[LoopStrengthReduce, x86] don't add cost for a cmp that will be macro-fused (PR35681)
In the motivating case from PR35681 and represented by the macro-fuse-cmp test:
https://bugs.llvm.org/show_bug.cgi?id=35681
...there's a 37 -> 31 byte size win for the loop because we eliminate the big base
address offsets.
SPEC2017 on Ryzen shows no significant perf difference.
Differential Revision: https://reviews.llvm.org/D42607
llvm-svn: 324289
diff --git a/llvm/test/Transforms/LoopStrengthReduce/X86/ivchain-X86.ll b/llvm/test/Transforms/LoopStrengthReduce/X86/ivchain-X86.ll
index bf0b574..0be39d3 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/X86/ivchain-X86.ll
+++ b/llvm/test/Transforms/LoopStrengthReduce/X86/ivchain-X86.ll
@@ -347,30 +347,31 @@
; X32-NEXT: pushl %ebx
; X32-NEXT: pushl %edi
; X32-NEXT: pushl %esi
-; X32-NEXT: movl $-400, %eax # imm = 0xFE70
+; X32-NEXT: movl $3, %eax
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: movl {{[0-9]+}}(%esp), %edx
; X32-NEXT: movl {{[0-9]+}}(%esp), %esi
; X32-NEXT: .p2align 4, 0x90
; X32-NEXT: .LBB3_1: # %for.body
; X32-NEXT: # =>This Inner Loop Header: Depth=1
-; X32-NEXT: movzbl 400(%esi,%eax), %edi
-; X32-NEXT: movzbl 400(%edx,%eax), %ebx
+; X32-NEXT: movzbl -3(%esi,%eax), %edi
+; X32-NEXT: movzbl -3(%edx,%eax), %ebx
; X32-NEXT: addl %edi, %ebx
-; X32-NEXT: movb %bl, 400(%ecx,%eax)
-; X32-NEXT: movzbl 401(%esi,%eax), %edi
-; X32-NEXT: movzbl 401(%edx,%eax), %ebx
+; X32-NEXT: movb %bl, -3(%ecx,%eax)
+; X32-NEXT: movzbl -2(%esi,%eax), %edi
+; X32-NEXT: movzbl -2(%edx,%eax), %ebx
; X32-NEXT: addl %edi, %ebx
-; X32-NEXT: movb %bl, 401(%ecx,%eax)
-; X32-NEXT: movzbl 402(%esi,%eax), %edi
-; X32-NEXT: movzbl 402(%edx,%eax), %ebx
+; X32-NEXT: movb %bl, -2(%ecx,%eax)
+; X32-NEXT: movzbl -1(%esi,%eax), %edi
+; X32-NEXT: movzbl -1(%edx,%eax), %ebx
; X32-NEXT: addl %edi, %ebx
-; X32-NEXT: movb %bl, 402(%ecx,%eax)
-; X32-NEXT: movzbl 403(%esi,%eax), %edi
-; X32-NEXT: movzbl 403(%edx,%eax), %ebx
+; X32-NEXT: movb %bl, -1(%ecx,%eax)
+; X32-NEXT: movzbl (%esi,%eax), %edi
+; X32-NEXT: movzbl (%edx,%eax), %ebx
; X32-NEXT: addl %edi, %ebx
-; X32-NEXT: movb %bl, 403(%ecx,%eax)
+; X32-NEXT: movb %bl, (%ecx,%eax)
; X32-NEXT: addl $4, %eax
+; X32-NEXT: cmpl $403, %eax # imm = 0x193
; X32-NEXT: jne .LBB3_1
; X32-NEXT: # %bb.2: # %for.end
; X32-NEXT: popl %esi
diff --git a/llvm/test/Transforms/LoopStrengthReduce/X86/macro-fuse-cmp.ll b/llvm/test/Transforms/LoopStrengthReduce/X86/macro-fuse-cmp.ll
index 219aed4..ba0da16 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/X86/macro-fuse-cmp.ll
+++ b/llvm/test/Transforms/LoopStrengthReduce/X86/macro-fuse-cmp.ll
@@ -43,27 +43,22 @@
;
; HSW-LABEL: @maxArray(
; HSW-NEXT: entry:
-; HSW-NEXT: [[Y1:%.*]] = bitcast double* [[Y:%.*]] to i8*
-; HSW-NEXT: [[X3:%.*]] = bitcast double* [[X:%.*]] to i8*
; HSW-NEXT: br label [[VECTOR_BODY:%.*]]
; HSW: vector.body:
-; HSW-NEXT: [[LSR_IV:%.*]] = phi i64 [ [[LSR_IV_NEXT:%.*]], [[VECTOR_BODY]] ], [ -524288, [[ENTRY:%.*]] ]
-; HSW-NEXT: [[UGLYGEP7:%.*]] = getelementptr i8, i8* [[X3]], i64 [[LSR_IV]]
-; HSW-NEXT: [[UGLYGEP78:%.*]] = bitcast i8* [[UGLYGEP7]] to <2 x double>*
-; HSW-NEXT: [[SCEVGEP9:%.*]] = getelementptr <2 x double>, <2 x double>* [[UGLYGEP78]], i64 32768
-; HSW-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, i8* [[Y1]], i64 [[LSR_IV]]
-; HSW-NEXT: [[UGLYGEP2:%.*]] = bitcast i8* [[UGLYGEP]] to <2 x double>*
-; HSW-NEXT: [[SCEVGEP:%.*]] = getelementptr <2 x double>, <2 x double>* [[UGLYGEP2]], i64 32768
-; HSW-NEXT: [[XVAL:%.*]] = load <2 x double>, <2 x double>* [[SCEVGEP9]], align 8
-; HSW-NEXT: [[YVAL:%.*]] = load <2 x double>, <2 x double>* [[SCEVGEP]], align 8
+; HSW-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; HSW-NEXT: [[SCEVGEP4:%.*]] = getelementptr double, double* [[X:%.*]], i64 [[INDEX]]
+; HSW-NEXT: [[SCEVGEP45:%.*]] = bitcast double* [[SCEVGEP4]] to <2 x double>*
+; HSW-NEXT: [[SCEVGEP:%.*]] = getelementptr double, double* [[Y:%.*]], i64 [[INDEX]]
+; HSW-NEXT: [[SCEVGEP1:%.*]] = bitcast double* [[SCEVGEP]] to <2 x double>*
+; HSW-NEXT: [[XVAL:%.*]] = load <2 x double>, <2 x double>* [[SCEVGEP45]], align 8
+; HSW-NEXT: [[YVAL:%.*]] = load <2 x double>, <2 x double>* [[SCEVGEP1]], align 8
; HSW-NEXT: [[CMP:%.*]] = fcmp ogt <2 x double> [[YVAL]], [[XVAL]]
; HSW-NEXT: [[MAX:%.*]] = select <2 x i1> [[CMP]], <2 x double> [[YVAL]], <2 x double> [[XVAL]]
-; HSW-NEXT: [[UGLYGEP4:%.*]] = getelementptr i8, i8* [[X3]], i64 [[LSR_IV]]
-; HSW-NEXT: [[UGLYGEP45:%.*]] = bitcast i8* [[UGLYGEP4]] to <2 x double>*
-; HSW-NEXT: [[SCEVGEP6:%.*]] = getelementptr <2 x double>, <2 x double>* [[UGLYGEP45]], i64 32768
-; HSW-NEXT: store <2 x double> [[MAX]], <2 x double>* [[SCEVGEP6]], align 8
-; HSW-NEXT: [[LSR_IV_NEXT]] = add nsw i64 [[LSR_IV]], 16
-; HSW-NEXT: [[DONE:%.*]] = icmp eq i64 [[LSR_IV_NEXT]], 0
+; HSW-NEXT: [[SCEVGEP2:%.*]] = getelementptr double, double* [[X]], i64 [[INDEX]]
+; HSW-NEXT: [[SCEVGEP23:%.*]] = bitcast double* [[SCEVGEP2]] to <2 x double>*
+; HSW-NEXT: store <2 x double> [[MAX]], <2 x double>* [[SCEVGEP23]], align 8
+; HSW-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 2
+; HSW-NEXT: [[DONE:%.*]] = icmp eq i64 [[INDEX_NEXT]], 65536
; HSW-NEXT: br i1 [[DONE]], label [[EXIT:%.*]], label [[VECTOR_BODY]]
; HSW: exit:
; HSW-NEXT: ret void
@@ -85,15 +80,16 @@
;
; FUSE-LABEL: maxArray:
; FUSE: # %bb.0: # %entry
-; FUSE-NEXT: movq $-524288, %rax # imm = 0xFFF80000
+; FUSE-NEXT: xorl %eax, %eax
; FUSE-NEXT: .p2align 4, 0x90
; FUSE-NEXT: .LBB0_1: # %vector.body
; FUSE-NEXT: # =>This Inner Loop Header: Depth=1
-; FUSE-NEXT: movupd 524288(%rdi,%rax), %xmm0
-; FUSE-NEXT: movupd 524288(%rsi,%rax), %xmm1
+; FUSE-NEXT: movupd (%rdi,%rax,8), %xmm0
+; FUSE-NEXT: movupd (%rsi,%rax,8), %xmm1
; FUSE-NEXT: maxpd %xmm0, %xmm1
-; FUSE-NEXT: movupd %xmm1, 524288(%rdi,%rax)
-; FUSE-NEXT: addq $16, %rax
+; FUSE-NEXT: movupd %xmm1, (%rdi,%rax,8)
+; FUSE-NEXT: addq $2, %rax
+; FUSE-NEXT: cmpq $65536, %rax # imm = 0x10000
; FUSE-NEXT: jne .LBB0_1
; FUSE-NEXT: # %bb.2: # %exit
; FUSE-NEXT: retq