This is an archive of the discontinued LLVM Phabricator instance.

Differential D36048

[X86]: Extending a test cases for LEA factorization.
ClosedPublic

Authored by jbhateja on Jul 29 2017, 9:33 AM.

Details

Reviewers
jbhateja
RKSimon
lsaba
Commits
rG11ea6fdcd7dc: [X86] Extending a test cases for LEA factorization.
rL309565: [X86] Extending a test cases for LEA factorization.
Summary

Adding more patterns.

Diff Detail

Event Timeline

jbhateja created this revision.Jul 29 2017, 9:33 AM
Harbormaster completed remote builds in B8729: Diff 108794.Jul 29 2017, 9:34 AM
jbhateja accepted this revision.Jul 29 2017, 9:36 AM
jbhateja added a reviewer: RKSimon.
This revision is now accepted and ready to land.Jul 29 2017, 9:36 AM
jbhateja added a comment.Jul 29 2017, 9:36 AM

LGTM

jbhateja requested review of this revision.Jul 29 2017, 9:48 AM
jbhateja edited edge metadata.
jbhateja added a reviewer: lsaba.
lsaba accepted this revision.Jul 30 2017, 6:36 AM
This revision is now accepted and ready to land.Jul 30 2017, 6:36 AM
RKSimon edited edge metadata.Jul 31 2017, 5:59 AM

@jbhateja Do you need this committing?

jbhateja updated this revision to Diff 108914.Jul 31 2017, 6:42 AM

Adding more test patterns to test LEA factorization.

jbhateja added a comment.Jul 31 2017, 6:48 AM

@ RK Simon, Yes, test case 3 (lea-opt-cse3.ll) has more patterns.

Closed by commit rL309565: [X86] Extending a test cases for LEA factorization. (authored by RKSimon). · Explain WhyJul 31 2017, 7:24 AM
This revision was automatically updated to reflect the committed changes.

Revision Contents

PathSize
test/
CodeGen/
X86/
48 lines
76 lines
167 lines

Diff 108914

test/CodeGen/X86/lea-opt-cse1.ll

  • This file was added.
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s -check-prefix=X64
; RUN: llc < %s -mtriple=i686-unknown | FileCheck %s -check-prefix=X86
%struct.SA = type { i32 , i32 , i32 , i32 ,i32 }
define void @test_func(%struct.SA* nocapture %ctx, i32 %n) local_unnamed_addr {
; X64-LABEL: test_func:
; X64: # BB#0: # %entry
; X64-NEXT: movl (%rdi), %eax
; X64-NEXT: movl 16(%rdi), %ecx
; X64-NEXT: leal (%rax,%rcx), %edx
; X64-NEXT: leal 1(%rax,%rcx), %eax
; X64-NEXT: movl %eax, 12(%rdi)
; X64-NEXT: leal 1(%rcx,%rdx), %eax
; X64-NEXT: movl %eax, 16(%rdi)
; X64-NEXT: retq
;
; X86-LABEL: test_func:
; X86: # BB#0: # %entry
; X86-NEXT: pushl %esi
; X86-NEXT: .Lcfi0:
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .Lcfi1:
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl (%eax), %ecx
; X86-NEXT: movl 16(%eax), %edx
; X86-NEXT: leal 1(%ecx,%edx), %esi
; X86-NEXT: addl %edx, %ecx
; X86-NEXT: movl %esi, 12(%eax)
; X86-NEXT: leal 1(%edx,%ecx), %ecx
; X86-NEXT: movl %ecx, 16(%eax)
; X86-NEXT: popl %esi
; X86-NEXT: retl
entry:
%h0 = getelementptr inbounds %struct.SA, %struct.SA* %ctx, i64 0, i32 0
%0 = load i32, i32* %h0, align 8
%h3 = getelementptr inbounds %struct.SA, %struct.SA* %ctx, i64 0, i32 3
%h4 = getelementptr inbounds %struct.SA, %struct.SA* %ctx, i64 0, i32 4
%1 = load i32, i32* %h4, align 8
%add = add i32 %0, 1
%add4 = add i32 %add, %1
store i32 %add4, i32* %h3, align 4
%add29 = add i32 %add4 , %1
store i32 %add29, i32* %h4, align 8
ret void
}

test/CodeGen/X86/lea-opt-cse2.ll

  • This file was added.
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s -check-prefix=X64
; RUN: llc < %s -mtriple=i686-unknown | FileCheck %s -check-prefix=X86
%struct.SA = type { i32 , i32 , i32 , i32 , i32};
define void @foo(%struct.SA* nocapture %ctx, i32 %n) local_unnamed_addr #0 {
; X64-LABEL: foo:
; X64: # BB#0: # %entry
; X64-NEXT: .p2align 4, 0x90
; X64-NEXT: .LBB0_1: # %loop
; X64-NEXT: # =>This Inner Loop Header: Depth=1
; X64-NEXT: movl (%rdi), %eax
; X64-NEXT: movl 16(%rdi), %ecx
; X64-NEXT: leal 1(%rax,%rcx), %edx
; X64-NEXT: movl %edx, 12(%rdi)
; X64-NEXT: decl %esi
; X64-NEXT: jne .LBB0_1
; X64-NEXT: # BB#2: # %exit
; X64-NEXT: addl %ecx, %eax
; X64-NEXT: leal 1(%rcx,%rax), %eax
; X64-NEXT: movl %eax, 16(%rdi)
; X64-NEXT: retq
;
; X86-LABEL: foo:
; X86: # BB#0: # %entry
; X86-NEXT: pushl %edi
; X86-NEXT: .Lcfi0:
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: pushl %esi
; X86-NEXT: .Lcfi1:
; X86-NEXT: .cfi_def_cfa_offset 12
; X86-NEXT: .Lcfi2:
; X86-NEXT: .cfi_offset %esi, -12
; X86-NEXT: .Lcfi3:
; X86-NEXT: .cfi_offset %edi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: .p2align 4, 0x90
; X86-NEXT: .LBB0_1: # %loop
; X86-NEXT: # =>This Inner Loop Header: Depth=1
; X86-NEXT: movl (%eax), %edx
; X86-NEXT: movl 16(%eax), %esi
; X86-NEXT: leal 1(%edx,%esi), %edi
; X86-NEXT: movl %edi, 12(%eax)
; X86-NEXT: decl %ecx
; X86-NEXT: jne .LBB0_1
; X86-NEXT: # BB#2: # %exit
; X86-NEXT: addl %esi, %edx
; X86-NEXT: leal 1(%esi,%edx), %ecx
; X86-NEXT: movl %ecx, 16(%eax)
; X86-NEXT: popl %esi
; X86-NEXT: popl %edi
; X86-NEXT: retl
entry:
br label %loop
loop:
%iter = phi i32 [%n ,%entry ] ,[ %iter.ctr ,%loop]
%h0 = getelementptr inbounds %struct.SA, %struct.SA* %ctx, i64 0, i32 0
%0 = load i32, i32* %h0, align 8
%h3 = getelementptr inbounds %struct.SA, %struct.SA* %ctx, i64 0, i32 3
%h4 = getelementptr inbounds %struct.SA, %struct.SA* %ctx, i64 0, i32 4
%1 = load i32, i32* %h4, align 8
%add = add i32 %0, 1
%add4 = add i32 %add, %1
store i32 %add4, i32* %h3, align 4
%add29 = add i32 %add4, %1
%iter.ctr = sub i32 %iter , 1
%res = icmp ne i32 %iter.ctr , 0
br i1 %res , label %loop , label %exit
exit:
store i32 %add29, i32* %h4, align 8
ret void
}

test/CodeGen/X86/lea-opt-cse3.ll

  • This file was added.
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s -check-prefix=X64
; RUN: llc < %s -mtriple=i686-unknown | FileCheck %s -check-prefix=X86
define i32 @foo(i32 %a, i32 %b) local_unnamed_addr #0 {
; X64-LABEL: foo:
; X64: # BB#0: # %entry
; X64-NEXT: # kill: %ESI<def> %ESI<kill> %RSI<def>
; X64-NEXT: # kill: %EDI<def> %EDI<kill> %RDI<def>
; X64-NEXT: leal 4(%rdi,%rsi,2), %ecx
; X64-NEXT: leal 4(%rdi,%rsi,4), %eax
; X64-NEXT: imull %ecx, %eax
; X64-NEXT: retq
;
; X86-LABEL: foo:
; X86: # BB#0: # %entry
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: leal 4(%ecx,%eax,2), %edx
; X86-NEXT: leal 4(%ecx,%eax,4), %eax
; X86-NEXT: imull %edx, %eax
; X86-NEXT: retl
entry:
%mul = shl i32 %b, 1
%add = add i32 %a, 4
%add1 = add i32 %add, %mul
%mul2 = shl i32 %b, 2
%add4 = add i32 %add, %mul2
%mul5 = mul nsw i32 %add1, %add4
ret i32 %mul5
}
define i32 @foo1(i32 %a, i32 %b) local_unnamed_addr #0 {
; X64-LABEL: foo1:
; X64: # BB#0: # %entry
; X64-NEXT: # kill: %ESI<def> %ESI<kill> %RSI<def>
; X64-NEXT: # kill: %EDI<def> %EDI<kill> %RDI<def>
; X64-NEXT: leal 4(%rdi,%rsi,4), %ecx
; X64-NEXT: leal 4(%rdi,%rsi,8), %eax
; X64-NEXT: imull %ecx, %eax
; X64-NEXT: retq
;
; X86-LABEL: foo1:
; X86: # BB#0: # %entry
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: leal 4(%ecx,%eax,4), %edx
; X86-NEXT: leal 4(%ecx,%eax,8), %eax
; X86-NEXT: imull %edx, %eax
; X86-NEXT: retl
entry:
%mul = shl i32 %b, 2
%add = add i32 %a, 4
%add1 = add i32 %add, %mul
%mul2 = shl i32 %b, 3
%add4 = add i32 %add, %mul2
%mul5 = mul nsw i32 %add1, %add4
ret i32 %mul5
}
define i32 @foo1_mult_basic_blocks(i32 %a, i32 %b) local_unnamed_addr #0 {
; X64-LABEL: foo1_mult_basic_blocks:
; X64: # BB#0: # %entry
; X64-NEXT: # kill: %ESI<def> %ESI<kill> %RSI<def>
; X64-NEXT: # kill: %EDI<def> %EDI<kill> %RDI<def>
; X64-NEXT: leal 4(%rdi,%rsi,4), %ecx
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpl $10, %ecx
; X64-NEXT: je .LBB2_2
; X64-NEXT: # BB#1: # %mid
; X64-NEXT: leal 4(%rdi,%rsi,8), %eax
; X64-NEXT: imull %eax, %ecx
; X64-NEXT: movl %ecx, %eax
; X64-NEXT: .LBB2_2: # %exit
; X64-NEXT: retq
;
; X86-LABEL: foo1_mult_basic_blocks:
; X86: # BB#0: # %entry
; X86-NEXT: pushl %esi
; X86-NEXT: .Lcfi0:
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .Lcfi1:
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: leal 4(%esi,%edx,4), %ecx
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: cmpl $10, %ecx
; X86-NEXT: je .LBB2_2
; X86-NEXT: # BB#1: # %mid
; X86-NEXT: leal 4(%esi,%edx,8), %eax
; X86-NEXT: imull %eax, %ecx
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: .LBB2_2: # %exit
; X86-NEXT: popl %esi
; X86-NEXT: retl
entry:
%mul = shl i32 %b, 2
%add = add i32 %a, 4
%add1 = add i32 %add, %mul
%cmp = icmp ne i32 %add1 , 10
br i1 %cmp , label %mid , label %exit
mid:
%addn = add i32 %a , 4
%mul2 = shl i32 %b, 3
%add4 = add i32 %addn, %mul2
%mul5 = mul nsw i32 %add1, %add4
br label %exit
exit:
%retmul = phi i32 [%mul5 , %mid] , [0 , %entry]
ret i32 %retmul
}
define i32 @foo1_mult_basic_blocks_illegal_scale(i32 %a, i32 %b) local_unnamed_addr #0 {
; X64-LABEL: foo1_mult_basic_blocks_illegal_scale:
; X64: # BB#0: # %entry
; X64-NEXT: # kill: %ESI<def> %ESI<kill> %RSI<def>
; X64-NEXT: # kill: %EDI<def> %EDI<kill> %RDI<def>
; X64-NEXT: leal 4(%rdi,%rsi,2), %ecx
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpl $10, %ecx
; X64-NEXT: je .LBB3_2
; X64-NEXT: # BB#1: # %mid
; X64-NEXT: leal 4(%rdi,%rsi,8), %eax
; X64-NEXT: imull %eax, %ecx
; X64-NEXT: movl %ecx, %eax
; X64-NEXT: .LBB3_2: # %exit
; X64-NEXT: retq
;
; X86-LABEL: foo1_mult_basic_blocks_illegal_scale:
; X86: # BB#0: # %entry
; X86-NEXT: pushl %esi
; X86-NEXT: .Lcfi2:
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .Lcfi3:
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: leal 4(%esi,%edx,2), %ecx
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: cmpl $10, %ecx
; X86-NEXT: je .LBB3_2
; X86-NEXT: # BB#1: # %mid
; X86-NEXT: leal 4(%esi,%edx,8), %eax
; X86-NEXT: imull %eax, %ecx
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: .LBB3_2: # %exit
; X86-NEXT: popl %esi
; X86-NEXT: retl
entry:
%mul = shl i32 %b, 1
%add = add i32 %a, 4
%add1 = add i32 %add, %mul
%cmp = icmp ne i32 %add1 , 10
br i1 %cmp, label %mid , label %exit
mid:
%addn = add i32 %a , 4
%mul2 = shl i32 %b, 3
%add4 = add i32 %addn, %mul2
%mul5 = mul nsw i32 %add1, %add4
br label %exit
exit:
%retmul = phi i32 [%mul5 , %mid] , [0 , %entry]
ret i32 %retmul
}