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/2013-05-17-CallFrame.ll

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

76 lines
2.5 KiB
LLVM
Raw Normal View History

UpdateTestChecks: sparc march handling Summary: Another target that prefers to use `-march` in tests ``` llvm/test/CodeGen/SPARC$ grep -ri mtriple | wc -l 25 llvm/test/CodeGen/SPARC$ grep -ri march | wc -l 165 ``` This test is being affected by a further patch, so regenerate it to better visualize the changes Reviewers: RKSimon, dcederman, gberry Reviewed By: RKSimon Subscribers: jyknight, fedor.sergeev, jrtc27, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62242 llvm-svn: 361381
2019-05-22 21:04:34 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
[SparcV9] Enable custom lowering of DYNAMIC_STACKALLOC in sparc64. llvm-svn: 195573
2013-11-25 01:41:41 +08:00
; RUN: llc -march=sparc < %s | FileCheck %s --check-prefix=V8
; RUN: llc -march=sparcv9 < %s | FileCheck %s --check-prefix=SPARC64
[Sparc] Don't overlap variable-sized allocas with other stack variables. On SparcV8, it was previously the case that a variable-sized alloca might overlap by 4-bytes the last fixed stack variable, effectively because 92 (the number of bytes reserved for the register spill area) != 96 (the offset added to SP for where to start a DYNAMIC_STACKALLOC). It's not as simple as changing 96 to 92, because variables that should be 8-byte aligned would then be misaligned. For now, simply increase the allocation size by 8 bytes for each dynamic allocation -- wastes space, but at least doesn't overlap. As the large comment says, doing this more efficiently will require larger changes in llvm. Also adds some test cases showing that we continue to not support dynamic stack allocation and over-alignment in the same function. llvm-svn: 285131
2016-10-26 06:13:28 +08:00
; (this should ideally be doing "add 4+7; and -8", instead of
; "add 7; and -8; add 8"; see comments in LowerDYNAMIC_STACKALLOC)
[Sparc] Implements hasReservedCallFrame and hasFP. This is to generate correct framesetup code when the function has variable sized allocas. llvm-svn: 182108
2013-05-17 23:14:34 +08:00
define void @variable_alloca_with_adj_call_stack(i32 %num) {
UpdateTestChecks: sparc march handling Summary: Another target that prefers to use `-march` in tests ``` llvm/test/CodeGen/SPARC$ grep -ri mtriple | wc -l 25 llvm/test/CodeGen/SPARC$ grep -ri march | wc -l 165 ``` This test is being affected by a further patch, so regenerate it to better visualize the changes Reviewers: RKSimon, dcederman, gberry Reviewed By: RKSimon Subscribers: jyknight, fedor.sergeev, jrtc27, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62242 llvm-svn: 361381
2019-05-22 21:04:34 +08:00
; V8-LABEL: variable_alloca_with_adj_call_stack:
; V8: .cfi_startproc
; V8-NEXT: ! %bb.0: ! %entry
; V8-NEXT: save %sp, -96, %sp
; V8-NEXT: .cfi_def_cfa_register %fp
; V8-NEXT: .cfi_window_save
Emit register names in cfi assembly directives Update .cfi_undefined, .cfi_register, and .cfi_return_column to print symbolic register arguments. Differential Revision: https://reviews.llvm.org/D74914
2020-02-25 22:01:26 +08:00
; V8-NEXT: .cfi_register %o7, %i7
UpdateTestChecks: sparc march handling Summary: Another target that prefers to use `-march` in tests ``` llvm/test/CodeGen/SPARC$ grep -ri mtriple | wc -l 25 llvm/test/CodeGen/SPARC$ grep -ri march | wc -l 165 ``` This test is being affected by a further patch, so regenerate it to better visualize the changes Reviewers: RKSimon, dcederman, gberry Reviewed By: RKSimon Subscribers: jyknight, fedor.sergeev, jrtc27, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62242 llvm-svn: 361381
2019-05-22 21:04:34 +08:00
; V8-NEXT: add %i0, 7, %i0
; V8-NEXT: and %i0, -8, %i0
; V8-NEXT: sub %sp, %i0, %i0
[DAGCombiner][X86][AArch64][SPARC][SystemZ] y - (x + C) -> (y - x) - C fold. Try 3 Summary: Direct sibling of D62223 patch. While i don't have a direct motivational pattern for this, it would seem to make sense to handle both patterns (or none), for symmetry? The aarch64 changes look neutral; sparc and systemz look like improvement (one less instruction each); x86 changes - 32bit case improves, 64bit case shows that LEA no longer gets constructed, which may be because that whole test is `-mattr=+slow-lea,+slow-3ops-lea` https://rise4fun.com/Alive/ffh This is a recommit, originally committed in rL361852, but reverted to investigate test-suite compile-time hangs, and then reverted in rL362109 to fix missing constant folds that were causing endless combine loops. Reviewers: RKSimon, craig.topper, spatel, t.p.northover Reviewed By: t.p.northover Subscribers: t.p.northover, jyknight, javed.absar, kristof.beyls, fedor.sergeev, jrtc27, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62252 llvm-svn: 362143
2019-05-31 04:37:18 +08:00
; V8-NEXT: add %i0, -8, %sp
; V8-NEXT: add %i0, 88, %o0
UpdateTestChecks: sparc march handling Summary: Another target that prefers to use `-march` in tests ``` llvm/test/CodeGen/SPARC$ grep -ri mtriple | wc -l 25 llvm/test/CodeGen/SPARC$ grep -ri march | wc -l 165 ``` This test is being affected by a further patch, so regenerate it to better visualize the changes Reviewers: RKSimon, dcederman, gberry Reviewed By: RKSimon Subscribers: jyknight, fedor.sergeev, jrtc27, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62242 llvm-svn: 361381
2019-05-22 21:04:34 +08:00
; V8-NEXT: add %sp, -16, %sp
; V8-NEXT: st %o0, [%sp+104]
; V8-NEXT: st %o0, [%sp+100]
; V8-NEXT: st %o0, [%sp+96]
; V8-NEXT: st %o0, [%sp+92]
; V8-NEXT: mov %o0, %o1
; V8-NEXT: mov %o0, %o2
; V8-NEXT: mov %o0, %o3
; V8-NEXT: mov %o0, %o4
; V8-NEXT: call foo
; V8-NEXT: mov %o0, %o5
; V8-NEXT: add %sp, 16, %sp
; V8-NEXT: ret
; V8-NEXT: restore
;
; SPARC64-LABEL: variable_alloca_with_adj_call_stack:
; SPARC64: .cfi_startproc
; SPARC64-NEXT: ! %bb.0: ! %entry
; SPARC64-NEXT: save %sp, -128, %sp
; SPARC64-NEXT: .cfi_def_cfa_register %fp
; SPARC64-NEXT: .cfi_window_save
Emit register names in cfi assembly directives Update .cfi_undefined, .cfi_register, and .cfi_return_column to print symbolic register arguments. Differential Revision: https://reviews.llvm.org/D74914
2020-02-25 22:01:26 +08:00
; SPARC64-NEXT: .cfi_register %o7, %i7
UpdateTestChecks: sparc march handling Summary: Another target that prefers to use `-march` in tests ``` llvm/test/CodeGen/SPARC$ grep -ri mtriple | wc -l 25 llvm/test/CodeGen/SPARC$ grep -ri march | wc -l 165 ``` This test is being affected by a further patch, so regenerate it to better visualize the changes Reviewers: RKSimon, dcederman, gberry Reviewed By: RKSimon Subscribers: jyknight, fedor.sergeev, jrtc27, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62242 llvm-svn: 361381
2019-05-22 21:04:34 +08:00
; SPARC64-NEXT: srl %i0, 0, %i0
; SPARC64-NEXT: add %i0, 15, %i0
; SPARC64-NEXT: sethi 4194303, %i1
; SPARC64-NEXT: or %i1, 1008, %i1
; SPARC64-NEXT: sethi 0, %i2
; SPARC64-NEXT: or %i2, 1, %i2
; SPARC64-NEXT: sllx %i2, 32, %i2
; SPARC64-NEXT: or %i2, %i1, %i1
; SPARC64-NEXT: and %i0, %i1, %i0
; SPARC64-NEXT: sub %sp, %i0, %i0
; SPARC64-NEXT: add %i0, 2175, %o0
; SPARC64-NEXT: mov %i0, %sp
; SPARC64-NEXT: add %sp, -80, %sp
; SPARC64-NEXT: stx %o0, [%sp+2247]
; SPARC64-NEXT: stx %o0, [%sp+2239]
; SPARC64-NEXT: stx %o0, [%sp+2231]
; SPARC64-NEXT: stx %o0, [%sp+2223]
; SPARC64-NEXT: mov %o0, %o1
; SPARC64-NEXT: mov %o0, %o2
; SPARC64-NEXT: mov %o0, %o3
; SPARC64-NEXT: mov %o0, %o4
; SPARC64-NEXT: call foo
; SPARC64-NEXT: mov %o0, %o5
; SPARC64-NEXT: add %sp, 80, %sp
; SPARC64-NEXT: ret
; SPARC64-NEXT: restore
[Sparc] Implements hasReservedCallFrame and hasFP. This is to generate correct framesetup code when the function has variable sized allocas. llvm-svn: 182108
2013-05-17 23:14:34 +08:00
entry:
%0 = alloca i8, i32 %num, align 8
call void @foo(i8* %0, i8* %0, i8* %0, i8* %0, i8* %0, i8* %0, i8* %0, i8* %0, i8* %0, i8* %0)
ret void
}
[Sparc] Don't overlap variable-sized allocas with other stack variables. On SparcV8, it was previously the case that a variable-sized alloca might overlap by 4-bytes the last fixed stack variable, effectively because 92 (the number of bytes reserved for the register spill area) != 96 (the offset added to SP for where to start a DYNAMIC_STACKALLOC). It's not as simple as changing 96 to 92, because variables that should be 8-byte aligned would then be misaligned. For now, simply increase the allocation size by 8 bytes for each dynamic allocation -- wastes space, but at least doesn't overlap. As the large comment says, doing this more efficiently will require larger changes in llvm. Also adds some test cases showing that we continue to not support dynamic stack allocation and over-alignment in the same function. llvm-svn: 285131
2016-10-26 06:13:28 +08:00
declare void @foo(i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*);