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/lcb2.ll

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

372 lines
10 KiB
LLVM
Raw Normal View History

[BPI] Improve static heuristics for integer comparisons Similarly as for pointers, even for integers a == b is usually false. GCC also uses this heuristic. Reviewed By: ebrevnov Differential Revision: https://reviews.llvm.org/D85781
2020-08-13 18:45:14 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
[mips][mips16] MIPS16 is not a CPU/Architecture but is an ASE. Summary: The -mcpu=mips16 option caused the Integrated Assembler to crash because it couldn't figure out the architecture revision number to write to the .MIPS.abiflags section. This CPU definition has been removed because, like microMIPS, MIPS16 is an ASE to a base architecture. Reviewers: vkalintiris Subscribers: rkotler, llvm-commits, dsanders Differential Revision: http://reviews.llvm.org/D13656 llvm-svn: 250407
2015-10-15 22:34:23 +08:00
; RUN: llc -mtriple=mipsel-linux-gnu -march=mipsel -mattr=mips16 -mattr=+soft-float -mips16-hard-float -relocation-model=static -mips16-constant-islands=true < %s | FileCheck %s -check-prefix=lcb
Check in conditional branches for constant islands. Still need to finish conditional branches for very large targets. That will be the next small patch. Everything now should in principle work as good (functionality wise) as without constant islands so we decided at Mips/Imagination to make constant islands the default for Mips16 now so that it will get excercised a lot and this port is still experimentatl though hopefully soon we will change the status. Some more cleanup and code review is in order but things are converging fast. llvm-svn: 195902
2013-11-28 08:56:37 +08:00
[mips][mips16] MIPS16 is not a CPU/Architecture but is an ASE. Summary: The -mcpu=mips16 option caused the Integrated Assembler to crash because it couldn't figure out the architecture revision number to write to the .MIPS.abiflags section. This CPU definition has been removed because, like microMIPS, MIPS16 is an ASE to a base architecture. Reviewers: vkalintiris Subscribers: rkotler, llvm-commits, dsanders Differential Revision: http://reviews.llvm.org/D13656 llvm-svn: 250407
2015-10-15 22:34:23 +08:00
; RUN: llc -mtriple=mipsel-linux-gnu -march=mipsel -mattr=mips16 -mattr=+soft-float -mips16-hard-float -relocation-model=static -mips16-constant-islands=true < %s | FileCheck %s -check-prefix=lcbn
Check in conditional branches for constant islands. Still need to finish conditional branches for very large targets. That will be the next small patch. Everything now should in principle work as good (functionality wise) as without constant islands so we decided at Mips/Imagination to make constant islands the default for Mips16 now so that it will get excercised a lot and this port is still experimentatl though hopefully soon we will change the status. Some more cleanup and code review is in order but things are converging fast. llvm-svn: 195902
2013-11-28 08:56:37 +08:00
@i = global i32 0, align 4
@j = common global i32 0, align 4
@k = common global i32 0, align 4
; Function Attrs: nounwind optsize
define i32 @bnez() #0 {
[BPI] Improve static heuristics for integer comparisons Similarly as for pointers, even for integers a == b is usually false. GCC also uses this heuristic. Reviewed By: ebrevnov Differential Revision: https://reviews.llvm.org/D85781
2020-08-13 18:45:14 +08:00
; lcb-LABEL: bnez:
; lcb: # %bb.0: # %entry
; lcb-NEXT: li $2, %hi(i)
; lcb-NEXT: sll $2, $2, 16
; lcb-NEXT: lw $3, %lo(i)($2)
; lcb-NEXT: bnez $3, $BB0_2
; lcb-NEXT: # %bb.1: # %if.then
; lcb-NEXT: li $3, 0
; lcb-NEXT: #APP
; lcb-NEXT: .set push
; lcb-NEXT: .set at
; lcb-NEXT: .set macro
; lcb-NEXT: .set reorder
; lcb-EMPTY:
; lcb-NEXT: .space 10000
; lcb-EMPTY:
; lcb-NEXT: .set pop
; lcb-NEXT: #NO_APP
; lcb-NEXT: sw $3, %lo(i)($2)
; lcb-NEXT: $BB0_2: # %if.end
; lcb-NEXT: li $2, 0
; lcb-NEXT: jrc $ra
;
; lcbn-LABEL: bnez:
; lcbn: # %bb.0: # %entry
; lcbn-NEXT: li $2, %hi(i)
; lcbn-NEXT: sll $2, $2, 16
; lcbn-NEXT: lw $3, %lo(i)($2)
; lcbn-NEXT: bnez $3, $BB0_2
; lcbn-NEXT: # %bb.1: # %if.then
; lcbn-NEXT: li $3, 0
; lcbn-NEXT: #APP
; lcbn-NEXT: .set push
; lcbn-NEXT: .set at
; lcbn-NEXT: .set macro
; lcbn-NEXT: .set reorder
; lcbn-EMPTY:
; lcbn-NEXT: .space 10000
; lcbn-EMPTY:
; lcbn-NEXT: .set pop
; lcbn-NEXT: #NO_APP
; lcbn-NEXT: sw $3, %lo(i)($2)
; lcbn-NEXT: $BB0_2: # %if.end
; lcbn-NEXT: li $2, 0
; lcbn-NEXT: jrc $ra
Check in conditional branches for constant islands. Still need to finish conditional branches for very large targets. That will be the next small patch. Everything now should in principle work as good (functionality wise) as without constant islands so we decided at Mips/Imagination to make constant islands the default for Mips16 now so that it will get excercised a lot and this port is still experimentatl though hopefully soon we will change the status. Some more cleanup and code review is in order but things are converging fast. llvm-svn: 195902
2013-11-28 08:56:37 +08:00
entry:
[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
%0 = load i32, i32* @i, align 4, !tbaa !1
Check in conditional branches for constant islands. Still need to finish conditional branches for very large targets. That will be the next small patch. Everything now should in principle work as good (functionality wise) as without constant islands so we decided at Mips/Imagination to make constant islands the default for Mips16 now so that it will get excercised a lot and this port is still experimentatl though hopefully soon we will change the status. Some more cleanup and code review is in order but things are converging fast. llvm-svn: 195902
2013-11-28 08:56:37 +08:00
%cmp = icmp eq i32 %0, 0
br i1 %cmp, label %if.then, label %if.end
if.then: ; preds = %entry
tail call void asm sideeffect ".space 10000", ""() #1, !srcloc !5
store i32 0, i32* @i, align 4, !tbaa !1
br label %if.end
if.end: ; preds = %if.then, %entry
ret i32 0
}
; Function Attrs: nounwind optsize
define i32 @beqz() #0 {
[BPI] Improve static heuristics for integer comparisons Similarly as for pointers, even for integers a == b is usually false. GCC also uses this heuristic. Reviewed By: ebrevnov Differential Revision: https://reviews.llvm.org/D85781
2020-08-13 18:45:14 +08:00
; lcb-LABEL: beqz:
; lcb: # %bb.0: # %entry
; lcb-NEXT: li $2, %hi(i)
; lcb-NEXT: sll $2, $2, 16
; lcb-NEXT: lw $2, %lo(i)($2)
; lcb-NEXT: beqz $2, $BB1_2
; lcb-NEXT: # %bb.1: # %if.else
; lcb-NEXT: li $2, %hi(j)
; lcb-NEXT: sll $2, $2, 16
; lcb-NEXT: li $3, 55
; lcb-NEXT: sw $3, %lo(j)($2)
; lcb-NEXT: #APP
; lcb-NEXT: .set push
; lcb-NEXT: .set at
; lcb-NEXT: .set macro
; lcb-NEXT: .set reorder
; lcb-EMPTY:
; lcb-NEXT: .space 10000
; lcb-EMPTY:
; lcb-NEXT: .set pop
; lcb-NEXT: #NO_APP
; lcb-NEXT: b $BB1_3
; lcb-NEXT: $BB1_2: # %if.then
; lcb-NEXT: li $2, %hi(j)
; lcb-NEXT: sll $2, $2, 16
; lcb-NEXT: li $3, 10
; lcb-NEXT: sw $3, %lo(j)($2)
; lcb-NEXT: #APP
; lcb-NEXT: .set push
; lcb-NEXT: .set at
; lcb-NEXT: .set macro
; lcb-NEXT: .set reorder
; lcb-EMPTY:
; lcb-NEXT: .space 10000
; lcb-EMPTY:
; lcb-NEXT: .set pop
; lcb-NEXT: #NO_APP
; lcb-NEXT: $BB1_3: # %if.end
; lcb-NEXT: li $2, 0
; lcb-NEXT: jrc $ra
;
; lcbn-LABEL: beqz:
; lcbn: # %bb.0: # %entry
; lcbn-NEXT: li $2, %hi(i)
; lcbn-NEXT: sll $2, $2, 16
; lcbn-NEXT: lw $2, %lo(i)($2)
; lcbn-NEXT: beqz $2, $BB1_2
; lcbn-NEXT: # %bb.1: # %if.else
; lcbn-NEXT: li $2, %hi(j)
; lcbn-NEXT: sll $2, $2, 16
; lcbn-NEXT: li $3, 55
; lcbn-NEXT: sw $3, %lo(j)($2)
; lcbn-NEXT: #APP
; lcbn-NEXT: .set push
; lcbn-NEXT: .set at
; lcbn-NEXT: .set macro
; lcbn-NEXT: .set reorder
; lcbn-EMPTY:
; lcbn-NEXT: .space 10000
; lcbn-EMPTY:
; lcbn-NEXT: .set pop
; lcbn-NEXT: #NO_APP
; lcbn-NEXT: b $BB1_3
; lcbn-NEXT: $BB1_2: # %if.then
; lcbn-NEXT: li $2, %hi(j)
; lcbn-NEXT: sll $2, $2, 16
; lcbn-NEXT: li $3, 10
; lcbn-NEXT: sw $3, %lo(j)($2)
; lcbn-NEXT: #APP
; lcbn-NEXT: .set push
; lcbn-NEXT: .set at
; lcbn-NEXT: .set macro
; lcbn-NEXT: .set reorder
; lcbn-EMPTY:
; lcbn-NEXT: .space 10000
; lcbn-EMPTY:
; lcbn-NEXT: .set pop
; lcbn-NEXT: #NO_APP
; lcbn-NEXT: $BB1_3: # %if.end
; lcbn-NEXT: li $2, 0
; lcbn-NEXT: jrc $ra
Check in conditional branches for constant islands. Still need to finish conditional branches for very large targets. That will be the next small patch. Everything now should in principle work as good (functionality wise) as without constant islands so we decided at Mips/Imagination to make constant islands the default for Mips16 now so that it will get excercised a lot and this port is still experimentatl though hopefully soon we will change the status. Some more cleanup and code review is in order but things are converging fast. llvm-svn: 195902
2013-11-28 08:56:37 +08:00
entry:
[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
%0 = load i32, i32* @i, align 4, !tbaa !1
Check in conditional branches for constant islands. Still need to finish conditional branches for very large targets. That will be the next small patch. Everything now should in principle work as good (functionality wise) as without constant islands so we decided at Mips/Imagination to make constant islands the default for Mips16 now so that it will get excercised a lot and this port is still experimentatl though hopefully soon we will change the status. Some more cleanup and code review is in order but things are converging fast. llvm-svn: 195902
2013-11-28 08:56:37 +08:00
%cmp = icmp eq i32 %0, 0
br i1 %cmp, label %if.then, label %if.else
if.then: ; preds = %entry
store i32 10, i32* @j, align 4, !tbaa !1
tail call void asm sideeffect ".space 10000", ""() #1, !srcloc !6
br label %if.end
if.else: ; preds = %entry
store i32 55, i32* @j, align 4, !tbaa !1
tail call void asm sideeffect ".space 10000", ""() #1, !srcloc !7
br label %if.end
if.end: ; preds = %if.else, %if.then
ret i32 0
}
; Function Attrs: nounwind optsize
define void @bteqz() #0 {
[BPI] Improve static heuristics for integer comparisons Similarly as for pointers, even for integers a == b is usually false. GCC also uses this heuristic. Reviewed By: ebrevnov Differential Revision: https://reviews.llvm.org/D85781
2020-08-13 18:45:14 +08:00
; lcb-LABEL: bteqz:
; lcb: # %bb.0: # %entry
; lcb-NEXT: li $2, %hi(j)
; lcb-NEXT: sll $2, $2, 16
; lcb-NEXT: lw $2, %lo(j)($2)
; lcb-NEXT: li $3, %hi(i)
; lcb-NEXT: sll $3, $3, 16
; lcb-NEXT: lw $3, %lo(i)($3)
; lcb-NEXT: cmp $3, $2
; lcb-NEXT: bteqz $BB2_2
; lcb-NEXT: # %bb.1: # %if.else
; lcb-NEXT: li $2, %hi(k)
; lcb-NEXT: sll $2, $2, 16
; lcb-NEXT: #APP
; lcb-NEXT: .set push
; lcb-NEXT: .set at
; lcb-NEXT: .set macro
; lcb-NEXT: .set reorder
; lcb-EMPTY:
; lcb-NEXT: .space 1000
; lcb-EMPTY:
; lcb-NEXT: .set pop
; lcb-NEXT: #NO_APP
; lcb-NEXT: li $3, 2
; lcb-NEXT: sw $3, %lo(k)($2)
; lcb-NEXT: jrc $ra
; lcb-NEXT: $BB2_2: # %if.then
; lcb-NEXT: li $2, %hi(k)
; lcb-NEXT: sll $2, $2, 16
; lcb-NEXT: li $3, 1
; lcb-NEXT: sw $3, %lo(k)($2)
; lcb-NEXT: #APP
; lcb-NEXT: .set push
; lcb-NEXT: .set at
; lcb-NEXT: .set macro
; lcb-NEXT: .set reorder
; lcb-EMPTY:
; lcb-NEXT: .space 1000
; lcb-EMPTY:
; lcb-NEXT: .set pop
; lcb-NEXT: #NO_APP
; lcb-NEXT: jrc $ra
;
; lcbn-LABEL: bteqz:
; lcbn: # %bb.0: # %entry
; lcbn-NEXT: li $2, %hi(j)
; lcbn-NEXT: sll $2, $2, 16
; lcbn-NEXT: lw $2, %lo(j)($2)
; lcbn-NEXT: li $3, %hi(i)
; lcbn-NEXT: sll $3, $3, 16
; lcbn-NEXT: lw $3, %lo(i)($3)
; lcbn-NEXT: cmp $3, $2
; lcbn-NEXT: bteqz $BB2_2
; lcbn-NEXT: # %bb.1: # %if.else
; lcbn-NEXT: li $2, %hi(k)
; lcbn-NEXT: sll $2, $2, 16
; lcbn-NEXT: #APP
; lcbn-NEXT: .set push
; lcbn-NEXT: .set at
; lcbn-NEXT: .set macro
; lcbn-NEXT: .set reorder
; lcbn-EMPTY:
; lcbn-NEXT: .space 1000
; lcbn-EMPTY:
; lcbn-NEXT: .set pop
; lcbn-NEXT: #NO_APP
; lcbn-NEXT: li $3, 2
; lcbn-NEXT: sw $3, %lo(k)($2)
; lcbn-NEXT: jrc $ra
; lcbn-NEXT: $BB2_2: # %if.then
; lcbn-NEXT: li $2, %hi(k)
; lcbn-NEXT: sll $2, $2, 16
; lcbn-NEXT: li $3, 1
; lcbn-NEXT: sw $3, %lo(k)($2)
; lcbn-NEXT: #APP
; lcbn-NEXT: .set push
; lcbn-NEXT: .set at
; lcbn-NEXT: .set macro
; lcbn-NEXT: .set reorder
; lcbn-EMPTY:
; lcbn-NEXT: .space 1000
; lcbn-EMPTY:
; lcbn-NEXT: .set pop
; lcbn-NEXT: #NO_APP
; lcbn-NEXT: jrc $ra
Check in conditional branches for constant islands. Still need to finish conditional branches for very large targets. That will be the next small patch. Everything now should in principle work as good (functionality wise) as without constant islands so we decided at Mips/Imagination to make constant islands the default for Mips16 now so that it will get excercised a lot and this port is still experimentatl though hopefully soon we will change the status. Some more cleanup and code review is in order but things are converging fast. llvm-svn: 195902
2013-11-28 08:56:37 +08:00
entry:
[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
%0 = load i32, i32* @i, align 4, !tbaa !1
%1 = load i32, i32* @j, align 4, !tbaa !1
Check in conditional branches for constant islands. Still need to finish conditional branches for very large targets. That will be the next small patch. Everything now should in principle work as good (functionality wise) as without constant islands so we decided at Mips/Imagination to make constant islands the default for Mips16 now so that it will get excercised a lot and this port is still experimentatl though hopefully soon we will change the status. Some more cleanup and code review is in order but things are converging fast. llvm-svn: 195902
2013-11-28 08:56:37 +08:00
%cmp = icmp eq i32 %0, %1
br i1 %cmp, label %if.then, label %if.else
if.then: ; preds = %entry
store i32 1, i32* @k, align 4, !tbaa !1
tail call void asm sideeffect ".space 1000", ""() #1, !srcloc !8
br label %if.end
if.else: ; preds = %entry
tail call void asm sideeffect ".space 1000", ""() #1, !srcloc !9
store i32 2, i32* @k, align 4, !tbaa !1
br label %if.end
if.end: ; preds = %if.else, %if.then
ret void
}
; Function Attrs: nounwind optsize
define void @btz() #0 {
[BPI] Improve static heuristics for integer comparisons Similarly as for pointers, even for integers a == b is usually false. GCC also uses this heuristic. Reviewed By: ebrevnov Differential Revision: https://reviews.llvm.org/D85781
2020-08-13 18:45:14 +08:00
; lcb-LABEL: btz:
; lcb: # %bb.0: # %entry
; lcb-NEXT: li $2, %hi(i)
; lcb-NEXT: sll $2, $2, 16
; lcb-NEXT: lw $4, %lo(i)($2)
; lcb-NEXT: li $3, %hi(j)
; lcb-NEXT: sll $3, $3, 16
; lcb-NEXT: lw $5, %lo(j)($3)
; lcb-NEXT: slt $5, $4
; lcb-NEXT: bteqz $BB3_2
; lcb-NEXT: $BB3_1: # %if.then
; lcb-NEXT: # =>This Inner Loop Header: Depth=1
; lcb-NEXT: #APP
; lcb-NEXT: .set push
; lcb-NEXT: .set at
; lcb-NEXT: .set macro
; lcb-NEXT: .set reorder
; lcb-EMPTY:
; lcb-NEXT: .space 60000
; lcb-EMPTY:
; lcb-NEXT: .set pop
; lcb-NEXT: #NO_APP
; lcb-NEXT: lw $4, %lo(i)($2)
; lcb-NEXT: lw $5, %lo(j)($3)
; lcb-NEXT: slt $5, $4
; lcb-NEXT: btnez $BB3_1
; lcb-NEXT: $BB3_2: # %if.end
; lcb-NEXT: jrc $ra
;
; lcbn-LABEL: btz:
; lcbn: # %bb.0: # %entry
; lcbn-NEXT: li $2, %hi(i)
; lcbn-NEXT: sll $2, $2, 16
; lcbn-NEXT: lw $4, %lo(i)($2)
; lcbn-NEXT: li $3, %hi(j)
; lcbn-NEXT: sll $3, $3, 16
; lcbn-NEXT: lw $5, %lo(j)($3)
; lcbn-NEXT: slt $5, $4
; lcbn-NEXT: bteqz $BB3_2
; lcbn-NEXT: $BB3_1: # %if.then
; lcbn-NEXT: # =>This Inner Loop Header: Depth=1
; lcbn-NEXT: #APP
; lcbn-NEXT: .set push
; lcbn-NEXT: .set at
; lcbn-NEXT: .set macro
; lcbn-NEXT: .set reorder
; lcbn-EMPTY:
; lcbn-NEXT: .space 60000
; lcbn-EMPTY:
; lcbn-NEXT: .set pop
; lcbn-NEXT: #NO_APP
; lcbn-NEXT: lw $4, %lo(i)($2)
; lcbn-NEXT: lw $5, %lo(j)($3)
; lcbn-NEXT: slt $5, $4
; lcbn-NEXT: btnez $BB3_1
; lcbn-NEXT: $BB3_2: # %if.end
; lcbn-NEXT: jrc $ra
Check in conditional branches for constant islands. Still need to finish conditional branches for very large targets. That will be the next small patch. Everything now should in principle work as good (functionality wise) as without constant islands so we decided at Mips/Imagination to make constant islands the default for Mips16 now so that it will get excercised a lot and this port is still experimentatl though hopefully soon we will change the status. Some more cleanup and code review is in order but things are converging fast. llvm-svn: 195902
2013-11-28 08:56:37 +08:00
entry:
[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
%0 = load i32, i32* @i, align 4, !tbaa !1
%1 = load i32, i32* @j, align 4, !tbaa !1
Check in conditional branches for constant islands. Still need to finish conditional branches for very large targets. That will be the next small patch. Everything now should in principle work as good (functionality wise) as without constant islands so we decided at Mips/Imagination to make constant islands the default for Mips16 now so that it will get excercised a lot and this port is still experimentatl though hopefully soon we will change the status. Some more cleanup and code review is in order but things are converging fast. llvm-svn: 195902
2013-11-28 08:56:37 +08:00
%cmp1 = icmp sgt i32 %0, %1
br i1 %cmp1, label %if.then, label %if.end
if.then: ; preds = %entry, %if.then
tail call void asm sideeffect ".space 60000", ""() #1, !srcloc !10
[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* @i, align 4, !tbaa !1
%3 = load i32, i32* @j, align 4, !tbaa !1
Check in conditional branches for constant islands. Still need to finish conditional branches for very large targets. That will be the next small patch. Everything now should in principle work as good (functionality wise) as without constant islands so we decided at Mips/Imagination to make constant islands the default for Mips16 now so that it will get excercised a lot and this port is still experimentatl though hopefully soon we will change the status. Some more cleanup and code review is in order but things are converging fast. llvm-svn: 195902
2013-11-28 08:56:37 +08:00
%cmp = icmp sgt i32 %2, %3
br i1 %cmp, label %if.then, label %if.end
if.end: ; preds = %if.then, %entry
ret void
}
Migrate function attribute "no-frame-pointer-elim"="false" to "frame-pointer"="none" as cleanups after D56351
2019-12-25 08:11:33 +08:00
attributes #0 = { nounwind optsize "less-precise-fpmad"="false" "frame-pointer"="none" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
Check in conditional branches for constant islands. Still need to finish conditional branches for very large targets. That will be the next small patch. Everything now should in principle work as good (functionality wise) as without constant islands so we decided at Mips/Imagination to make constant islands the default for Mips16 now so that it will get excercised a lot and this port is still experimentatl though hopefully soon we will change the status. Some more cleanup and code review is in order but things are converging fast. llvm-svn: 195902
2013-11-28 08:56:37 +08:00
attributes #1 = { nounwind }
!llvm.ident = !{!0}
IR: Make metadata typeless in assembly Now that `Metadata` is typeless, reflect that in the assembly. These are the matching assembly changes for the metadata/value split in r223802. - Only use the `metadata` type when referencing metadata from a call intrinsic -- i.e., only when it's used as a `Value`. - Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode` when referencing it from call intrinsics. So, assembly like this: define @foo(i32 %v) { call void @llvm.foo(metadata !{i32 %v}, metadata !0) call void @llvm.foo(metadata !{i32 7}, metadata !0) call void @llvm.foo(metadata !1, metadata !0) call void @llvm.foo(metadata !3, metadata !0) call void @llvm.foo(metadata !{metadata !3}, metadata !0) ret void, !bar !2 } !0 = metadata !{metadata !2} !1 = metadata !{i32* @global} !2 = metadata !{metadata !3} !3 = metadata !{} turns into this: define @foo(i32 %v) { call void @llvm.foo(metadata i32 %v, metadata !0) call void @llvm.foo(metadata i32 7, metadata !0) call void @llvm.foo(metadata i32* @global, metadata !0) call void @llvm.foo(metadata !3, metadata !0) call void @llvm.foo(metadata !{!3}, metadata !0) ret void, !bar !2 } !0 = !{!2} !1 = !{i32* @global} !2 = !{!3} !3 = !{} I wrote an upgrade script that handled almost all of the tests in llvm and many of the tests in cfe (even handling many `CHECK` lines). I've attached it (or will attach it in a moment if you're speedy) to PR21532 to help everyone update their out-of-tree testcases. This is part of PR21532. llvm-svn: 224257
2014-12-16 03:07:53 +08:00
!0 = !{!"clang version 3.5 (gitosis@dmz-portal.mips.com:clang.git ed197d08c90d82e1119774e10920e6f7a841c8ec) (gitosis@dmz-portal.mips.com:llvm.git b9235a363fa2dddb26ac01cbaed58efbc9eff392)"}
!1 = !{!2, !2, i64 0}
!2 = !{!"int", !3, i64 0}
!3 = !{!"omnipotent char", !4, i64 0}
!4 = !{!"Simple C/C++ TBAA"}
!5 = !{i32 59}
!6 = !{i32 156}
!7 = !{i32 210}
!8 = !{i32 299}
!9 = !{i32 340}
!10 = !{i32 412}