llvm.org/D45995 llvm-svn: 331300
2018-05-02 03:26:15 +08:00
; CHECK-BE-NEXT: addcc %l0, %i1, %i1
[Sparc] Fix handling of double incoming arguments on sparc little-endian. On SparcV8, doubles get passed in two 32-bit integer registers. The call code was already handling endianness correctly, but the incoming argument code was not -- it got the two halves in opposite order. Also remove some dead code in LowerFormalArguments_32 to handle less-than-32bit values, which can't actually happen. Finally, add some test cases for the 32-bit calling convention, cribbed from the 64abi.ll test, and run for both big and little-endian. llvm-svn: 255668
2015-12-16 03:23:12 +08:00
; CHECK-BE-NEXT: addxcc %i5, %i0, %i0
[DAGCombiner] Set the right SDLoc on a newly-created zextload (1/N) Setting the right SDLoc on a newly-created zextload fixes a line table bug which resulted in non-linear stepping behavior. Several backend tests contained CHECK lines which relied on the IROrder inherited from the wrong SDLoc. This patch breaks that dependence where feasbile and regenerates test cases where not. In some cases, changing a node's IROrder may alter register allocation and spill behavior. This can affect performance. I have chosen not to prevent this by applying a "known good" IROrder to SDLocs, as this may hide a more general bug in the scheduler, or cause regressions on other test inputs. rdar://33755881, Part of: llvm.org/PR37262 Differential Revision: https://reviews.llvm.org/D45995 llvm-svn: 331300
2018-05-02 03:26:15 +08:00
; CHECK-BE-NEXT: addcc %g3, %i1, %i1
; CHECK-BE-NEXT: addxcc %g4, %i0, %i0
[Sparc] Fix handling of double incoming arguments on sparc little-endian. On SparcV8, doubles get passed in two 32-bit integer registers. The call code was already handling endianness correctly, but the incoming argument code was not -- it got the two halves in opposite order. Also remove some dead code in LowerFormalArguments_32 to handle less-than-32bit values, which can't actually happen. Finally, add some test cases for the 32-bit calling convention, cribbed from the 64abi.ll test, and run for both big and little-endian. llvm-svn: 255668
2015-12-16 03:23:12 +08:00
; CHECK-BE-NEXT: addcc %g2, %i1, %i1
; CHECK-BE-NEXT: addxcc %i0, 0, %i0
;
[DAGCombiner] Set the right SDLoc on a newly-created zextload (1/N) Setting the right SDLoc on a newly-created zextload fixes a line table bug which resulted in non-linear stepping behavior. Several backend tests contained CHECK lines which relied on the IROrder inherited from the wrong SDLoc. This patch breaks that dependence where feasbile and regenerates test cases where not. In some cases, changing a node's IROrder may alter register allocation and spill behavior. This can affect performance. I have chosen not to prevent this by applying a "known good" IROrder to SDLocs, as this may hide a more general bug in the scheduler, or cause regressions on other test inputs. rdar://33755881, Part of: llvm.org/PR37262 Differential Revision: https://reviews.llvm.org/D45995 llvm-svn: 331300
2018-05-02 03:26:15 +08:00
; CHECK-LE: ld [%fp+104], %g2
; CHECK-LE-NEXT: ld [%fp+96], %g3
; CHECK-LE-NEXT: ld [%fp+100], %g4
; CHECK-LE-NEXT: ld [%fp+92], %l0
[Sparc] Fix handling of double incoming arguments on sparc little-endian. On SparcV8, doubles get passed in two 32-bit integer registers. The call code was already handling endianness correctly, but the incoming argument code was not -- it got the two halves in opposite order. Also remove some dead code in LowerFormalArguments_32 to handle less-than-32bit values, which can't actually happen. Finally, add some test cases for the 32-bit calling convention, cribbed from the 64abi.ll test, and run for both big and little-endian. llvm-svn: 255668
2015-12-16 03:23:12 +08:00
; CHECK-LE-NEXT: addcc %i0, %i2, %i0
; CHECK-LE-NEXT: addxcc %i1, 0, %i1
; CHECK-LE-NEXT: addcc %i3, %i0, %i0
; CHECK-LE-NEXT: addxcc %i4, %i1, %i1
; CHECK-LE-NEXT: addcc %i5, %i0, %i0
[DAGCombiner] Set the right SDLoc on a newly-created zextload (1/N) Setting the right SDLoc on a newly-created zextload fixes a line table bug which resulted in non-linear stepping behavior. Several backend tests contained CHECK lines which relied on the IROrder inherited from the wrong SDLoc. This patch breaks that dependence where feasbile and regenerates test cases where not. In some cases, changing a node's IROrder may alter register allocation and spill behavior. This can affect performance. I have chosen not to prevent this by applying a "known good" IROrder to SDLocs, as this may hide a more general bug in the scheduler, or cause regressions on other test inputs. rdar://33755881, Part of: llvm.org/PR37262 Differential Revision: https://reviews.llvm.org/D45995 llvm-svn: 331300
2018-05-02 03:26:15 +08:00
; CHECK-LE-NEXT: addxcc %l0, %i1, %i1
; CHECK-LE-NEXT: addcc %g3, %i0, %i0
[Sparc] Fix handling of double incoming arguments on sparc little-endian. On SparcV8, doubles get passed in two 32-bit integer registers. The call code was already handling endianness correctly, but the incoming argument code was not -- it got the two halves in opposite order. Also remove some dead code in LowerFormalArguments_32 to handle less-than-32bit values, which can't actually happen. Finally, add some test cases for the 32-bit calling convention, cribbed from the 64abi.ll test, and run for both big and little-endian. llvm-svn: 255668
2015-12-16 03:23:12 +08:00
; CHECK-LE-NEXT: addxcc %g4, %i1, %i1
; CHECK-LE-NEXT: addcc %g2, %i0, %i0
; CHECK-LE-NEXT: addxcc %i1, 0, %i1
; CHECK-NEXT: restore
define i64 @i64arg(i64 %a0, ; %i0,%i1
i32 %a1, ; %i2
i64 %a2, ; %i3, %i4
i64 %a3, ; %i5, [%fp+92] (using 4 bytes)
i64 %a4, ; [%fp+96] (using 8 bytes)
i32 %a5) { ; [%fp+104] (using 4 bytes)
%a1L = zext i32 %a1 to i64
%s1 = add i64 %a0, %a1L
%s2 = add i64 %a2, %s1
%s3 = add i64 %a3, %s2
%s4 = add i64 %a4, %s3
%a5L = zext i32 %a5 to i64
%s5 = add i64 %a5L, %s4
ret i64 %s5
}
; CHECK-LABEL: call_i64arg:
; CHECK: save %sp, -112, %sp
; CHECK: st %i0, [%sp+104]
; CHECK-NEXT: st %i2, [%sp+100]
; CHECK-NEXT: st %i1, [%sp+96]
; CHECK-NEXT: st %i2, [%sp+92]
; CHECK-NEXT: mov %i1, %o0
; CHECK-NEXT: mov %i2, %o1
; CHECK-NEXT: mov %i0, %o2
; CHECK-NEXT: mov %i1, %o3
; CHECK-NEXT: mov %i2, %o4
; CHECK-NEXT: mov %i1, %o5
; CHECK-NEXT: call i64arg
; CHECK: std %o0, [%i3]
; CHECK-NEXT: restore
define void @call_i64arg(i32 %a0, i64 %a1, i64* %p) {
%r = call i64 @i64arg(i64 %a1, i32 %a0, i64 %a1, i64 %a1, i64 %a1, i32 %a0)
store i64 %r, i64* %p
ret void
}