RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-01 16:33:37 +01:00
Code Issues Projects Releases Wiki Activity
1ac635c712
llvm-mirror/test/CodeGen/X86/umul-with-overflow.ll

39 lines
926 B
LLVM
Raw Normal View History

it turns out that when ".with.overflow" intrinsics were added to the X86 backend that they were all implemented except umul. This one fell back to the default implementation that did a hi/lo multiply and compared the top. Fix this to check the overflow flag that the 'mul' instruction sets, so we can avoid an explicit test. Now we compile: void *func(long count) { return new int[count]; } into: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] seto %cl ## encoding: [0x0f,0x90,0xc1] testb %cl, %cl ## encoding: [0x84,0xc9] movq $-1, %rdi ## encoding: [0x48,0xc7,0xc7,0xff,0xff,0xff,0xff] cmoveq %rax, %rdi ## encoding: [0x48,0x0f,0x44,0xf8] jmp __Znam ## TAILCALL instead of: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] testq %rdx, %rdx ## encoding: [0x48,0x85,0xd2] movq $-1, %rdi ## encoding: [0x48,0xc7,0xc7,0xff,0xff,0xff,0xff] cmoveq %rax, %rdi ## encoding: [0x48,0x0f,0x44,0xf8] jmp __Znam ## TAILCALL Other than the silly seto+test, this is using the o bit directly, so it's going in the right direction. llvm-svn: 120935
2010-12-05 08:30:36 +01:00
; RUN: llc < %s -march=x86 | FileCheck %s
Add some generic expansion logic for SMULO and UMULO. Fixes UMULO support for x86, and UMULO/SMULO for many architectures, including PPC (PR4201), ARM, and Cell. The resulting expansion isn't perfect, but it's not bad. llvm-svn: 73477
2009-06-16 08:58:29 +02:00
declare {i32, i1} @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
manually upgrade a bunch of tests to modern syntax, and remove some that are either unreduced or only test old syntax. llvm-svn: 133228
2011-06-17 05:14:27 +02:00
define zeroext i1 @a(i32 %x) nounwind {
Add some generic expansion logic for SMULO and UMULO. Fixes UMULO support for x86, and UMULO/SMULO for many architectures, including PPC (PR4201), ARM, and Cell. The resulting expansion isn't perfect, but it's not bad. llvm-svn: 73477
2009-06-16 08:58:29 +02:00
%res = call {i32, i1} @llvm.umul.with.overflow.i32(i32 %x, i32 3)
%obil = extractvalue {i32, i1} %res, 1
ret i1 %obil
it turns out that when ".with.overflow" intrinsics were added to the X86 backend that they were all implemented except umul. This one fell back to the default implementation that did a hi/lo multiply and compared the top. Fix this to check the overflow flag that the 'mul' instruction sets, so we can avoid an explicit test. Now we compile: void *func(long count) { return new int[count]; } into: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] seto %cl ## encoding: [0x0f,0x90,0xc1] testb %cl, %cl ## encoding: [0x84,0xc9] movq $-1, %rdi ## encoding: [0x48,0xc7,0xc7,0xff,0xff,0xff,0xff] cmoveq %rax, %rdi ## encoding: [0x48,0x0f,0x44,0xf8] jmp __Znam ## TAILCALL instead of: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] testq %rdx, %rdx ## encoding: [0x48,0x85,0xd2] movq $-1, %rdi ## encoding: [0x48,0xc7,0xc7,0xff,0xff,0xff,0xff] cmoveq %rax, %rdi ## encoding: [0x48,0x0f,0x44,0xf8] jmp __Znam ## TAILCALL Other than the silly seto+test, this is using the o bit directly, so it's going in the right direction. llvm-svn: 120935
2010-12-05 08:30:36 +01:00
; CHECK: a:
; CHECK: mull
; CHECK: seto %al
As Dan pointed out, movzbl, movsbl, and friends are nicer than their alias (movzx/movsx) because they give more information. Revert that part of the patch. llvm-svn: 129498
2011-04-14 03:46:37 +02:00
; CHECK: movzbl %al, %eax
it turns out that when ".with.overflow" intrinsics were added to the X86 backend that they were all implemented except umul. This one fell back to the default implementation that did a hi/lo multiply and compared the top. Fix this to check the overflow flag that the 'mul' instruction sets, so we can avoid an explicit test. Now we compile: void *func(long count) { return new int[count]; } into: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] seto %cl ## encoding: [0x0f,0x90,0xc1] testb %cl, %cl ## encoding: [0x84,0xc9] movq $-1, %rdi ## encoding: [0x48,0xc7,0xc7,0xff,0xff,0xff,0xff] cmoveq %rax, %rdi ## encoding: [0x48,0x0f,0x44,0xf8] jmp __Znam ## TAILCALL instead of: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] testq %rdx, %rdx ## encoding: [0x48,0x85,0xd2] movq $-1, %rdi ## encoding: [0x48,0xc7,0xc7,0xff,0xff,0xff,0xff] cmoveq %rax, %rdi ## encoding: [0x48,0x0f,0x44,0xf8] jmp __Znam ## TAILCALL Other than the silly seto+test, this is using the o bit directly, so it's going in the right direction. llvm-svn: 120935
2010-12-05 08:30:36 +01:00
; CHECK: ret
Add some generic expansion logic for SMULO and UMULO. Fixes UMULO support for x86, and UMULO/SMULO for many architectures, including PPC (PR4201), ARM, and Cell. The resulting expansion isn't perfect, but it's not bad. llvm-svn: 73477
2009-06-16 08:58:29 +02:00
}
Implement mulo x, 2 -> addo x, x in DAGCombiner. llvm-svn: 131800
2011-05-21 20:31:55 +02:00
define i32 @test2(i32 %a, i32 %b) nounwind readnone {
entry:
%tmp0 = add i32 %b, %a
%tmp1 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 %tmp0, i32 2)
%tmp2 = extractvalue { i32, i1 } %tmp1, 0
ret i32 %tmp2
; CHECK: test2:
; CHECK: addl
; CHECK-NEXT: addl
; CHECK-NEXT: ret
}
define i32 @test3(i32 %a, i32 %b) nounwind readnone {
entry:
%tmp0 = add i32 %b, %a
%tmp1 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 %tmp0, i32 4)
%tmp2 = extractvalue { i32, i1 } %tmp1, 0
ret i32 %tmp2
; CHECK: test3:
; CHECK: addl
; CHECK: mull
; CHECK-NEXT: ret
}
Reference in New Issue Copy Permalink