mirror of
https://github.com/Gericom/teak-llvm.git
synced 2025-06-19 11:35:51 -04:00
09d8ea5282
X86TargetLowering::EmitLoweredSelect presently detects sequences of CMOV pseudo instructions without accounting for debug intrinsics. This leads to different codegen with and without option -g, if a DBG_VALUE instruction lands in the middle of several lowered selects. Work around this by skipping over debug instructions when looking for CMOV sequences, and sinking those debug insts into the EmitLoweredSelect sunk block. This might slightly shift where variables appear in the instruction sequence, but won't re-order assignments. Differential Revision: https://reviews.llvm.org/D58672 llvm-svn: 355307
264 lines
9.7 KiB
LLVM
264 lines
9.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-linux-gnu -o - | FileCheck %s
|
|
|
|
; This test checks that only a single jae gets generated in the final code
|
|
; for lowering the CMOV pseudos that get created for this IR. The tricky part
|
|
; of this test is that it tests the special PHI operand rewriting code in
|
|
; X86TargetLowering::EmitLoweredSelect.
|
|
;
|
|
define double @foo1(float %p1, double %p2, double %p3) nounwind {
|
|
; CHECK-LABEL: foo1:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: xorps %xmm3, %xmm3
|
|
; CHECK-NEXT: ucomiss %xmm3, %xmm0
|
|
; CHECK-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
|
|
; CHECK-NEXT: jae .LBB0_1
|
|
; CHECK-NEXT: # %bb.2: # %entry
|
|
; CHECK-NEXT: addsd %xmm2, %xmm0
|
|
; CHECK-NEXT: jmp .LBB0_3
|
|
; CHECK-NEXT: .LBB0_1:
|
|
; CHECK-NEXT: addsd %xmm0, %xmm1
|
|
; CHECK-NEXT: movapd %xmm1, %xmm0
|
|
; CHECK-NEXT: movapd %xmm1, %xmm2
|
|
; CHECK-NEXT: .LBB0_3: # %entry
|
|
; CHECK-NEXT: subsd %xmm1, %xmm0
|
|
; CHECK-NEXT: addsd %xmm2, %xmm0
|
|
; CHECK-NEXT: retq
|
|
entry:
|
|
%c1 = fcmp oge float %p1, 0.000000e+00
|
|
%d0 = fadd double %p2, 1.25e0
|
|
%d1 = fadd double %p3, 1.25e0
|
|
%d2 = select i1 %c1, double %d0, double %d1
|
|
%d3 = select i1 %c1, double %d2, double %p2
|
|
%d4 = select i1 %c1, double %d3, double %p3
|
|
%d5 = fsub double %d2, %d3
|
|
%d6 = fadd double %d5, %d4
|
|
ret double %d6
|
|
}
|
|
|
|
; This test checks that only a single jae gets generated in the final code
|
|
; for lowering the CMOV pseudos that get created for this IR. The tricky part
|
|
; of this test is that it tests the special PHI operand rewriting code in
|
|
; X86TargetLowering::EmitLoweredSelect.
|
|
;
|
|
define double @foo2(float %p1, double %p2, double %p3) nounwind {
|
|
; CHECK-LABEL: foo2:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: xorps %xmm3, %xmm3
|
|
; CHECK-NEXT: ucomiss %xmm3, %xmm0
|
|
; CHECK-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
|
|
; CHECK-NEXT: jae .LBB1_1
|
|
; CHECK-NEXT: # %bb.2: # %entry
|
|
; CHECK-NEXT: addsd %xmm0, %xmm2
|
|
; CHECK-NEXT: movapd %xmm2, %xmm0
|
|
; CHECK-NEXT: movapd %xmm2, %xmm1
|
|
; CHECK-NEXT: jmp .LBB1_3
|
|
; CHECK-NEXT: .LBB1_1:
|
|
; CHECK-NEXT: addsd %xmm1, %xmm0
|
|
; CHECK-NEXT: .LBB1_3: # %entry
|
|
; CHECK-NEXT: subsd %xmm1, %xmm0
|
|
; CHECK-NEXT: addsd %xmm2, %xmm0
|
|
; CHECK-NEXT: retq
|
|
entry:
|
|
%c1 = fcmp oge float %p1, 0.000000e+00
|
|
%d0 = fadd double %p2, 1.25e0
|
|
%d1 = fadd double %p3, 1.25e0
|
|
%d2 = select i1 %c1, double %d0, double %d1
|
|
%d3 = select i1 %c1, double %p2, double %d2
|
|
%d4 = select i1 %c1, double %p3, double %d3
|
|
%d5 = fsub double %d2, %d3
|
|
%d6 = fadd double %d5, %d4
|
|
ret double %d6
|
|
}
|
|
|
|
; This test checks that only a single js gets generated in the final code
|
|
; for lowering the CMOV pseudos that get created for this IR. The tricky part
|
|
; of this test is that it tests the special PHI operand rewriting code in
|
|
; X86TargetLowering::EmitLoweredSelect. It also tests to make sure all
|
|
; the operands of the resulting instructions are from the proper places.
|
|
;
|
|
define double @foo3(i32 %p1, double %p2, double %p3,
|
|
; CHECK-LABEL: foo3:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: testl %edi, %edi
|
|
; CHECK-NEXT: js .LBB2_2
|
|
; CHECK-NEXT: # %bb.1: # %entry
|
|
; CHECK-NEXT: movapd %xmm2, %xmm1
|
|
; CHECK-NEXT: movapd %xmm2, %xmm0
|
|
; CHECK-NEXT: .LBB2_2: # %entry
|
|
; CHECK-NEXT: divsd %xmm1, %xmm0
|
|
; CHECK-NEXT: retq
|
|
double %p4, double %p5) nounwind {
|
|
entry:
|
|
%c1 = icmp slt i32 %p1, 0
|
|
%d2 = select i1 %c1, double %p2, double %p3
|
|
%d3 = select i1 %c1, double %p3, double %p4
|
|
%d4 = select i1 %c1, double %d2, double %d3
|
|
%d5 = fdiv double %d4, %d3
|
|
ret double %d5
|
|
}
|
|
|
|
; This test checks that only a single js gets generated in the final code
|
|
; for lowering the CMOV pseudos that get created for this IR. The tricky part
|
|
; of this test is that it tests the special PHI operand rewriting code in
|
|
; X86TargetLowering::EmitLoweredSelect. It also tests to make sure all
|
|
; the operands of the resulting instructions are from the proper places
|
|
; when the "opposite condition" handling code in the compiler is used.
|
|
; This should be the same code as foo3 above, because we use the opposite
|
|
; condition code in the second two selects, but we also swap the operands
|
|
; of the selects to give the same actual computation.
|
|
;
|
|
define double @foo4(i32 %p1, double %p2, double %p3,
|
|
; CHECK-LABEL: foo4:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: testl %edi, %edi
|
|
; CHECK-NEXT: js .LBB3_2
|
|
; CHECK-NEXT: # %bb.1: # %entry
|
|
; CHECK-NEXT: movapd %xmm2, %xmm1
|
|
; CHECK-NEXT: movapd %xmm2, %xmm0
|
|
; CHECK-NEXT: .LBB3_2: # %entry
|
|
; CHECK-NEXT: divsd %xmm1, %xmm0
|
|
; CHECK-NEXT: retq
|
|
double %p4, double %p5) nounwind {
|
|
entry:
|
|
%c1 = icmp slt i32 %p1, 0
|
|
%d2 = select i1 %c1, double %p2, double %p3
|
|
%c2 = icmp sge i32 %p1, 0
|
|
%d3 = select i1 %c2, double %p4, double %p3
|
|
%d4 = select i1 %c2, double %d3, double %d2
|
|
%d5 = fdiv double %d4, %d3
|
|
ret double %d5
|
|
}
|
|
|
|
; This test checks that only a single jae gets generated in the final code
|
|
; for lowering the CMOV pseudos that get created for this IR. The tricky part
|
|
; of this test is that it tests the special code in CodeGenPrepare.
|
|
;
|
|
define double @foo5(float %p1, double %p2, double %p3) nounwind {
|
|
; CHECK-LABEL: foo5:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: xorps %xmm3, %xmm3
|
|
; CHECK-NEXT: ucomiss %xmm3, %xmm0
|
|
; CHECK-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
|
|
; CHECK-NEXT: jae .LBB4_1
|
|
; CHECK-NEXT: # %bb.2: # %select.false
|
|
; CHECK-NEXT: addsd %xmm2, %xmm0
|
|
; CHECK-NEXT: .LBB4_3: # %select.end
|
|
; CHECK-NEXT: subsd %xmm1, %xmm0
|
|
; CHECK-NEXT: addsd %xmm2, %xmm0
|
|
; CHECK-NEXT: retq
|
|
; CHECK-NEXT: .LBB4_1:
|
|
; CHECK-NEXT: addsd %xmm0, %xmm1
|
|
; CHECK-NEXT: movapd %xmm1, %xmm0
|
|
; CHECK-NEXT: movapd %xmm1, %xmm2
|
|
; CHECK-NEXT: jmp .LBB4_3
|
|
entry:
|
|
%c1 = fcmp oge float %p1, 0.000000e+00
|
|
%d0 = fadd double %p2, 1.25e0
|
|
%d1 = fadd double %p3, 1.25e0
|
|
%d2 = select i1 %c1, double %d0, double %d1, !prof !0
|
|
%d3 = select i1 %c1, double %d2, double %p2, !prof !0
|
|
%d4 = select i1 %c1, double %d3, double %p3, !prof !0
|
|
%d5 = fsub double %d2, %d3
|
|
%d6 = fadd double %d5, %d4
|
|
ret double %d6
|
|
}
|
|
|
|
; We should expand select instructions into 3 conditional branches as their
|
|
; condtions are different.
|
|
;
|
|
define double @foo6(float %p1, double %p2, double %p3) nounwind {
|
|
; CHECK-LABEL: foo6:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: movaps %xmm0, %xmm3
|
|
; CHECK-NEXT: xorps %xmm0, %xmm0
|
|
; CHECK-NEXT: ucomiss %xmm0, %xmm3
|
|
; CHECK-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
|
|
; CHECK-NEXT: jae .LBB5_1
|
|
; CHECK-NEXT: # %bb.2: # %select.false
|
|
; CHECK-NEXT: addsd %xmm2, %xmm0
|
|
; CHECK-NEXT: .LBB5_3: # %select.end
|
|
; CHECK-NEXT: ucomiss {{.*}}(%rip), %xmm3
|
|
; CHECK-NEXT: movapd %xmm0, %xmm4
|
|
; CHECK-NEXT: jae .LBB5_5
|
|
; CHECK-NEXT: # %bb.4: # %select.false2
|
|
; CHECK-NEXT: movapd %xmm1, %xmm4
|
|
; CHECK-NEXT: .LBB5_5: # %select.end1
|
|
; CHECK-NEXT: ucomiss {{.*}}(%rip), %xmm3
|
|
; CHECK-NEXT: movapd %xmm4, %xmm1
|
|
; CHECK-NEXT: jae .LBB5_7
|
|
; CHECK-NEXT: # %bb.6: # %select.false4
|
|
; CHECK-NEXT: movapd %xmm2, %xmm1
|
|
; CHECK-NEXT: .LBB5_7: # %select.end3
|
|
; CHECK-NEXT: subsd %xmm4, %xmm0
|
|
; CHECK-NEXT: addsd %xmm1, %xmm0
|
|
; CHECK-NEXT: retq
|
|
; CHECK-NEXT: .LBB5_1:
|
|
; CHECK-NEXT: addsd %xmm1, %xmm0
|
|
; CHECK-NEXT: jmp .LBB5_3
|
|
entry:
|
|
%c1 = fcmp oge float %p1, 0.000000e+00
|
|
%c2 = fcmp oge float %p1, 1.000000e+00
|
|
%c3 = fcmp oge float %p1, 2.000000e+00
|
|
%d0 = fadd double %p2, 1.25e0
|
|
%d1 = fadd double %p3, 1.25e0
|
|
%d2 = select i1 %c1, double %d0, double %d1, !prof !0
|
|
%d3 = select i1 %c2, double %d2, double %p2, !prof !0
|
|
%d4 = select i1 %c3, double %d3, double %p3, !prof !0
|
|
%d5 = fsub double %d2, %d3
|
|
%d6 = fadd double %d5, %d4
|
|
ret double %d6
|
|
}
|
|
|
|
declare void @llvm.dbg.value(metadata, metadata, metadata)
|
|
|
|
; Like the test for @foo1, but check that the inserted dbg.value does not
|
|
; affect codegen. The CHECK items below should always be identical to @foo1,
|
|
; minus the DEBUG_VALUE line and changes in labels..
|
|
define double @foo1_g(float %p1, double %p2, double %p3) nounwind !dbg !4 {
|
|
; CHECK-LABEL: foo1_g:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: xorps %xmm3, %xmm3
|
|
; CHECK-NEXT: ucomiss %xmm3, %xmm0
|
|
; CHECK-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
|
|
; CHECK-NEXT: jae .LBB6_1
|
|
; CHECK-NEXT: # %bb.2: # %entry
|
|
; CHECK-NEXT: addsd %xmm2, %xmm0
|
|
; CHECK-NEXT: jmp .LBB6_3
|
|
; CHECK-NEXT: .LBB6_1:
|
|
; CHECK-NEXT: addsd %xmm0, %xmm1
|
|
; CHECK-NEXT: movapd %xmm1, %xmm0
|
|
; CHECK-NEXT: movapd %xmm1, %xmm2
|
|
; CHECK-NEXT: .LBB6_3: # %entry
|
|
; CHECK-NEXT: #DEBUG_VALUE: foobar:xyzzy <- undef
|
|
; CHECK-NEXT: subsd %xmm1, %xmm0
|
|
; CHECK-NEXT: addsd %xmm2, %xmm0
|
|
; CHECK-NEXT: retq
|
|
entry:
|
|
%c1 = fcmp oge float %p1, 0.000000e+00
|
|
%d0 = fadd double %p2, 1.25e0
|
|
%d1 = fadd double %p3, 1.25e0
|
|
%d2 = select i1 %c1, double %d0, double %d1
|
|
call void @llvm.dbg.value(metadata float undef, metadata !5, metadata !DIExpression()), !dbg !6
|
|
%d3 = select i1 %c1, double %d2, double %p2
|
|
%d4 = select i1 %c1, double %d3, double %p3
|
|
%d5 = fsub double %d2, %d3
|
|
%d6 = fadd double %d5, %d4
|
|
ret double %d6
|
|
}
|
|
|
|
!llvm.module.flags = !{!1}
|
|
!llvm.dbg.cu = !{!2}
|
|
|
|
!0 = !{!"branch_weights", i32 1, i32 2000}
|
|
!1 = !{i32 2, !"Debug Info Version", i32 3}
|
|
!2 = distinct !DICompileUnit(language: DW_LANG_C99, file: !3, producer: "clang", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, nameTableKind: None)
|
|
!3 = !DIFile(filename: "test.c", directory: ".")
|
|
!4 = distinct !DISubprogram(name: "foobar", scope: !2, file: !3, line: 1, type: !9, scopeLine: 3, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !2, retainedNodes: !8)
|
|
!5 = !DILocalVariable(name: "xyzzy", scope: !4, file: !3, line: 2, type: !7)
|
|
!6 = !DILocation(line: 1, column: 1, scope: !4)
|
|
!7 = !DIBasicType(name: "float", size: 32, encoding: DW_ATE_float)
|
|
!8 = !{!5}
|
|
!9 = !DISubroutineType(types: !10)
|
|
!10 = !{!7}
|