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/X86/codegen-prepare-uaddo.ll

271 lines
8.1 KiB
LLVM
Raw Normal View History

[X86] Add CGP tests for PR40486 llvm-svn: 352316
2019-01-27 22:04:45 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s
; PR31754
;
; #include <x86intrin.h>
; using u64 = unsigned long long;
;
; template<u64 K>
; void test(u64& alo, u64& ahi)
; {
; u64 blo = K;
; u64 bhi = 0;
; bool cf = (alo += blo) < blo;
; _addcarry_u64(cf, ahi, bhi, &ahi);
; }
;
; template void test<0ull>(u64&, u64&);
; template void test<1ull>(u64&, u64&);
; template void test<2ull>(u64&, u64&);
; template void test<3ull>(u64&, u64&);
; template void test<4ull>(u64&, u64&);
; template void test<0x7fffffffffffffffull>(u64&, u64&);
; template void test<0x8000000000000000ull>(u64&, u64&);
; template void test<0x8000000000000001ull>(u64&, u64&);
; template void test<0xffffffff80000000ull>(u64&, u64&);
; template void test<0xfffffffffffffffdull>(u64&, u64&);
; template void test<0xfffffffffffffffeull>(u64&, u64&);
; template void test<0xffffffffffffffffull>(u64&, u64&);
define void @test_0(i64*, i64*) {
; CHECK-LABEL: test_0:
; CHECK: # %bb.0:
; CHECK-NEXT: retq
%3 = load i64, i64* %1, align 8
%4 = tail call { i8, i64 } @llvm.x86.addcarry.64(i8 0, i64 %3, i64 0)
%5 = extractvalue { i8, i64 } %4, 1
store i64 %5, i64* %1, align 8
ret void
}
define void @test_1(i64*, i64*) {
; CHECK-LABEL: test_1:
; CHECK: # %bb.0:
[X86] Lower ISD::UADDO to use the Z flag instead of C flag when the RHS is a constant 1 to encourage INC formation. Summary: Add an additional combine to combineCarryThroughADD to reverse it back to the C flag to avoid regressions. I believe this catches the cases that D57547 got. Reviewers: RKSimon, spatel Reviewed By: spatel Subscribers: javed.absar, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D57637 llvm-svn: 352984
2019-02-03 15:25:06 +08:00
; CHECK-NEXT: addq $1, (%rdi)
[X86] Add CGP tests for PR40486 llvm-svn: 352316
2019-01-27 22:04:45 +08:00
; CHECK-NEXT: adcq $0, (%rsi)
; CHECK-NEXT: retq
%3 = load i64, i64* %0, align 8
%4 = add i64 %3, 1
store i64 %4, i64* %0, align 8
%5 = icmp eq i64 %4, 0
%6 = zext i1 %5 to i8
%7 = load i64, i64* %1, align 8
%8 = tail call { i8, i64 } @llvm.x86.addcarry.64(i8 %6, i64 %7, i64 0)
%9 = extractvalue { i8, i64 } %8, 1
store i64 %9, i64* %1, align 8
ret void
}
define void @test_2(i64*, i64*) {
; CHECK-LABEL: test_2:
; CHECK: # %bb.0:
; CHECK-NEXT: addq $2, (%rdi)
; CHECK-NEXT: adcq $0, (%rsi)
; CHECK-NEXT: retq
%3 = load i64, i64* %0, align 8
%4 = add i64 %3, 2
store i64 %4, i64* %0, align 8
%5 = icmp ult i64 %4, 2
%6 = zext i1 %5 to i8
%7 = load i64, i64* %1, align 8
%8 = tail call { i8, i64 } @llvm.x86.addcarry.64(i8 %6, i64 %7, i64 0)
%9 = extractvalue { i8, i64 } %8, 1
store i64 %9, i64* %1, align 8
ret void
}
define void @test_3(i64*, i64*) {
; CHECK-LABEL: test_3:
; CHECK: # %bb.0:
; CHECK-NEXT: addq $3, (%rdi)
; CHECK-NEXT: adcq $0, (%rsi)
; CHECK-NEXT: retq
%3 = load i64, i64* %0, align 8
%4 = add i64 %3, 3
store i64 %4, i64* %0, align 8
%5 = icmp ult i64 %4, 3
%6 = zext i1 %5 to i8
%7 = load i64, i64* %1, align 8
%8 = tail call { i8, i64 } @llvm.x86.addcarry.64(i8 %6, i64 %7, i64 0)
%9 = extractvalue { i8, i64 } %8, 1
store i64 %9, i64* %1, align 8
ret void
}
define void @test_4(i64*, i64*) {
; CHECK-LABEL: test_4:
; CHECK: # %bb.0:
; CHECK-NEXT: addq $4, (%rdi)
; CHECK-NEXT: adcq $0, (%rsi)
; CHECK-NEXT: retq
%3 = load i64, i64* %0, align 8
%4 = add i64 %3, 4
store i64 %4, i64* %0, align 8
%5 = icmp ult i64 %4, 4
%6 = zext i1 %5 to i8
%7 = load i64, i64* %1, align 8
%8 = tail call { i8, i64 } @llvm.x86.addcarry.64(i8 %6, i64 %7, i64 0)
%9 = extractvalue { i8, i64 } %8, 1
store i64 %9, i64* %1, align 8
ret void
}
define void @test_9223372036854775807(i64*, i64*) {
; CHECK-LABEL: test_9223372036854775807:
; CHECK: # %bb.0:
; CHECK-NEXT: movabsq $9223372036854775807, %rax # imm = 0x7FFFFFFFFFFFFFFF
; CHECK-NEXT: addq %rax, (%rdi)
; CHECK-NEXT: adcq $0, (%rsi)
; CHECK-NEXT: retq
%3 = load i64, i64* %0, align 8
%4 = add i64 %3, 9223372036854775807
store i64 %4, i64* %0, align 8
%5 = icmp ult i64 %4, 9223372036854775807
%6 = zext i1 %5 to i8
%7 = load i64, i64* %1, align 8
%8 = tail call { i8, i64 } @llvm.x86.addcarry.64(i8 %6, i64 %7, i64 0)
%9 = extractvalue { i8, i64 } %8, 1
store i64 %9, i64* %1, align 8
ret void
}
define void @test_9223372036854775808(i64*, i64*) {
; CHECK-LABEL: test_9223372036854775808:
; CHECK: # %bb.0:
; CHECK-NEXT: movq (%rdi), %rax
; CHECK-NEXT: movabsq $-9223372036854775808, %rcx # imm = 0x8000000000000000
; CHECK-NEXT: xorq %rax, %rcx
; CHECK-NEXT: movq %rcx, (%rdi)
; CHECK-NEXT: shrq $63, %rax
; CHECK-NEXT: addb $-1, %al
; CHECK-NEXT: adcq $0, (%rsi)
; CHECK-NEXT: retq
%3 = load i64, i64* %0, align 8
%4 = xor i64 %3, -9223372036854775808
store i64 %4, i64* %0, align 8
%5 = lshr i64 %3, 63
%6 = trunc i64 %5 to i8
%7 = load i64, i64* %1, align 8
%8 = tail call { i8, i64 } @llvm.x86.addcarry.64(i8 %6, i64 %7, i64 0)
%9 = extractvalue { i8, i64 } %8, 1
store i64 %9, i64* %1, align 8
ret void
}
define void @test_9223372036854775809(i64*, i64*) {
; CHECK-LABEL: test_9223372036854775809:
; CHECK: # %bb.0:
; CHECK-NEXT: movabsq $-9223372036854775807, %rax # imm = 0x8000000000000001
; CHECK-NEXT: addq %rax, (%rdi)
; CHECK-NEXT: adcq $0, (%rsi)
; CHECK-NEXT: retq
%3 = load i64, i64* %0, align 8
%4 = add i64 %3, -9223372036854775807
store i64 %4, i64* %0, align 8
%5 = icmp ult i64 %4, -9223372036854775807
%6 = zext i1 %5 to i8
%7 = load i64, i64* %1, align 8
%8 = tail call { i8, i64 } @llvm.x86.addcarry.64(i8 %6, i64 %7, i64 0)
%9 = extractvalue { i8, i64 } %8, 1
store i64 %9, i64* %1, align 8
ret void
}
define void @test_18446744071562067968(i64*, i64*) {
; CHECK-LABEL: test_18446744071562067968:
; CHECK: # %bb.0:
; CHECK-NEXT: addq $-2147483648, (%rdi) # imm = 0x80000000
; CHECK-NEXT: adcq $0, (%rsi)
; CHECK-NEXT: retq
%3 = load i64, i64* %0, align 8
%4 = add i64 %3, -2147483648
store i64 %4, i64* %0, align 8
%5 = icmp ult i64 %4, -2147483648
%6 = zext i1 %5 to i8
%7 = load i64, i64* %1, align 8
%8 = tail call { i8, i64 } @llvm.x86.addcarry.64(i8 %6, i64 %7, i64 0)
%9 = extractvalue { i8, i64 } %8, 1
store i64 %9, i64* %1, align 8
ret void
}
define void @test_18446744073709551613(i64*, i64*) {
; CHECK-LABEL: test_18446744073709551613:
; CHECK: # %bb.0:
; CHECK-NEXT: addq $-3, (%rdi)
; CHECK-NEXT: adcq $0, (%rsi)
; CHECK-NEXT: retq
%3 = load i64, i64* %0, align 8
%4 = add i64 %3, -3
store i64 %4, i64* %0, align 8
%5 = icmp ult i64 %4, -3
%6 = zext i1 %5 to i8
%7 = load i64, i64* %1, align 8
%8 = tail call { i8, i64 } @llvm.x86.addcarry.64(i8 %6, i64 %7, i64 0)
%9 = extractvalue { i8, i64 } %8, 1
store i64 %9, i64* %1, align 8
ret void
}
define void @test_18446744073709551614(i64*, i64*) {
; CHECK-LABEL: test_18446744073709551614:
; CHECK: # %bb.0:
; CHECK-NEXT: addq $-2, (%rdi)
; CHECK-NEXT: adcq $0, (%rsi)
; CHECK-NEXT: retq
%3 = load i64, i64* %0, align 8
%4 = add i64 %3, -2
store i64 %4, i64* %0, align 8
%5 = icmp ult i64 %4, -2
%6 = zext i1 %5 to i8
%7 = load i64, i64* %1, align 8
%8 = tail call { i8, i64 } @llvm.x86.addcarry.64(i8 %6, i64 %7, i64 0)
%9 = extractvalue { i8, i64 } %8, 1
store i64 %9, i64* %1, align 8
ret void
}
define void @test_18446744073709551615(i64*, i64*) {
; CHECK-LABEL: test_18446744073709551615:
; CHECK: # %bb.0:
; CHECK-NEXT: movq (%rdi), %rax
; CHECK-NEXT: leaq -1(%rax), %rcx
; CHECK-NEXT: movq %rcx, (%rdi)
; CHECK-NEXT: testq %rax, %rax
; CHECK-NEXT: setne %al
; CHECK-NEXT: addb $-1, %al
; CHECK-NEXT: adcq $0, (%rsi)
; CHECK-NEXT: retq
%3 = load i64, i64* %0, align 8
%4 = add i64 %3, -1
store i64 %4, i64* %0, align 8
%5 = icmp ne i64 %3, 0
%6 = zext i1 %5 to i8
%7 = load i64, i64* %1, align 8
%8 = tail call { i8, i64 } @llvm.x86.addcarry.64(i8 %6, i64 %7, i64 0)
%9 = extractvalue { i8, i64 } %8, 1
store i64 %9, i64* %1, align 8
ret void
}
[x86] add CGP uaddo test with weird type; NFC There's probably no reason to try this transform for an obviously unsupported op. llvm-svn: 352993
2019-02-03 22:22:43 +08:00
define i1 @illegal_type(i17 %x, i17* %p) {
; CHECK-LABEL: illegal_type:
; CHECK: # %bb.0:
; CHECK-NEXT: addl $29, %edi
; CHECK-NEXT: movw %di, (%rsi)
[CGP] adjust target constraints for forming uaddo There are 2 changes visible here: 1. There's no reason to limit this transform based on number of condition registers. That diff allows PPC to produce slightly better (dot-instructions should be generally good) code. Note: someone that cares about PPC codegen might want to look closer at that output because it seems like we could still improve this. 2. We (probably?) should not bother trying to form uaddo (or other overflow ops) when there's no target support for such an op. This goes beyond checking whether the op is expanded because both PPC and AArch64 show better codegen for standard types regardless of whether the op is legal/custom. llvm-svn: 353001
2019-02-04 01:53:09 +08:00
; CHECK-NEXT: andl $131071, %edi # imm = 0x1FFFF
; CHECK-NEXT: movl %edi, %eax
; CHECK-NEXT: shrl $16, %eax
; CHECK-NEXT: movb %al, 2(%rsi)
; CHECK-NEXT: cmpl $29, %edi
; CHECK-NEXT: setb %al
[x86] add CGP uaddo test with weird type; NFC There's probably no reason to try this transform for an obviously unsupported op. llvm-svn: 352993
2019-02-03 22:22:43 +08:00
; CHECK-NEXT: retq
%a = add i17 %x, 29
store i17 %a, i17* %p
%ov = icmp ult i17 %a, 29
ret i1 %ov
}
[X86] Add CGP tests for PR40486 llvm-svn: 352316
2019-01-27 22:04:45 +08:00
declare { i8, i64 } @llvm.x86.addcarry.64(i8, i64, i64)