[X86] Remove FeatureSlowIncDec from Sandy Bridge and later Intel Core…

… CPUs Summary: Inc and Dec were at one point slow on Intel CPUs due to their tendency to cause partial flag stalls on P6 derived CPU cores. This is because these instructions are defined to preserve the carry flag. This partial flag stall issue persisted until Sandy Bridge when flag merging was changed to be handled as a data dependency instead of as a stall until retirement. Sandy Bridge and later CPUs rename the C flag separately from OSPAZ so there is no flag merge needed on INC/DEC to preserve the C flag. Given these improvements I don't know why INC/DEC was ever considered slow on Sandy Bridge. If anything they should have been disabled on the earlier CPUs instead. Note after this patch, INC/DEC are still considered slow on Silvermont, Goldmont, Knights Landing and our generic "x86-64" CPU. Reviewers: spatel, RKSimon, chandlerc Reviewed By: chandlerc Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D58412 llvm-svn: 354436
llvm · Feb 20, 2019 · e4025c5 · e4025c5
1 parent a07f1b9
commit e4025c5
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 4 deletions.
diff --git a/llvm/lib/Target/X86/X86.td b/llvm/lib/Target/X86/X86.td
@@ -733,7 +733,6 @@ def SNBFeatures : ProcessorFeatures<[], [
   FeatureSlow3OpsLEA,
   FeatureFastScalarFSQRT,
   FeatureFastSHLDRotate,
-  FeatureSlowIncDec,
   FeatureMergeToThreeWayBranch,
   FeatureMacroFusion
 ]>;

diff --git a/llvm/test/CodeGen/X86/mul-constant-result.ll b/llvm/test/CodeGen/X86/mul-constant-result.ll
@@ -254,7 +254,7 @@ define i32 @mult(i32, i32) local_unnamed_addr #0 {
 ; X64-HSW-NEXT:    cmovgl %ecx, %eax
 ; X64-HSW-NEXT:    testl %esi, %esi
 ; X64-HSW-NEXT:    cmovel %ecx, %eax
-; X64-HSW-NEXT:    addl $-1, %edi
+; X64-HSW-NEXT:    decl %edi
 ; X64-HSW-NEXT:    cmpl $31, %edi
 ; X64-HSW-NEXT:    ja .LBB0_36
 ; X64-HSW-NEXT:  # %bb.1:

diff --git a/llvm/test/CodeGen/X86/rdrand.ll b/llvm/test/CodeGen/X86/rdrand.ll
@@ -94,7 +94,7 @@ define void @loop(i32* %p, i32 %n) nounwind {
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    rdrandl %esi
 ; X86-NEXT:    movl %esi, (%ecx,%edx,4)
-; X86-NEXT:    addl $1, %edx
+; X86-NEXT:    incl %edx
 ; X86-NEXT:    cmpl %edx, %eax
 ; X86-NEXT:    jne .LBB3_2
 ; X86-NEXT:  .LBB3_3: # %while.end
@@ -113,7 +113,7 @@ define void @loop(i32* %p, i32 %n) nounwind {
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    rdrandl %edx
 ; X64-NEXT:    movl %edx, (%rdi,%rcx,4)
-; X64-NEXT:    addq $1, %rcx
+; X64-NEXT:    incq %rcx
 ; X64-NEXT:    cmpl %ecx, %eax
 ; X64-NEXT:    jne .LBB3_2
 ; X64-NEXT:  .LBB3_3: # %while.end