diff options
Diffstat (limited to 'llvm/test/CodeGen/X86')
-rw-r--r-- | llvm/test/CodeGen/X86/muloti.ll | 44 | ||||
-rw-r--r-- | llvm/test/CodeGen/X86/select.ll | 135 | ||||
-rw-r--r-- | llvm/test/CodeGen/X86/umulo-128-legalisation-lowering.ll | 196 | ||||
-rw-r--r-- | llvm/test/CodeGen/X86/umulo-64-legalisation-lowering.ll | 66 |
4 files changed, 298 insertions, 143 deletions
diff --git a/llvm/test/CodeGen/X86/muloti.ll b/llvm/test/CodeGen/X86/muloti.ll index 6c6198e400f..305f71e8eb3 100644 --- a/llvm/test/CodeGen/X86/muloti.ll +++ b/llvm/test/CodeGen/X86/muloti.ll @@ -32,50 +32,6 @@ nooverflow: ; preds = %entry ret %0 %tmp24 } -define %0 @foo(i64 %a.coerce0, i64 %a.coerce1, i64 %b.coerce0, i64 %b.coerce1) nounwind uwtable ssp { -entry: -; CHECK: foo - %retval = alloca i128, align 16 - %coerce = alloca i128, align 16 - %a.addr = alloca i128, align 16 - %coerce1 = alloca i128, align 16 - %b.addr = alloca i128, align 16 - %0 = bitcast i128* %coerce to %0* - %1 = getelementptr %0, %0* %0, i32 0, i32 0 - store i64 %a.coerce0, i64* %1 - %2 = getelementptr %0, %0* %0, i32 0, i32 1 - store i64 %a.coerce1, i64* %2 - %a = load i128, i128* %coerce, align 16 - store i128 %a, i128* %a.addr, align 16 - %3 = bitcast i128* %coerce1 to %0* - %4 = getelementptr %0, %0* %3, i32 0, i32 0 - store i64 %b.coerce0, i64* %4 - %5 = getelementptr %0, %0* %3, i32 0, i32 1 - store i64 %b.coerce1, i64* %5 - %b = load i128, i128* %coerce1, align 16 - store i128 %b, i128* %b.addr, align 16 - %tmp = load i128, i128* %a.addr, align 16 - %tmp2 = load i128, i128* %b.addr, align 16 - %6 = call %1 @llvm.umul.with.overflow.i128(i128 %tmp, i128 %tmp2) -; CHECK: cmov -; CHECK: divti3 - %7 = extractvalue %1 %6, 0 - %8 = extractvalue %1 %6, 1 - br i1 %8, label %overflow, label %nooverflow - -overflow: ; preds = %entry - call void @llvm.trap() - unreachable - -nooverflow: ; preds = %entry - store i128 %7, i128* %retval - %9 = bitcast i128* %retval to %0* - %10 = load %0, %0* %9, align 1 - ret %0 %10 -} - -declare %1 @llvm.umul.with.overflow.i128(i128, i128) nounwind readnone - declare %1 @llvm.smul.with.overflow.i128(i128, i128) nounwind readnone declare void @llvm.trap() nounwind diff --git a/llvm/test/CodeGen/X86/select.ll b/llvm/test/CodeGen/X86/select.ll index 7d518ab8751..c703c46f0a2 100644 --- a/llvm/test/CodeGen/X86/select.ll +++ b/llvm/test/CodeGen/X86/select.ll @@ -53,6 +53,7 @@ define i32 @test2() nounwind { ; GENERIC-NEXT: popq %rcx ; GENERIC-NEXT: retq ; GENERIC-NEXT: LBB1_1: ## %bb90 +; GENERIC-NEXT: ud2 ; ; ATOM-LABEL: test2: ; ATOM: ## %bb.0: ## %entry @@ -70,6 +71,7 @@ define i32 @test2() nounwind { ; ATOM-NEXT: popq %rcx ; ATOM-NEXT: retq ; ATOM-NEXT: LBB1_1: ## %bb90 +; ATOM-NEXT: ud2 ; ; MCU-LABEL: test2: ; MCU: # %bb.0: # %entry @@ -636,71 +638,6 @@ define i64 @test11a(i64 %x, i64 %y) nounwind readnone ssp noredzone { ret i64 %cond } - -declare noalias i8* @_Znam(i64) noredzone - -define noalias i8* @test12(i64 %count) nounwind ssp noredzone { -; GENERIC-LABEL: test12: -; GENERIC: ## %bb.0: ## %entry -; GENERIC-NEXT: movl $4, %ecx -; GENERIC-NEXT: movq %rdi, %rax -; GENERIC-NEXT: mulq %rcx -; GENERIC-NEXT: movq $-1, %rdi -; GENERIC-NEXT: cmovnoq %rax, %rdi -; GENERIC-NEXT: jmp __Znam ## TAILCALL -; -; ATOM-LABEL: test12: -; ATOM: ## %bb.0: ## %entry -; ATOM-NEXT: movq %rdi, %rax -; ATOM-NEXT: movl $4, %ecx -; ATOM-NEXT: movq $-1, %rdi -; ATOM-NEXT: mulq %rcx -; ATOM-NEXT: cmovnoq %rax, %rdi -; ATOM-NEXT: jmp __Znam ## TAILCALL -; -; MCU-LABEL: test12: -; MCU: # %bb.0: # %entry -; MCU-NEXT: pushl %ebp -; MCU-NEXT: pushl %ebx -; MCU-NEXT: pushl %edi -; MCU-NEXT: pushl %esi -; MCU-NEXT: movl %edx, %ebx -; MCU-NEXT: movl %eax, %ebp -; MCU-NEXT: movl $4, %ecx -; MCU-NEXT: mull %ecx -; MCU-NEXT: movl %eax, %esi -; MCU-NEXT: leal (%edx,%ebx,4), %edi -; MCU-NEXT: movl %edi, %edx -; MCU-NEXT: pushl $0 -; MCU-NEXT: pushl $4 -; MCU-NEXT: calll __udivdi3 -; MCU-NEXT: addl $8, %esp -; MCU-NEXT: xorl %ebx, %edx -; MCU-NEXT: xorl %ebp, %eax -; MCU-NEXT: orl %edx, %eax -; MCU-NEXT: movl $-1, %eax -; MCU-NEXT: movl $-1, %edx -; MCU-NEXT: jne .LBB14_2 -; MCU-NEXT: # %bb.1: # %entry -; MCU-NEXT: movl %esi, %eax -; MCU-NEXT: movl %edi, %edx -; MCU-NEXT: .LBB14_2: # %entry -; MCU-NEXT: popl %esi -; MCU-NEXT: popl %edi -; MCU-NEXT: popl %ebx -; MCU-NEXT: popl %ebp -; MCU-NEXT: jmp _Znam # TAILCALL -entry: - %A = tail call { i64, i1 } @llvm.umul.with.overflow.i64(i64 %count, i64 4) - %B = extractvalue { i64, i1 } %A, 1 - %C = extractvalue { i64, i1 } %A, 0 - %D = select i1 %B, i64 -1, i64 %C - %call = tail call noalias i8* @_Znam(i64 %D) nounwind noredzone - ret i8* %call -} - -declare { i64, i1 } @llvm.umul.with.overflow.i64(i64, i64) nounwind readnone - define i32 @test13(i32 %a, i32 %b) nounwind { ; GENERIC-LABEL: test13: ; GENERIC: ## %bb.0: @@ -862,10 +799,10 @@ define i8 @test18(i32 %x, i8 zeroext %a, i8 zeroext %b) nounwind { ; MCU-LABEL: test18: ; MCU: # %bb.0: ; MCU-NEXT: cmpl $15, %eax -; MCU-NEXT: jl .LBB20_2 +; MCU-NEXT: jl .LBB19_2 ; MCU-NEXT: # %bb.1: ; MCU-NEXT: movl %ecx, %edx -; MCU-NEXT: .LBB20_2: +; MCU-NEXT: .LBB19_2: ; MCU-NEXT: movl %edx, %eax ; MCU-NEXT: retl %cmp = icmp slt i32 %x, 15 @@ -902,10 +839,10 @@ define void @clamp_i8(i32 %src, i8* %dst) { ; GENERIC-NEXT: cmovlel %edi, %eax ; GENERIC-NEXT: cmpl $-128, %eax ; GENERIC-NEXT: movb $-128, %cl -; GENERIC-NEXT: jl LBB22_2 +; GENERIC-NEXT: jl LBB21_2 ; GENERIC-NEXT: ## %bb.1: ; GENERIC-NEXT: movl %eax, %ecx -; GENERIC-NEXT: LBB22_2: +; GENERIC-NEXT: LBB21_2: ; GENERIC-NEXT: movb %cl, (%rsi) ; GENERIC-NEXT: retq ; @@ -916,10 +853,10 @@ define void @clamp_i8(i32 %src, i8* %dst) { ; ATOM-NEXT: movb $-128, %cl ; ATOM-NEXT: cmovlel %edi, %eax ; ATOM-NEXT: cmpl $-128, %eax -; ATOM-NEXT: jl LBB22_2 +; ATOM-NEXT: jl LBB21_2 ; ATOM-NEXT: ## %bb.1: ; ATOM-NEXT: movl %eax, %ecx -; ATOM-NEXT: LBB22_2: +; ATOM-NEXT: LBB21_2: ; ATOM-NEXT: movb %cl, (%rsi) ; ATOM-NEXT: retq ; @@ -927,16 +864,16 @@ define void @clamp_i8(i32 %src, i8* %dst) { ; MCU: # %bb.0: ; MCU-NEXT: cmpl $127, %eax ; MCU-NEXT: movl $127, %ecx -; MCU-NEXT: jg .LBB22_2 +; MCU-NEXT: jg .LBB21_2 ; MCU-NEXT: # %bb.1: ; MCU-NEXT: movl %eax, %ecx -; MCU-NEXT: .LBB22_2: +; MCU-NEXT: .LBB21_2: ; MCU-NEXT: cmpl $-128, %ecx ; MCU-NEXT: movb $-128, %al -; MCU-NEXT: jl .LBB22_4 +; MCU-NEXT: jl .LBB21_4 ; MCU-NEXT: # %bb.3: ; MCU-NEXT: movl %ecx, %eax -; MCU-NEXT: .LBB22_4: +; MCU-NEXT: .LBB21_4: ; MCU-NEXT: movb %al, (%edx) ; MCU-NEXT: retl %cmp = icmp sgt i32 %src, 127 @@ -976,16 +913,16 @@ define void @clamp(i32 %src, i16* %dst) { ; MCU: # %bb.0: ; MCU-NEXT: cmpl $32767, %eax # imm = 0x7FFF ; MCU-NEXT: movl $32767, %ecx # imm = 0x7FFF -; MCU-NEXT: jg .LBB23_2 +; MCU-NEXT: jg .LBB22_2 ; MCU-NEXT: # %bb.1: ; MCU-NEXT: movl %eax, %ecx -; MCU-NEXT: .LBB23_2: +; MCU-NEXT: .LBB22_2: ; MCU-NEXT: cmpl $-32768, %ecx # imm = 0x8000 ; MCU-NEXT: movl $32768, %eax # imm = 0x8000 -; MCU-NEXT: jl .LBB23_4 +; MCU-NEXT: jl .LBB22_4 ; MCU-NEXT: # %bb.3: ; MCU-NEXT: movl %ecx, %eax -; MCU-NEXT: .LBB23_4: +; MCU-NEXT: .LBB22_4: ; MCU-NEXT: movw %ax, (%edx) ; MCU-NEXT: retl %cmp = icmp sgt i32 %src, 32767 @@ -1009,19 +946,19 @@ define void @test19() { ; CHECK-NEXT: movl $-1, %eax ; CHECK-NEXT: movb $1, %cl ; CHECK-NEXT: .p2align 4, 0x90 -; CHECK-NEXT: LBB24_1: ## %CF +; CHECK-NEXT: LBB23_1: ## %CF ; CHECK-NEXT: ## =>This Inner Loop Header: Depth=1 ; CHECK-NEXT: testb %cl, %cl -; CHECK-NEXT: jne LBB24_1 +; CHECK-NEXT: jne LBB23_1 ; CHECK-NEXT: ## %bb.2: ## %CF250 -; CHECK-NEXT: ## in Loop: Header=BB24_1 Depth=1 -; CHECK-NEXT: jne LBB24_1 +; CHECK-NEXT: ## in Loop: Header=BB23_1 Depth=1 +; CHECK-NEXT: jne LBB23_1 ; CHECK-NEXT: .p2align 4, 0x90 -; CHECK-NEXT: LBB24_3: ## %CF242 +; CHECK-NEXT: LBB23_3: ## %CF242 ; CHECK-NEXT: ## =>This Inner Loop Header: Depth=1 ; CHECK-NEXT: cmpl %eax, %eax ; CHECK-NEXT: ucomiss %xmm0, %xmm0 -; CHECK-NEXT: jp LBB24_3 +; CHECK-NEXT: jp LBB23_3 ; CHECK-NEXT: ## %bb.4: ## %CF244 ; CHECK-NEXT: retq ; @@ -1030,24 +967,24 @@ define void @test19() { ; MCU-NEXT: movl $-1, %ecx ; MCU-NEXT: movb $1, %al ; MCU-NEXT: .p2align 4, 0x90 -; MCU-NEXT: .LBB24_1: # %CF +; MCU-NEXT: .LBB23_1: # %CF ; MCU-NEXT: # =>This Inner Loop Header: Depth=1 ; MCU-NEXT: testb %al, %al -; MCU-NEXT: jne .LBB24_1 +; MCU-NEXT: jne .LBB23_1 ; MCU-NEXT: # %bb.2: # %CF250 -; MCU-NEXT: # in Loop: Header=BB24_1 Depth=1 -; MCU-NEXT: jne .LBB24_1 +; MCU-NEXT: # in Loop: Header=BB23_1 Depth=1 +; MCU-NEXT: jne .LBB23_1 ; MCU-NEXT: # %bb.3: # %CF242.preheader ; MCU-NEXT: fldz ; MCU-NEXT: .p2align 4, 0x90 -; MCU-NEXT: .LBB24_4: # %CF242 +; MCU-NEXT: .LBB23_4: # %CF242 ; MCU-NEXT: # =>This Inner Loop Header: Depth=1 ; MCU-NEXT: cmpl %eax, %ecx ; MCU-NEXT: fucom %st(0) ; MCU-NEXT: fnstsw %ax ; MCU-NEXT: # kill: def $ah killed $ah killed $ax ; MCU-NEXT: sahf -; MCU-NEXT: jp .LBB24_4 +; MCU-NEXT: jp .LBB23_4 ; MCU-NEXT: # %bb.5: # %CF244 ; MCU-NEXT: fstp %st(0) ; MCU-NEXT: retl @@ -1116,10 +1053,10 @@ define i16 @select_xor_1b(i16 %A, i8 %cond) { ; MCU-LABEL: select_xor_1b: ; MCU: # %bb.0: # %entry ; MCU-NEXT: testb $1, %dl -; MCU-NEXT: je .LBB26_2 +; MCU-NEXT: je .LBB25_2 ; MCU-NEXT: # %bb.1: ; MCU-NEXT: xorl $43, %eax -; MCU-NEXT: .LBB26_2: # %entry +; MCU-NEXT: .LBB25_2: # %entry ; MCU-NEXT: # kill: def $ax killed $ax killed $eax ; MCU-NEXT: retl entry: @@ -1168,10 +1105,10 @@ define i32 @select_xor_2b(i32 %A, i32 %B, i8 %cond) { ; MCU-LABEL: select_xor_2b: ; MCU: # %bb.0: # %entry ; MCU-NEXT: testb $1, %cl -; MCU-NEXT: je .LBB28_2 +; MCU-NEXT: je .LBB27_2 ; MCU-NEXT: # %bb.1: ; MCU-NEXT: xorl %edx, %eax -; MCU-NEXT: .LBB28_2: # %entry +; MCU-NEXT: .LBB27_2: # %entry ; MCU-NEXT: retl entry: %and = and i8 %cond, 1 @@ -1219,10 +1156,10 @@ define i32 @select_or_b(i32 %A, i32 %B, i8 %cond) { ; MCU-LABEL: select_or_b: ; MCU: # %bb.0: # %entry ; MCU-NEXT: testb $1, %cl -; MCU-NEXT: je .LBB30_2 +; MCU-NEXT: je .LBB29_2 ; MCU-NEXT: # %bb.1: ; MCU-NEXT: orl %edx, %eax -; MCU-NEXT: .LBB30_2: # %entry +; MCU-NEXT: .LBB29_2: # %entry ; MCU-NEXT: retl entry: %and = and i8 %cond, 1 @@ -1270,10 +1207,10 @@ define i32 @select_or_1b(i32 %A, i32 %B, i32 %cond) { ; MCU-LABEL: select_or_1b: ; MCU: # %bb.0: # %entry ; MCU-NEXT: testb $1, %cl -; MCU-NEXT: je .LBB32_2 +; MCU-NEXT: je .LBB31_2 ; MCU-NEXT: # %bb.1: ; MCU-NEXT: orl %edx, %eax -; MCU-NEXT: .LBB32_2: # %entry +; MCU-NEXT: .LBB31_2: # %entry ; MCU-NEXT: retl entry: %and = and i32 %cond, 1 diff --git a/llvm/test/CodeGen/X86/umulo-128-legalisation-lowering.ll b/llvm/test/CodeGen/X86/umulo-128-legalisation-lowering.ll new file mode 100644 index 00000000000..a1193afc626 --- /dev/null +++ b/llvm/test/CodeGen/X86/umulo-128-legalisation-lowering.ll @@ -0,0 +1,196 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu | FileCheck %s --check-prefixes=X64 +; RUN: llc < %s -mtriple=i686-unknown-linux-gnu | FileCheck %s --check-prefixes=X86 + +define { i128, i8 } @muloti_test(i128 %l, i128 %r) unnamed_addr #0 { +; X64-LABEL: muloti_test: +; X64: # %bb.0: # %start +; X64-NEXT: movq %rdx, %r8 +; X64-NEXT: testq %rcx, %rcx +; X64-NEXT: setne %al +; X64-NEXT: testq %rsi, %rsi +; X64-NEXT: setne %r9b +; X64-NEXT: andb %al, %r9b +; X64-NEXT: movq %rsi, %rax +; X64-NEXT: mulq %rdx +; X64-NEXT: movq %rax, %rsi +; X64-NEXT: seto %r10b +; X64-NEXT: movq %rcx, %rax +; X64-NEXT: mulq %rdi +; X64-NEXT: movq %rax, %rcx +; X64-NEXT: seto %r11b +; X64-NEXT: orb %r10b, %r11b +; X64-NEXT: addq %rsi, %rcx +; X64-NEXT: movq %rdi, %rax +; X64-NEXT: mulq %r8 +; X64-NEXT: addq %rcx, %rdx +; X64-NEXT: setb %cl +; X64-NEXT: orb %r11b, %cl +; X64-NEXT: orb %r9b, %cl +; X64-NEXT: retq +; +; X86-LABEL: muloti_test: +; X86: # %bb.0: # %start +; X86-NEXT: pushl %ebp +; X86-NEXT: .cfi_def_cfa_offset 8 +; X86-NEXT: pushl %ebx +; X86-NEXT: .cfi_def_cfa_offset 12 +; X86-NEXT: pushl %edi +; X86-NEXT: .cfi_def_cfa_offset 16 +; X86-NEXT: pushl %esi +; X86-NEXT: .cfi_def_cfa_offset 20 +; X86-NEXT: subl $28, %esp +; X86-NEXT: .cfi_def_cfa_offset 48 +; X86-NEXT: .cfi_offset %esi, -20 +; X86-NEXT: .cfi_offset %edi, -16 +; X86-NEXT: .cfi_offset %ebx, -12 +; X86-NEXT: .cfi_offset %ebp, -8 +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill +; X86-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ebx +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: mull %ebx +; X86-NEXT: movl %eax, %ecx +; X86-NEXT: seto {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill +; X86-NEXT: movl %esi, %eax +; X86-NEXT: mull %edi +; X86-NEXT: movl %eax, %esi +; X86-NEXT: seto {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill +; X86-NEXT: addl %ecx, %esi +; X86-NEXT: movl %edi, %eax +; X86-NEXT: mull %ebx +; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill +; X86-NEXT: movl %edx, %ecx +; X86-NEXT: addl %esi, %ecx +; X86-NEXT: setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill +; X86-NEXT: movl {{[0-9]+}}(%esp), %ebp +; X86-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-NEXT: mull %ebp +; X86-NEXT: movl %eax, %edi +; X86-NEXT: seto {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill +; X86-NEXT: movl {{[0-9]+}}(%esp), %ebx +; X86-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill +; X86-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-NEXT: mull %ebx +; X86-NEXT: movl %eax, %esi +; X86-NEXT: seto {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill +; X86-NEXT: addl %edi, %esi +; X86-NEXT: movl %ebx, %eax +; X86-NEXT: mull %ebp +; X86-NEXT: movl %ebp, %ebx +; X86-NEXT: movl %edx, %edi +; X86-NEXT: addl %esi, %edi +; X86-NEXT: setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill +; X86-NEXT: addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload +; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill +; X86-NEXT: adcl %ecx, %edi +; X86-NEXT: movl {{[0-9]+}}(%esp), %ebp +; X86-NEXT: movl %ebp, %eax +; X86-NEXT: movl %ebx, %ecx +; X86-NEXT: mull %ebx +; X86-NEXT: movl %edx, %ebx +; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill +; X86-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-NEXT: mull %ecx +; X86-NEXT: movl %edx, %esi +; X86-NEXT: movl %eax, %ecx +; X86-NEXT: addl %ebx, %ecx +; X86-NEXT: adcl $0, %esi +; X86-NEXT: movl %ebp, %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ebp +; X86-NEXT: mull %ebp +; X86-NEXT: movl %edx, %ebx +; X86-NEXT: addl %ecx, %eax +; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill +; X86-NEXT: adcl %esi, %ebx +; X86-NEXT: setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill +; X86-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-NEXT: mull %ebp +; X86-NEXT: movl %edx, %ecx +; X86-NEXT: movl %eax, %esi +; X86-NEXT: addl %ebx, %esi +; X86-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload +; X86-NEXT: adcl %eax, %ecx +; X86-NEXT: xorl %edx, %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-NEXT: mull %edx +; X86-NEXT: movl %edx, %ebp +; X86-NEXT: movl %eax, %ebx +; X86-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-NEXT: xorl %edx, %edx +; X86-NEXT: mull %edx +; X86-NEXT: addl %ebx, %eax +; X86-NEXT: adcl %ebp, %edx +; X86-NEXT: addl %esi, %eax +; X86-NEXT: adcl %ecx, %edx +; X86-NEXT: addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload +; X86-NEXT: adcl %edi, %edx +; X86-NEXT: setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill +; X86-NEXT: cmpl $0, {{[0-9]+}}(%esp) +; X86-NEXT: setne %cl +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: testl %esi, %esi +; X86-NEXT: setne %ch +; X86-NEXT: andb %cl, %ch +; X86-NEXT: movb {{[-0-9]+}}(%e{{[sb]}}p), %cl # 1-byte Reload +; X86-NEXT: orb {{[-0-9]+}}(%e{{[sb]}}p), %cl # 1-byte Folded Reload +; X86-NEXT: orb {{[-0-9]+}}(%e{{[sb]}}p), %cl # 1-byte Folded Reload +; X86-NEXT: orb %ch, %cl +; X86-NEXT: movb %cl, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill +; X86-NEXT: cmpl $0, {{[0-9]+}}(%esp) +; X86-NEXT: setne %cl +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: testl %edi, %edi +; X86-NEXT: setne %bh +; X86-NEXT: andb %cl, %bh +; X86-NEXT: movb {{[-0-9]+}}(%e{{[sb]}}p), %cl # 1-byte Reload +; X86-NEXT: orb {{[-0-9]+}}(%e{{[sb]}}p), %cl # 1-byte Folded Reload +; X86-NEXT: orb {{[-0-9]+}}(%e{{[sb]}}p), %cl # 1-byte Folded Reload +; X86-NEXT: movb %cl, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill +; X86-NEXT: orl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill +; X86-NEXT: setne %bl +; X86-NEXT: orl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload +; X86-NEXT: movl %esi, (%ecx) +; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload +; X86-NEXT: movl %esi, 4(%ecx) +; X86-NEXT: movl %eax, 8(%ecx) +; X86-NEXT: movl %edx, 12(%ecx) +; X86-NEXT: setne %al +; X86-NEXT: andb %bl, %al +; X86-NEXT: orb {{[-0-9]+}}(%e{{[sb]}}p), %al # 1-byte Folded Reload +; X86-NEXT: orb {{[-0-9]+}}(%e{{[sb]}}p), %al # 1-byte Folded Reload +; X86-NEXT: orb {{[-0-9]+}}(%e{{[sb]}}p), %al # 1-byte Folded Reload +; X86-NEXT: orb %bh, %al +; X86-NEXT: andb $1, %al +; X86-NEXT: movb %al, 16(%ecx) +; X86-NEXT: movl %ecx, %eax +; X86-NEXT: addl $28, %esp +; X86-NEXT: .cfi_def_cfa_offset 20 +; X86-NEXT: popl %esi +; X86-NEXT: .cfi_def_cfa_offset 16 +; X86-NEXT: popl %edi +; X86-NEXT: .cfi_def_cfa_offset 12 +; X86-NEXT: popl %ebx +; X86-NEXT: .cfi_def_cfa_offset 8 +; X86-NEXT: popl %ebp +; X86-NEXT: .cfi_def_cfa_offset 4 +; X86-NEXT: retl $4 +start: + %0 = tail call { i128, i1 } @llvm.umul.with.overflow.i128(i128 %l, i128 %r) #2 + %1 = extractvalue { i128, i1 } %0, 0 + %2 = extractvalue { i128, i1 } %0, 1 + %3 = zext i1 %2 to i8 + %4 = insertvalue { i128, i8 } undef, i128 %1, 0 + %5 = insertvalue { i128, i8 } %4, i8 %3, 1 + ret { i128, i8 } %5 +} + +; Function Attrs: nounwind readnone speculatable +declare { i128, i1 } @llvm.umul.with.overflow.i128(i128, i128) #1 + +attributes #0 = { nounwind readnone uwtable } +attributes #1 = { nounwind readnone speculatable } +attributes #2 = { nounwind } diff --git a/llvm/test/CodeGen/X86/umulo-64-legalisation-lowering.ll b/llvm/test/CodeGen/X86/umulo-64-legalisation-lowering.ll new file mode 100644 index 00000000000..044e5f2da28 --- /dev/null +++ b/llvm/test/CodeGen/X86/umulo-64-legalisation-lowering.ll @@ -0,0 +1,66 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc < %s -mtriple=i686-unknown-linux-gnu | FileCheck %s --check-prefixes=X86 + +define { i64, i8 } @mulodi_test(i64 %l, i64 %r) unnamed_addr #0 { +; X86-LABEL: mulodi_test: +; X86: # %bb.0: # %start +; X86-NEXT: pushl %ebp +; X86-NEXT: .cfi_def_cfa_offset 8 +; X86-NEXT: pushl %ebx +; X86-NEXT: .cfi_def_cfa_offset 12 +; X86-NEXT: pushl %edi +; X86-NEXT: .cfi_def_cfa_offset 16 +; X86-NEXT: pushl %esi +; X86-NEXT: .cfi_def_cfa_offset 20 +; X86-NEXT: .cfi_offset %esi, -20 +; X86-NEXT: .cfi_offset %edi, -16 +; X86-NEXT: .cfi_offset %ebx, -12 +; X86-NEXT: .cfi_offset %ebp, -8 +; X86-NEXT: movl {{[0-9]+}}(%esp), %ebp +; X86-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: testl %esi, %esi +; X86-NEXT: setne %dl +; X86-NEXT: testl %eax, %eax +; X86-NEXT: setne %bl +; X86-NEXT: andb %dl, %bl +; X86-NEXT: mull {{[0-9]+}}(%esp) +; X86-NEXT: movl %eax, %edi +; X86-NEXT: seto %cl +; X86-NEXT: movl %esi, %eax +; X86-NEXT: mull %ebp +; X86-NEXT: movl %eax, %esi +; X86-NEXT: seto %ch +; X86-NEXT: orb %cl, %ch +; X86-NEXT: addl %edi, %esi +; X86-NEXT: movl %ebp, %eax +; X86-NEXT: mull {{[0-9]+}}(%esp) +; X86-NEXT: addl %esi, %edx +; X86-NEXT: setb %cl +; X86-NEXT: orb %ch, %cl +; X86-NEXT: orb %bl, %cl +; X86-NEXT: popl %esi +; X86-NEXT: .cfi_def_cfa_offset 16 +; X86-NEXT: popl %edi +; X86-NEXT: .cfi_def_cfa_offset 12 +; X86-NEXT: popl %ebx +; X86-NEXT: .cfi_def_cfa_offset 8 +; X86-NEXT: popl %ebp +; X86-NEXT: .cfi_def_cfa_offset 4 +; X86-NEXT: retl +start: + %0 = tail call { i64, i1 } @llvm.umul.with.overflow.i64(i64 %l, i64 %r) #2 + %1 = extractvalue { i64, i1 } %0, 0 + %2 = extractvalue { i64, i1 } %0, 1 + %3 = zext i1 %2 to i8 + %4 = insertvalue { i64, i8 } undef, i64 %1, 0 + %5 = insertvalue { i64, i8 } %4, i8 %3, 1 + ret { i64, i8 } %5 +} + +; Function Attrs: nounwind readnone speculatable +declare { i64, i1 } @llvm.umul.with.overflow.i64(i64, i64) #1 + +attributes #0 = { nounwind readnone uwtable } +attributes #1 = { nounwind readnone speculatable } +attributes #2 = { nounwind } |