maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[Test] Two more tests on usub 

They are analogous to the existing tests, but use different starting offset
which can be important for some transforms.
This commit is contained in:
Max Kazantsev 2021-02-10 12:28:08 +07:00
parent a6439b5208
commit b910fab705
2 changed files with 103 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

65
llvm/test/CodeGen/X86/2020_12_02_decrementing_loop.ll
View File

@ -43,24 +43,67 @@ failure: ; preds = %backedge
unreachable
}
define i32 @test_02(i32* %p, i64 %len, i32 %x) {
; CHECK-LABEL: test_02:
; Similar to test_01, but we use offsetted pointer as base.
define i32 @test_01a(i32* %p, i64 %len, i32 %x) {
; CHECK-LABEL: test_01a:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: movq %rsi, %rax
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: LBB1_1: ## %loop
; CHECK-NEXT: ## =>This Inner Loop Header: Depth=1
; CHECK-NEXT: testq %rsi, %rsi
; CHECK-NEXT: je LBB1_4
; CHECK-NEXT: subq $1, %rax
; CHECK-NEXT: jb LBB1_4
; CHECK-NEXT: ## %bb.2: ## %backedge
; CHECK-NEXT: ## in Loop: Header=BB1_1 Depth=1
; CHECK-NEXT: cmpl %edx, -4(%rdi,%rsi,4)
; CHECK-NEXT: leaq -1(%rsi), %rsi
; CHECK-NEXT: cmpl %edx, -28(%rdi,%rsi,4)
; CHECK-NEXT: movq %rax, %rsi
; CHECK-NEXT: jne LBB1_1
; CHECK-NEXT: ## %bb.3: ## %failure
; CHECK-NEXT: ud2
; CHECK-NEXT: LBB1_4: ## %exit
; CHECK-NEXT: movl $-1, %eax
; CHECK-NEXT: retq
entry:
%base = getelementptr inbounds i32, i32* %p, i64 -6
br label %loop
loop: ; preds = %backedge, %entry
%iv = phi i64 [ %iv.next, %backedge ], [ %len, %entry ]
%iv.next = add nsw i64 %iv, -1
%cond_1 = icmp eq i64 %iv, 0
br i1 %cond_1, label %exit, label %backedge
backedge: ; preds = %loop
%addr = getelementptr inbounds i32, i32* %base, i64 %iv.next
%loaded = load atomic i32, i32* %addr unordered, align 4
%cond_2 = icmp eq i32 %loaded, %x
br i1 %cond_2, label %failure, label %loop
exit: ; preds = %loop
ret i32 -1
failure: ; preds = %backedge
unreachable
}
define i32 @test_02(i32* %p, i64 %len, i32 %x) {
; CHECK-LABEL: test_02:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: LBB2_1: ## %loop
; CHECK-NEXT: ## =>This Inner Loop Header: Depth=1
; CHECK-NEXT: testq %rsi, %rsi
; CHECK-NEXT: je LBB2_4
; CHECK-NEXT: ## %bb.2: ## %backedge
; CHECK-NEXT: ## in Loop: Header=BB2_1 Depth=1
; CHECK-NEXT: cmpl %edx, -4(%rdi,%rsi,4)
; CHECK-NEXT: leaq -1(%rsi), %rsi
; CHECK-NEXT: jne LBB2_1
; CHECK-NEXT: ## %bb.3: ## %failure
; CHECK-NEXT: ud2
; CHECK-NEXT: LBB2_4: ## %exit
; CHECK-NEXT: movl $-1, %eax
; CHECK-NEXT: retq
entry:
%start = add i64 %len, -1
br label %loop
@ -90,18 +133,18 @@ define i32 @test_03(i32* %p, i64 %len, i32 %x) {
; CHECK-LABEL: test_03:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: LBB2_1: ## %loop
; CHECK-NEXT: LBB3_1: ## %loop
; CHECK-NEXT: ## =>This Inner Loop Header: Depth=1
; CHECK-NEXT: testq %rsi, %rsi
; CHECK-NEXT: je LBB2_4
; CHECK-NEXT: je LBB3_4
; CHECK-NEXT: ## %bb.2: ## %backedge
; CHECK-NEXT: ## in Loop: Header=BB2_1 Depth=1
; CHECK-NEXT: ## in Loop: Header=BB3_1 Depth=1
; CHECK-NEXT: cmpl %edx, -4(%rdi,%rsi,4)
; CHECK-NEXT: leaq -1(%rsi), %rsi
; CHECK-NEXT: jne LBB2_1
; CHECK-NEXT: jne LBB3_1
; CHECK-NEXT: ## %bb.3: ## %failure
; CHECK-NEXT: ud2
; CHECK-NEXT: LBB2_4: ## %exit
; CHECK-NEXT: LBB3_4: ## %exit
; CHECK-NEXT: movl $-1, %eax
; CHECK-NEXT: retq
entry:

49
llvm/test/CodeGen/X86/usub_inc_iv.ll
View File

@ -48,6 +48,55 @@ failure: ; preds = %backedge
unreachable
}
; Similar to test_01, but with different offset.
define i32 @test_01a(i32* %p, i64 %len, i32 %x) {
; CHECK-LABEL: @test_01a(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[MATH:%.*]], [[BACKEDGE:%.*]] ], [ [[LEN:%.*]], [[ENTRY:%.*]] ]
; CHECK-NEXT: [[TMP0:%.*]] = call { i64, i1 } @llvm.usub.with.overflow.i64(i64 [[IV]], i64 1)
; CHECK-NEXT: [[MATH]] = extractvalue { i64, i1 } [[TMP0]], 0
; CHECK-NEXT: [[OV:%.*]] = extractvalue { i64, i1 } [[TMP0]], 1
; CHECK-NEXT: br i1 [[OV]], label [[EXIT:%.*]], label [[BACKEDGE]]
; CHECK: backedge:
; CHECK-NEXT: [[SUNKADDR:%.*]] = mul i64 [[IV]], 4
; CHECK-NEXT: [[TMP1:%.*]] = bitcast i32* [[P:%.*]] to i8*
; CHECK-NEXT: [[SUNKADDR1:%.*]] = getelementptr i8, i8* [[TMP1]], i64 [[SUNKADDR]]
; CHECK-NEXT: [[SUNKADDR2:%.*]] = getelementptr i8, i8* [[SUNKADDR1]], i64 -28
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i8* [[SUNKADDR2]] to i32*
; CHECK-NEXT: [[LOADED:%.*]] = load atomic i32, i32* [[TMP2]] unordered, align 4
; CHECK-NEXT: [[COND_2:%.*]] = icmp eq i32 [[LOADED]], [[X:%.*]]
; CHECK-NEXT: br i1 [[COND_2]], label [[FAILURE:%.*]], label [[LOOP]]
; CHECK: exit:
; CHECK-NEXT: ret i32 -1
; CHECK: failure:
; CHECK-NEXT: unreachable
;
entry:
%scevgep = getelementptr i32, i32* %p, i64 -7
br label %loop
loop: ; preds = %backedge, %entry
%iv = phi i64 [ %iv.next, %backedge ], [ %len, %entry ]
%iv.next = add i64 %iv, -1
%cond_1 = icmp eq i64 %iv, 0
br i1 %cond_1, label %exit, label %backedge
backedge: ; preds = %loop
%scevgep1 = getelementptr i32, i32* %scevgep, i64 %iv
%loaded = load atomic i32, i32* %scevgep1 unordered, align 4
%cond_2 = icmp eq i32 %loaded, %x
br i1 %cond_2, label %failure, label %loop
exit: ; preds = %loop
ret i32 -1
failure: ; preds = %backedge
unreachable
}
; TODO: We can use trick with usub here.
define i32 @test_02(i32* %p, i64 %len, i32 %x) {
; CHECK-LABEL: @test_02(