Improve on r192635, ExeDepsFix for avx, and add a test case.

rdar:15221834 False AVX register dependencies cause 5x slowdown on
flops-5/6 and significant slowdown on several others.

This was blocking the switch to MI-Sched.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192669 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/ExecutionDepsFix.cpp b/lib/CodeGen/ExecutionDepsFix.cpp
index 0d26f9d4cba0b283138712adfbb2c367a58555fb..031f19c135a97df9a81c83ad9f5f73e0a6e24031 100644 (file)
--- a/lib/CodeGen/ExecutionDepsFix.cpp
+++ b/lib/CodeGen/ExecutionDepsFix.cpp
@@ -557,6 +557,9 @@ void ExeDepsFix::processUndefReads(MachineBasicBlock *MBB) {
 
   for (MachineBasicBlock::reverse_iterator I = MBB->rbegin(), E = MBB->rend();
        I != E; ++I) {
+    // Update liveness, including the current instrucion's defs.
+    LiveUnits.stepBackward(*I, *TRI);
+
     if (UndefMI == &*I) {
       if (!LiveUnits.contains(UndefMI->getOperand(OpIdx).getReg(), *TRI))
         TII->breakPartialRegDependency(UndefMI, OpIdx, TRI);
@@ -568,7 +571,6 @@ void ExeDepsFix::processUndefReads(MachineBasicBlock *MBB) {
       UndefMI = UndefReads.back().first;
       OpIdx = UndefReads.back().second;
     }
-    LiveUnits.stepBackward(*I, *TRI);
   }
 }
 

diff --git a/test/CodeGen/X86/break-avx-dep.ll b/test/CodeGen/X86/break-avx-dep.ll
new file mode 100644 (file)
index 0000000..eea7d15
--- /dev/null
+++ b/test/CodeGen/X86/break-avx-dep.ll
@@ -0,0 +1,29 @@
+; RUN: llc < %s -march=x86-64 -mattr=+avx | FileCheck %s
+;
+; rdar:15221834 False AVX register dependencies cause 5x slowdown on
+; flops-6. Make sure the unused register read by vcvtsi2sdq is zeroed
+; to avoid cyclic dependence on a write to the same register in a
+; previous iteration.
+
+; CHECK-LABEL: t1:
+; CHECK-LABEL: %loop
+; CHECK: vxorps %[[REG:xmm.]], %{{xmm.}}, %{{xmm.}}
+; CHECK: vcvtsi2sdq %{{r..}}, %[[REG]], %{{xmm.}}
+define i64 @t1(i64* nocapture %x, double* nocapture %y) nounwind {
+entry:
+  %vx = load i64* %x
+  br label %loop
+loop:
+  %i = phi i64 [ 1, %entry ], [ %inc, %loop ]
+  %s1 = phi i64 [ %vx, %entry ], [ %s2, %loop ]
+  %fi = sitofp i64 %i to double
+  %vy = load double* %y
+  %fipy = fadd double %fi, %vy
+  %iipy = fptosi double %fipy to i64
+  %s2 = add i64 %s1, %iipy
+  %inc = add nsw i64 %i, 1
+  %exitcond = icmp eq i64 %inc, 156250000
+  br i1 %exitcond, label %ret, label %loop
+ret:
+  ret i64 %s2
+}