diff options
author | Matt Morehouse <mascasa@google.com> | 2017-12-01 22:20:26 +0000 |
---|---|---|
committer | Matt Morehouse <mascasa@google.com> | 2017-12-01 22:20:26 +0000 |
commit | 79f1f0032c4d34fa0108b1ad0653b66f1970a322 (patch) | |
tree | eec040ed374edcbfa049f4542dbd51288b2defe3 /test | |
parent | 1fe1bd128c218a113d2f16f3260122cadd949b91 (diff) |
Revert "[X86] Improvement in CodeGen instruction selection for LEAs."
This reverts r319543, due to ASan bot breakage.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@319591 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test')
-rw-r--r-- | test/CodeGen/X86/GlobalISel/callingconv.ll | 2 | ||||
-rw-r--r-- | test/CodeGen/X86/GlobalISel/gep.ll | 34 | ||||
-rw-r--r-- | test/CodeGen/X86/GlobalISel/memop-scalar.ll | 2 | ||||
-rw-r--r-- | test/CodeGen/X86/lea-opt-cse1.ll | 12 | ||||
-rw-r--r-- | test/CodeGen/X86/lea-opt-cse2.ll | 40 | ||||
-rw-r--r-- | test/CodeGen/X86/lea-opt-cse3.ll | 34 | ||||
-rw-r--r-- | test/CodeGen/X86/lea-opt-cse4.ll | 68 | ||||
-rw-r--r-- | test/CodeGen/X86/mul-constant-i16.ll | 12 | ||||
-rw-r--r-- | test/CodeGen/X86/mul-constant-i32.ll | 15 | ||||
-rw-r--r-- | test/CodeGen/X86/mul-constant-i64.ll | 9 | ||||
-rw-r--r-- | test/CodeGen/X86/mul-constant-result.ll | 14 | ||||
-rw-r--r-- | test/CodeGen/X86/umul-with-overflow.ll | 16 | ||||
-rw-r--r-- | test/Transforms/LoopStrengthReduce/X86/ivchain-X86.ll | 6 |
13 files changed, 151 insertions, 113 deletions
diff --git a/test/CodeGen/X86/GlobalISel/callingconv.ll b/test/CodeGen/X86/GlobalISel/callingconv.ll index a55ff862e2b..4100a7217ac 100644 --- a/test/CodeGen/X86/GlobalISel/callingconv.ll +++ b/test/CodeGen/X86/GlobalISel/callingconv.ll @@ -388,7 +388,7 @@ define void @test_variadic_call_2(i8** %addr_ptr, double* %val_ptr) { ; X32-NEXT: movl 4(%ecx), %ecx ; X32-NEXT: movl %eax, (%esp) ; X32-NEXT: movl $4, %eax -; X32-NEXT: addl %esp, %eax +; X32-NEXT: leal (%esp,%eax), %eax ; X32-NEXT: movl %edx, 4(%esp) ; X32-NEXT: movl %ecx, 4(%eax) ; X32-NEXT: calll variadic_callee diff --git a/test/CodeGen/X86/GlobalISel/gep.ll b/test/CodeGen/X86/GlobalISel/gep.ll index 95ad8d4eb30..ee66accc77d 100644 --- a/test/CodeGen/X86/GlobalISel/gep.ll +++ b/test/CodeGen/X86/GlobalISel/gep.ll @@ -5,10 +5,10 @@ define i32* @test_gep_i8(i32 *%arr, i8 %ind) { ; X64_GISEL-LABEL: test_gep_i8: ; X64_GISEL: # BB#0: -; X64_GISEL-NEXT: movq $4, %rcx -; X64_GISEL-NEXT: movsbq %sil, %rax -; X64_GISEL-NEXT: imulq %rcx, %rax -; X64_GISEL-NEXT: addq %rdi, %rax +; X64_GISEL-NEXT: movq $4, %rax +; X64_GISEL-NEXT: movsbq %sil, %rcx +; X64_GISEL-NEXT: imulq %rax, %rcx +; X64_GISEL-NEXT: leaq (%rdi,%rcx), %rax ; X64_GISEL-NEXT: retq ; ; X64-LABEL: test_gep_i8: @@ -25,7 +25,7 @@ define i32* @test_gep_i8_const(i32 *%arr) { ; X64_GISEL-LABEL: test_gep_i8_const: ; X64_GISEL: # BB#0: ; X64_GISEL-NEXT: movq $80, %rax -; X64_GISEL-NEXT: addq %rdi, %rax +; X64_GISEL-NEXT: leaq (%rdi,%rax), %rax ; X64_GISEL-NEXT: retq ; ; X64-LABEL: test_gep_i8_const: @@ -39,10 +39,10 @@ define i32* @test_gep_i8_const(i32 *%arr) { define i32* @test_gep_i16(i32 *%arr, i16 %ind) { ; X64_GISEL-LABEL: test_gep_i16: ; X64_GISEL: # BB#0: -; X64_GISEL-NEXT: movq $4, %rcx -; X64_GISEL-NEXT: movswq %si, %rax -; X64_GISEL-NEXT: imulq %rcx, %rax -; X64_GISEL-NEXT: addq %rdi, %rax +; X64_GISEL-NEXT: movq $4, %rax +; X64_GISEL-NEXT: movswq %si, %rcx +; X64_GISEL-NEXT: imulq %rax, %rcx +; X64_GISEL-NEXT: leaq (%rdi,%rcx), %rax ; X64_GISEL-NEXT: retq ; ; X64-LABEL: test_gep_i16: @@ -59,7 +59,7 @@ define i32* @test_gep_i16_const(i32 *%arr) { ; X64_GISEL-LABEL: test_gep_i16_const: ; X64_GISEL: # BB#0: ; X64_GISEL-NEXT: movq $80, %rax -; X64_GISEL-NEXT: addq %rdi, %rax +; X64_GISEL-NEXT: leaq (%rdi,%rax), %rax ; X64_GISEL-NEXT: retq ; ; X64-LABEL: test_gep_i16_const: @@ -73,10 +73,10 @@ define i32* @test_gep_i16_const(i32 *%arr) { define i32* @test_gep_i32(i32 *%arr, i32 %ind) { ; X64_GISEL-LABEL: test_gep_i32: ; X64_GISEL: # BB#0: -; X64_GISEL-NEXT: movq $4, %rcx -; X64_GISEL-NEXT: movslq %esi, %rax -; X64_GISEL-NEXT: imulq %rcx, %rax -; X64_GISEL-NEXT: addq %rdi, %rax +; X64_GISEL-NEXT: movq $4, %rax +; X64_GISEL-NEXT: movslq %esi, %rcx +; X64_GISEL-NEXT: imulq %rax, %rcx +; X64_GISEL-NEXT: leaq (%rdi,%rcx), %rax ; X64_GISEL-NEXT: retq ; ; X64-LABEL: test_gep_i32: @@ -92,7 +92,7 @@ define i32* @test_gep_i32_const(i32 *%arr) { ; X64_GISEL-LABEL: test_gep_i32_const: ; X64_GISEL: # BB#0: ; X64_GISEL-NEXT: movq $20, %rax -; X64_GISEL-NEXT: addq %rdi, %rax +; X64_GISEL-NEXT: leaq (%rdi,%rax), %rax ; X64_GISEL-NEXT: retq ; ; X64-LABEL: test_gep_i32_const: @@ -108,7 +108,7 @@ define i32* @test_gep_i64(i32 *%arr, i64 %ind) { ; X64_GISEL: # BB#0: ; X64_GISEL-NEXT: movq $4, %rax ; X64_GISEL-NEXT: imulq %rsi, %rax -; X64_GISEL-NEXT: addq %rdi, %rax +; X64_GISEL-NEXT: leaq (%rdi,%rax), %rax ; X64_GISEL-NEXT: retq ; ; X64-LABEL: test_gep_i64: @@ -123,7 +123,7 @@ define i32* @test_gep_i64_const(i32 *%arr) { ; X64_GISEL-LABEL: test_gep_i64_const: ; X64_GISEL: # BB#0: ; X64_GISEL-NEXT: movq $20, %rax -; X64_GISEL-NEXT: addq %rdi, %rax +; X64_GISEL-NEXT: leaq (%rdi,%rax), %rax ; X64_GISEL-NEXT: retq ; ; X64-LABEL: test_gep_i64_const: diff --git a/test/CodeGen/X86/GlobalISel/memop-scalar.ll b/test/CodeGen/X86/GlobalISel/memop-scalar.ll index c73a43177e3..2097a3b0bfc 100644 --- a/test/CodeGen/X86/GlobalISel/memop-scalar.ll +++ b/test/CodeGen/X86/GlobalISel/memop-scalar.ll @@ -181,7 +181,7 @@ define i32 @test_gep_folding_largeGepIndex(i32* %arr, i32 %val) { ; ALL-LABEL: test_gep_folding_largeGepIndex: ; ALL: # BB#0: ; ALL-NEXT: movabsq $228719476720, %rax # imm = 0x3540BE3FF0 -; ALL-NEXT: addq %rdi, %rax +; ALL-NEXT: leaq (%rdi,%rax), %rax ; ALL-NEXT: movl %esi, (%rax) ; ALL-NEXT: movl (%rax), %eax ; ALL-NEXT: retq diff --git a/test/CodeGen/X86/lea-opt-cse1.ll b/test/CodeGen/X86/lea-opt-cse1.ll index 512740ce075..05b47690e81 100644 --- a/test/CodeGen/X86/lea-opt-cse1.ll +++ b/test/CodeGen/X86/lea-opt-cse1.ll @@ -9,21 +9,27 @@ define void @test_func(%struct.SA* nocapture %ctx, i32 %n) local_unnamed_addr { ; 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: addq %ecx, %eax +; 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: .cfi_def_cfa_offset 8 +; 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), %ecx -; X86-NEXT: movl %ecx, 12(%eax) +; 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 diff --git a/test/CodeGen/X86/lea-opt-cse2.ll b/test/CodeGen/X86/lea-opt-cse2.ll index 4226e3d25c8..865dd49a6e1 100644 --- a/test/CodeGen/X86/lea-opt-cse2.ll +++ b/test/CodeGen/X86/lea-opt-cse2.ll @@ -1,6 +1,6 @@ ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py -; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+slow-3ops-lea | FileCheck %s -check-prefix=X64 -; RUN: llc < %s -mtriple=i686-unknown -mattr=+slow-3ops-lea | FileCheck %s -check-prefix=X86 +; 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}; @@ -10,39 +10,43 @@ define void @foo(%struct.SA* nocapture %ctx, i32 %n) local_unnamed_addr #0 { ; X64-NEXT: .p2align 4, 0x90 ; X64-NEXT: .LBB0_1: # %loop ; X64-NEXT: # =>This Inner Loop Header: Depth=1 -; X64-NEXT: movl 16(%rdi), %eax -; X64-NEXT: movl (%rdi), %ecx -; X64-NEXT: addl %eax, %ecx -; X64-NEXT: incl %ecx -; X64-NEXT: movl %ecx, 12(%rdi) +; 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 %eax, %ecx -; X64-NEXT: movl %ecx, 16(%rdi) +; 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 %esi +; X86-NEXT: pushl %edi ; X86-NEXT: .cfi_def_cfa_offset 8 -; X86-NEXT: .cfi_offset %esi, -8 +; X86-NEXT: pushl %esi +; X86-NEXT: .cfi_def_cfa_offset 12 +; X86-NEXT: .cfi_offset %esi, -12 +; 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 16(%eax), %edx -; X86-NEXT: movl (%eax), %esi -; X86-NEXT: addl %edx, %esi -; X86-NEXT: incl %esi -; X86-NEXT: movl %esi, 12(%eax) +; 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 %edx, %esi -; X86-NEXT: movl %esi, 16(%eax) +; 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 diff --git a/test/CodeGen/X86/lea-opt-cse3.ll b/test/CodeGen/X86/lea-opt-cse3.ll index 57c20cceed1..48ab3130bf0 100644 --- a/test/CodeGen/X86/lea-opt-cse3.ll +++ b/test/CodeGen/X86/lea-opt-cse3.ll @@ -8,7 +8,7 @@ define i32 @foo(i32 %a, i32 %b) local_unnamed_addr #0 { ; 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 (%ecx,%esi,2), %eax +; X64-NEXT: leal 4(%rdi,%rsi,4), %eax ; X64-NEXT: imull %ecx, %eax ; X64-NEXT: retq ; @@ -16,9 +16,9 @@ define i32 @foo(i32 %a, i32 %b) local_unnamed_addr #0 { ; 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), %ecx -; X86-NEXT: leal (%ecx,%eax,2), %eax -; X86-NEXT: imull %ecx, %eax +; 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 @@ -36,7 +36,7 @@ define i32 @foo1(i32 %a, i32 %b) local_unnamed_addr #0 { ; 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 (%ecx,%esi,4), %eax +; X64-NEXT: leal 4(%rdi,%rsi,8), %eax ; X64-NEXT: imull %ecx, %eax ; X64-NEXT: retq ; @@ -44,9 +44,9 @@ define i32 @foo1(i32 %a, i32 %b) local_unnamed_addr #0 { ; 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), %ecx -; X86-NEXT: leal (%ecx,%eax,4), %eax -; X86-NEXT: imull %ecx, %eax +; 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 @@ -68,23 +68,29 @@ define i32 @foo1_mult_basic_blocks(i32 %a, i32 %b) local_unnamed_addr #0 { ; X64-NEXT: cmpl $10, %ecx ; X64-NEXT: je .LBB2_2 ; X64-NEXT: # BB#1: # %mid -; X64-NEXT: leal (%ecx,%esi,4), %eax -; X64-NEXT: imull %ecx, %eax +; 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: .cfi_def_cfa_offset 8 +; X86-NEXT: .cfi_offset %esi, -8 ; X86-NEXT: movl {{[0-9]+}}(%esp), %edx -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: leal 4(%eax,%edx,4), %ecx +; 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 (%ecx,%edx,4), %eax -; X86-NEXT: imull %ecx, %eax +; 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 diff --git a/test/CodeGen/X86/lea-opt-cse4.ll b/test/CodeGen/X86/lea-opt-cse4.ll index 6f1fe282f92..31f31a73d44 100644 --- a/test/CodeGen/X86/lea-opt-cse4.ll +++ b/test/CodeGen/X86/lea-opt-cse4.ll @@ -1,31 +1,41 @@ ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py -; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+slow-3ops-lea | FileCheck %s -check-prefix=X64 -; RUN: llc < %s -mtriple=i686-unknown -mattr=+slow-3ops-lea | FileCheck %s -check-prefix=X86 +; 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: movl (%rdi), %eax -; X64-NEXT: movl 16(%rdi), %ecx -; X64-NEXT: leal (%rax,%rcx,4), %eax -; X64-NEXT: addl $1, %eax -; X64-NEXT: movl %eax, 12(%rdi) -; X64-NEXT: addl %ecx, %eax +; X64-NEXT: movl 16(%rdi), %eax +; X64-NEXT: movl (%rdi), %ecx +; X64-NEXT: addl %eax, %ecx +; X64-NEXT: addl %eax, %ecx +; X64-NEXT: addl %eax, %ecx +; X64-NEXT: leal (%rcx,%rax), %edx +; X64-NEXT: leal 1(%rax,%rcx), %ecx +; X64-NEXT: movl %ecx, 12(%rdi) +; X64-NEXT: leal 1(%rax,%rdx), %eax ; X64-NEXT: movl %eax, 16(%rdi) ; X64-NEXT: retq ; ; X86-LABEL: foo: ; X86: # BB#0: # %entry +; X86-NEXT: pushl %esi +; X86-NEXT: .cfi_def_cfa_offset 8 +; 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 (%ecx,%edx,4), %ecx -; X86-NEXT: addl $1, %ecx -; X86-NEXT: movl %ecx, 12(%eax) -; X86-NEXT: addl %edx, %ecx +; X86-NEXT: movl 16(%eax), %ecx +; X86-NEXT: movl (%eax), %edx +; X86-NEXT: addl %ecx, %edx +; X86-NEXT: addl %ecx, %edx +; X86-NEXT: addl %ecx, %edx +; X86-NEXT: leal 1(%ecx,%edx), %esi +; X86-NEXT: addl %ecx, %edx +; X86-NEXT: movl %esi, 12(%eax) +; X86-NEXT: leal 1(%ecx,%edx), %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 @@ -52,15 +62,15 @@ define void @foo_loop(%struct.SA* nocapture %ctx, i32 %n) local_unnamed_addr #0 ; X64-NEXT: .p2align 4, 0x90 ; X64-NEXT: .LBB1_1: # %loop ; X64-NEXT: # =>This Inner Loop Header: Depth=1 -; X64-NEXT: movl 16(%rdi), %eax ; X64-NEXT: movl (%rdi), %ecx -; X64-NEXT: addl %eax, %ecx -; X64-NEXT: incl %ecx -; X64-NEXT: movl %ecx, 12(%rdi) +; X64-NEXT: movl 16(%rdi), %eax +; X64-NEXT: leal 1(%rcx,%rax), %edx +; X64-NEXT: movl %edx, 12(%rdi) ; X64-NEXT: decl %esi ; X64-NEXT: jne .LBB1_1 ; X64-NEXT: # BB#2: # %exit ; X64-NEXT: addl %eax, %ecx +; X64-NEXT: leal 1(%rax,%rcx), %ecx ; X64-NEXT: addl %eax, %ecx ; X64-NEXT: addl %eax, %ecx ; X64-NEXT: addl %eax, %ecx @@ -72,23 +82,26 @@ define void @foo_loop(%struct.SA* nocapture %ctx, i32 %n) local_unnamed_addr #0 ; ; X86-LABEL: foo_loop: ; X86: # BB#0: # %entry -; X86-NEXT: pushl %esi +; X86-NEXT: pushl %edi ; X86-NEXT: .cfi_def_cfa_offset 8 -; X86-NEXT: .cfi_offset %esi, -8 -; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: pushl %esi +; X86-NEXT: .cfi_def_cfa_offset 12 +; X86-NEXT: .cfi_offset %esi, -12 +; X86-NEXT: .cfi_offset %edi, -8 +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx ; X86-NEXT: movl {{[0-9]+}}(%esp), %eax ; X86-NEXT: .p2align 4, 0x90 ; X86-NEXT: .LBB1_1: # %loop ; X86-NEXT: # =>This Inner Loop Header: Depth=1 +; X86-NEXT: movl (%eax), %esi ; X86-NEXT: movl 16(%eax), %ecx -; X86-NEXT: movl (%eax), %edx -; X86-NEXT: addl %ecx, %edx -; X86-NEXT: incl %edx -; X86-NEXT: movl %edx, 12(%eax) -; X86-NEXT: decl %esi +; X86-NEXT: leal 1(%esi,%ecx), %edi +; X86-NEXT: movl %edi, 12(%eax) +; X86-NEXT: decl %edx ; X86-NEXT: jne .LBB1_1 ; X86-NEXT: # BB#2: # %exit -; X86-NEXT: addl %ecx, %edx +; X86-NEXT: addl %ecx, %esi +; X86-NEXT: leal 1(%ecx,%esi), %edx ; X86-NEXT: addl %ecx, %edx ; X86-NEXT: addl %ecx, %edx ; X86-NEXT: addl %ecx, %edx @@ -97,6 +110,7 @@ define void @foo_loop(%struct.SA* nocapture %ctx, i32 %n) local_unnamed_addr #0 ; X86-NEXT: addl %ecx, %edx ; X86-NEXT: movl %edx, 16(%eax) ; X86-NEXT: popl %esi +; X86-NEXT: popl %edi ; X86-NEXT: retl entry: br label %loop diff --git a/test/CodeGen/X86/mul-constant-i16.ll b/test/CodeGen/X86/mul-constant-i16.ll index 72731b3ba67..c3b822ac214 100644 --- a/test/CodeGen/X86/mul-constant-i16.ll +++ b/test/CodeGen/X86/mul-constant-i16.ll @@ -558,10 +558,11 @@ define i16 @test_mul_by_28(i16 %x) { define i16 @test_mul_by_29(i16 %x) { ; X86-LABEL: test_mul_by_29: ; X86: # BB#0: -; X86-NEXT: movzwl {{[0-9]+}}(%esp), %eax -; X86-NEXT: leal (%eax,%eax,8), %ecx -; X86-NEXT: leal (%ecx,%ecx,2), %ecx -; X86-NEXT: leal (%ecx,%eax,2), %eax +; X86-NEXT: movzwl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: leal (%ecx,%ecx,8), %eax +; X86-NEXT: leal (%eax,%eax,2), %eax +; X86-NEXT: addl %ecx, %eax +; X86-NEXT: addl %ecx, %eax ; X86-NEXT: # kill: %ax<def> %ax<kill> %eax<kill> ; X86-NEXT: retl ; @@ -570,7 +571,8 @@ define i16 @test_mul_by_29(i16 %x) { ; X64-NEXT: # kill: %edi<def> %edi<kill> %rdi<def> ; X64-NEXT: leal (%rdi,%rdi,8), %eax ; X64-NEXT: leal (%rax,%rax,2), %eax -; X64-NEXT: leal (%rax,%rdi,2), %eax +; X64-NEXT: addl %edi, %eax +; X64-NEXT: addl %edi, %eax ; X64-NEXT: # kill: %ax<def> %ax<kill> %eax<kill> ; X64-NEXT: retq %mul = mul nsw i16 %x, 29 diff --git a/test/CodeGen/X86/mul-constant-i32.ll b/test/CodeGen/X86/mul-constant-i32.ll index c8ac6a70927..228dd5e5f37 100644 --- a/test/CodeGen/X86/mul-constant-i32.ll +++ b/test/CodeGen/X86/mul-constant-i32.ll @@ -1457,10 +1457,11 @@ define i32 @test_mul_by_28(i32 %x) { define i32 @test_mul_by_29(i32 %x) { ; X86-LABEL: test_mul_by_29: ; X86: # BB#0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-NEXT: leal (%eax,%eax,8), %ecx -; X86-NEXT: leal (%ecx,%ecx,2), %ecx -; X86-NEXT: leal (%ecx,%eax,2), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: leal (%ecx,%ecx,8), %eax +; X86-NEXT: leal (%eax,%eax,2), %eax +; X86-NEXT: addl %ecx, %eax +; X86-NEXT: addl %ecx, %eax ; X86-NEXT: retl ; ; X64-HSW-LABEL: test_mul_by_29: @@ -1468,7 +1469,8 @@ define i32 @test_mul_by_29(i32 %x) { ; X64-HSW-NEXT: # kill: %edi<def> %edi<kill> %rdi<def> ; X64-HSW-NEXT: leal (%rdi,%rdi,8), %eax # sched: [1:0.50] ; X64-HSW-NEXT: leal (%rax,%rax,2), %eax # sched: [1:0.50] -; X64-HSW-NEXT: leal (%rax,%rdi,2), %eax # sched: [1:0.50] +; X64-HSW-NEXT: addl %edi, %eax # sched: [1:0.25] +; X64-HSW-NEXT: addl %edi, %eax # sched: [1:0.25] ; X64-HSW-NEXT: retq # sched: [2:1.00] ; ; X64-JAG-LABEL: test_mul_by_29: @@ -1476,7 +1478,8 @@ define i32 @test_mul_by_29(i32 %x) { ; X64-JAG-NEXT: # kill: %edi<def> %edi<kill> %rdi<def> ; X64-JAG-NEXT: leal (%rdi,%rdi,8), %eax # sched: [1:0.50] ; X64-JAG-NEXT: leal (%rax,%rax,2), %eax # sched: [1:0.50] -; X64-JAG-NEXT: leal (%rax,%rdi,2), %eax # sched: [1:0.50] +; X64-JAG-NEXT: addl %edi, %eax # sched: [1:0.50] +; X64-JAG-NEXT: addl %edi, %eax # sched: [1:0.50] ; X64-JAG-NEXT: retq # sched: [4:1.00] ; ; X86-NOOPT-LABEL: test_mul_by_29: diff --git a/test/CodeGen/X86/mul-constant-i64.ll b/test/CodeGen/X86/mul-constant-i64.ll index 8e171f973e0..98568a6fc8e 100644 --- a/test/CodeGen/X86/mul-constant-i64.ll +++ b/test/CodeGen/X86/mul-constant-i64.ll @@ -1523,7 +1523,8 @@ define i64 @test_mul_by_29(i64 %x) { ; X86-NEXT: movl {{[0-9]+}}(%esp), %eax ; X86-NEXT: leal (%eax,%eax,8), %ecx ; X86-NEXT: leal (%ecx,%ecx,2), %ecx -; X86-NEXT: leal (%ecx,%eax,2), %ecx +; X86-NEXT: addl %eax, %ecx +; X86-NEXT: addl %eax, %ecx ; X86-NEXT: movl $29, %eax ; X86-NEXT: mull {{[0-9]+}}(%esp) ; X86-NEXT: addl %ecx, %edx @@ -1533,14 +1534,16 @@ define i64 @test_mul_by_29(i64 %x) { ; X64-HSW: # BB#0: ; X64-HSW-NEXT: leaq (%rdi,%rdi,8), %rax # sched: [1:0.50] ; X64-HSW-NEXT: leaq (%rax,%rax,2), %rax # sched: [1:0.50] -; X64-HSW-NEXT: leaq (%rax,%rdi,2), %rax # sched: [1:0.50] +; X64-HSW-NEXT: addq %rdi, %rax # sched: [1:0.25] +; X64-HSW-NEXT: addq %rdi, %rax # sched: [1:0.25] ; X64-HSW-NEXT: retq # sched: [2:1.00] ; ; X64-JAG-LABEL: test_mul_by_29: ; X64-JAG: # BB#0: ; X64-JAG-NEXT: leaq (%rdi,%rdi,8), %rax # sched: [1:0.50] ; X64-JAG-NEXT: leaq (%rax,%rax,2), %rax # sched: [1:0.50] -; X64-JAG-NEXT: leaq (%rax,%rdi,2), %rax # sched: [1:0.50] +; X64-JAG-NEXT: addq %rdi, %rax # sched: [1:0.50] +; X64-JAG-NEXT: addq %rdi, %rax # sched: [1:0.50] ; X64-JAG-NEXT: retq # sched: [4:1.00] ; ; X86-NOOPT-LABEL: test_mul_by_29: diff --git a/test/CodeGen/X86/mul-constant-result.ll b/test/CodeGen/X86/mul-constant-result.ll index f5846ab37ba..6e74c1d4e9e 100644 --- a/test/CodeGen/X86/mul-constant-result.ll +++ b/test/CodeGen/X86/mul-constant-result.ll @@ -164,7 +164,8 @@ define i32 @mult(i32, i32) local_unnamed_addr #0 { ; X86-NEXT: .LBB0_35: ; X86-NEXT: leal (%eax,%eax,8), %ecx ; X86-NEXT: leal (%ecx,%ecx,2), %ecx -; X86-NEXT: leal (%ecx,%eax,2), %eax +; X86-NEXT: addl %eax, %ecx +; X86-NEXT: addl %ecx, %eax ; X86-NEXT: popl %esi ; X86-NEXT: retl ; X86-NEXT: .LBB0_36: @@ -322,15 +323,14 @@ define i32 @mult(i32, i32) local_unnamed_addr #0 { ; X64-HSW-NEXT: .LBB0_31: ; X64-HSW-NEXT: leal (%rax,%rax,8), %ecx ; X64-HSW-NEXT: leal (%rcx,%rcx,2), %ecx -; X64-HSW-NEXT: .LBB0_17: -; X64-HSW-NEXT: addl %eax, %ecx -; X64-HSW-NEXT: movl %ecx, %eax -; X64-HSW-NEXT: # kill: %eax<def> %eax<kill> %rax<kill> -; X64-HSW-NEXT: retq +; X64-HSW-NEXT: jmp .LBB0_17 ; X64-HSW-NEXT: .LBB0_32: ; X64-HSW-NEXT: leal (%rax,%rax,8), %ecx ; X64-HSW-NEXT: leal (%rcx,%rcx,2), %ecx -; X64-HSW-NEXT: leal (%rcx,%rax,2), %eax +; X64-HSW-NEXT: addl %eax, %ecx +; X64-HSW-NEXT: .LBB0_17: +; X64-HSW-NEXT: addl %eax, %ecx +; X64-HSW-NEXT: movl %ecx, %eax ; X64-HSW-NEXT: # kill: %eax<def> %eax<kill> %rax<kill> ; X64-HSW-NEXT: retq ; X64-HSW-NEXT: .LBB0_33: diff --git a/test/CodeGen/X86/umul-with-overflow.ll b/test/CodeGen/X86/umul-with-overflow.ll index 70b7daa6c16..2e877a0b6e0 100644 --- a/test/CodeGen/X86/umul-with-overflow.ll +++ b/test/CodeGen/X86/umul-with-overflow.ll @@ -40,10 +40,10 @@ define i32 @test2(i32 %a, i32 %b) nounwind readnone { ; X64-NEXT: leal (%rdi,%rdi), %eax ; X64-NEXT: retq 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 + %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 } define i32 @test3(i32 %a, i32 %b) nounwind readnone { @@ -64,8 +64,8 @@ define i32 @test3(i32 %a, i32 %b) nounwind readnone { ; X64-NEXT: mull %ecx ; X64-NEXT: retq 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 + %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 } diff --git a/test/Transforms/LoopStrengthReduce/X86/ivchain-X86.ll b/test/Transforms/LoopStrengthReduce/X86/ivchain-X86.ll index 3f6d234c929..7c01432914f 100644 --- a/test/Transforms/LoopStrengthReduce/X86/ivchain-X86.ll +++ b/test/Transforms/LoopStrengthReduce/X86/ivchain-X86.ll @@ -13,14 +13,14 @@ ; X64-NEXT: .p2align ; X64: %loop ; no complex address modes -; X64-NOT: [1-9]+(%{{[^)]+}},%{{[^)]+}}, +; X64-NOT: (%{{[^)]+}},%{{[^)]+}}, ; ; X32: @simple ; no expensive address computation in the preheader ; X32-NOT: imul ; X32: %loop ; no complex address modes -; X32-NOT: [1-9]+(%{{[^)]+}},%{{[^)]+}}, +; X32-NOT: (%{{[^)]+}},%{{[^)]+}}, define i32 @simple(i32* %a, i32* %b, i32 %x) nounwind { entry: br label %loop @@ -103,7 +103,7 @@ exit: ; X32-NOT: mov{{.*}}(%esp){{$}} ; X32: %for.body{{$}} ; no complex address modes -; X32-NOT: [1-9]+(%{{[^)]+}},%{{[^)]+}}, +; X32-NOT: (%{{[^)]+}},%{{[^)]+}}, ; no reloads ; X32-NOT: (%esp) define void @extrastride(i8* nocapture %main, i32 %main_stride, i32* nocapture %res, i32 %x, i32 %y, i32 %z) nounwind { |