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/fast-isel-mem.ll

35 lines
822 B
LLVM
Raw Normal View History

implement rdar://6653118 - fastisel should fold loads where possible. Since mem2reg isn't run at -O0, we get a ton of reloads from the stack, for example, before, this code: int foo(int x, int y, int z) { return x+y+z; } used to compile into: _foo: ## @foo subq $12, %rsp movl %edi, 8(%rsp) movl %esi, 4(%rsp) movl %edx, (%rsp) movl 8(%rsp), %edx movl 4(%rsp), %esi addl %edx, %esi movl (%rsp), %edx addl %esi, %edx movl %edx, %eax addq $12, %rsp ret Now we produce: _foo: ## @foo subq $12, %rsp movl %edi, 8(%rsp) movl %esi, 4(%rsp) movl %edx, (%rsp) movl 8(%rsp), %edx addl 4(%rsp), %edx ## Folded load addl (%rsp), %edx ## Folded load movl %edx, %eax addq $12, %rsp ret Fewer instructions and less register use = faster compiles. llvm-svn: 113102
2010-09-05 10:18:34 +08:00
; RUN: llc < %s -fast-isel -mtriple=i386-apple-darwin | FileCheck %s
Load from GV stub should be locally CSE'd. llvm-svn: 55763
2008-09-04 14:18:33 +08:00
@src = external global i32
implement rdar://6653118 - fastisel should fold loads where possible. Since mem2reg isn't run at -O0, we get a ton of reloads from the stack, for example, before, this code: int foo(int x, int y, int z) { return x+y+z; } used to compile into: _foo: ## @foo subq $12, %rsp movl %edi, 8(%rsp) movl %esi, 4(%rsp) movl %edx, (%rsp) movl 8(%rsp), %edx movl 4(%rsp), %esi addl %edx, %esi movl (%rsp), %edx addl %esi, %edx movl %edx, %eax addq $12, %rsp ret Now we produce: _foo: ## @foo subq $12, %rsp movl %edi, 8(%rsp) movl %esi, 4(%rsp) movl %edx, (%rsp) movl 8(%rsp), %edx addl 4(%rsp), %edx ## Folded load addl (%rsp), %edx ## Folded load movl %edx, %eax addq $12, %rsp ret Fewer instructions and less register use = faster compiles. llvm-svn: 113102
2010-09-05 10:18:34 +08:00
; rdar://6653118
Load from GV stub should be locally CSE'd. llvm-svn: 55763
2008-09-04 14:18:33 +08:00
define i32 @loadgv() nounwind {
entry:
%0 = load i32* @src, align 4
%1 = load i32* @src, align 4
%2 = add i32 %0, %1
Fix a constant lowering bug. Now we can do load and store instructions with funky getelementptr embedded in the address operand. llvm-svn: 55975
2008-09-09 09:26:59 +08:00
store i32 %2, i32* @src
Load from GV stub should be locally CSE'd. llvm-svn: 55763
2008-09-04 14:18:33 +08:00
ret i32 %2
implement rdar://6653118 - fastisel should fold loads where possible. Since mem2reg isn't run at -O0, we get a ton of reloads from the stack, for example, before, this code: int foo(int x, int y, int z) { return x+y+z; } used to compile into: _foo: ## @foo subq $12, %rsp movl %edi, 8(%rsp) movl %esi, 4(%rsp) movl %edx, (%rsp) movl 8(%rsp), %edx movl 4(%rsp), %esi addl %edx, %esi movl (%rsp), %edx addl %esi, %edx movl %edx, %eax addq $12, %rsp ret Now we produce: _foo: ## @foo subq $12, %rsp movl %edi, 8(%rsp) movl %esi, 4(%rsp) movl %edx, (%rsp) movl 8(%rsp), %edx addl 4(%rsp), %edx ## Folded load addl (%rsp), %edx ## Folded load movl %edx, %eax addq $12, %rsp ret Fewer instructions and less register use = faster compiles. llvm-svn: 113102
2010-09-05 10:18:34 +08:00
; This should fold one of the loads into the add.
; CHECK: loadgv:
; CHECK: movl L_src$non_lazy_ptr, %ecx
; CHECK: movl (%ecx), %eax
; CHECK: addl (%ecx), %eax
; CHECK: movl %eax, (%ecx)
; CHECK: ret
Load from GV stub should be locally CSE'd. llvm-svn: 55763
2008-09-04 14:18:33 +08:00
}
Fix a constant lowering bug. Now we can do load and store instructions with funky getelementptr embedded in the address operand. llvm-svn: 55975
2008-09-09 09:26:59 +08:00
%stuff = type { i32 (...)** }
@LotsStuff = external constant [4 x i32 (...)*]
define void @t(%stuff* %this) nounwind {
entry:
store i32 (...)** getelementptr ([4 x i32 (...)*]* @LotsStuff, i32 0, i32 2), i32 (...)*** null, align 4
ret void
implement rdar://6653118 - fastisel should fold loads where possible. Since mem2reg isn't run at -O0, we get a ton of reloads from the stack, for example, before, this code: int foo(int x, int y, int z) { return x+y+z; } used to compile into: _foo: ## @foo subq $12, %rsp movl %edi, 8(%rsp) movl %esi, 4(%rsp) movl %edx, (%rsp) movl 8(%rsp), %edx movl 4(%rsp), %esi addl %edx, %esi movl (%rsp), %edx addl %esi, %edx movl %edx, %eax addq $12, %rsp ret Now we produce: _foo: ## @foo subq $12, %rsp movl %edi, 8(%rsp) movl %esi, 4(%rsp) movl %edx, (%rsp) movl 8(%rsp), %edx addl 4(%rsp), %edx ## Folded load addl (%rsp), %edx ## Folded load movl %edx, %eax addq $12, %rsp ret Fewer instructions and less register use = faster compiles. llvm-svn: 113102
2010-09-05 10:18:34 +08:00
; CHECK: _t:
; CHECK: movl $0, %eax
; CHECK: movl L_LotsStuff$non_lazy_ptr, %ecx
Fix a constant lowering bug. Now we can do load and store instructions with funky getelementptr embedded in the address operand. llvm-svn: 55975
2008-09-09 09:26:59 +08:00
}