MachineCopyPropagation: Catch copies of the form A<-B;A<-B

Differential Revision: http://reviews.llvm.org/D17475

llvm-svn: 261966

3 files changed, 108 insertions, 9 deletions

diff --git a/llvm/test/CodeGen/AMDGPU/llvm.AMDGPU.rsq.clamped.f64.ll b/llvm/test/CodeGen/AMDGPU/llvm.AMDGPU.rsq.clamped.f64.ll
index 67f1d22c717..6cf4b4c3e55 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.AMDGPU.rsq.clamped.f64.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.AMDGPU.rsq.clamped.f64.ll
@@ -10,11 +10,10 @@ declare double @llvm.AMDGPU.rsq.clamped.f64(double) nounwind readnone
 ; TODO: this constant should be folded:
 ; VI: s_mov_b32 s[[ALLBITS:[0-9+]]], -1
 ; VI: s_mov_b32 s[[HIGH1:[0-9+]]], 0x7fefffff
-; VI: s_mov_b32 s[[LOW1:[0-9+]]], s[[ALLBITS]]
-; VI: v_min_f64 v[0:1], [[RSQ]], s{{\[}}[[LOW1]]:[[HIGH1]]]
+; VI: s_mov_b32 s[[LOW:[0-9+]]], s[[ALLBITS]]
+; VI: v_min_f64 v[0:1], [[RSQ]], s{{\[}}[[LOW]]:[[HIGH1]]]
 ; VI: s_mov_b32 s[[HIGH2:[0-9+]]], 0xffefffff
-; VI: s_mov_b32 s[[LOW2:[0-9+]]], s[[ALLBITS]]
-; VI: v_max_f64 v[0:1], v[0:1], s{{\[}}[[LOW2]]:[[HIGH2]]]
+; VI: v_max_f64 v[0:1], v[0:1], s{{\[}}[[LOW]]:[[HIGH2]]]
 
 define void @rsq_clamped_f64(double addrspace(1)* %out, double %src) nounwind {
   %rsq_clamped = call double @llvm.AMDGPU.rsq.clamped.f64(double %src) nounwind readnone
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.rsq.clamp.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.rsq.clamp.ll
index ede1df76f2e..52292f6daa5 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.rsq.clamp.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.rsq.clamp.ll
@@ -28,11 +28,10 @@ define void @rsq_clamp_f32(float addrspace(1)* %out, float %src) #0 {
 ; TODO: this constant should be folded:
 ; VI: s_mov_b32 s[[ALLBITS:[0-9+]]], -1
 ; VI: s_mov_b32 s[[HIGH1:[0-9+]]], 0x7fefffff
-; VI: s_mov_b32 s[[LOW1:[0-9+]]], s[[ALLBITS]]
-; VI: v_min_f64 v[0:1], [[RSQ]], s{{\[}}[[LOW1]]:[[HIGH1]]]
+; VI: s_mov_b32 s[[LOW:[0-9+]]], s[[ALLBITS]]
+; VI: v_min_f64 v[0:1], [[RSQ]], s{{\[}}[[LOW]]:[[HIGH1]]]
 ; VI: s_mov_b32 s[[HIGH2:[0-9+]]], 0xffefffff
-; VI: s_mov_b32 s[[LOW2:[0-9+]]], s[[ALLBITS]]
-; VI: v_max_f64 v[0:1], v[0:1], s{{\[}}[[LOW2]]:[[HIGH2]]]
+; VI: v_max_f64 v[0:1], v[0:1], s{{\[}}[[LOW]]:[[HIGH2]]]
 define void @rsq_clamp_f64(double addrspace(1)* %out, double %src) #0 {
   %rsq_clamp = call double @llvm.amdgcn.rsq.clamp.f64(double %src)
   store double %rsq_clamp, double addrspace(1)* %out
diff --git a/llvm/test/CodeGen/X86/machine-copy-prop.mir b/llvm/test/CodeGen/X86/machine-copy-prop.mir
index cf566edf253..a9b9c57bcc5 100644
--- a/llvm/test/CodeGen/X86/machine-copy-prop.mir
+++ b/llvm/test/CodeGen/X86/machine-copy-prop.mir
@@ -1,4 +1,4 @@
-# RUN: llc -march=x86 -run-pass machine-cp -o /dev/null %s 2>&1 | FileCheck %s
+# RUN: llc -march=x86 -run-pass machine-cp -verify-machineinstrs -o /dev/null %s 2>&1 | FileCheck %s
 
 --- |
   declare void @foo()
@@ -6,8 +6,14 @@
   define void @copyprop_remove_kill1() { ret void }
   define void @copyprop_remove_kill2() { ret void }
   define void @copyprop0() { ret void }
+  define void @copyprop1() { ret void }
+  define void @copyprop2() { ret void }
   define void @nocopyprop0() { ret void }
   define void @nocopyprop1() { ret void }
+  define void @nocopyprop2() { ret void }
+  define void @nocopyprop3() { ret void }
+  define void @nocopyprop4() { ret void }
+  define void @nocopyprop5() { ret void }
 ...
 ---
 # The second copy is redundant and will be removed, check that we also remove
@@ -79,6 +85,38 @@ body: |
     NOOP implicit %rax, implicit %rdi
 ...
 ---
+# The 2nd copy is redundant; The call preserves the source and dest register.
+# CHECK-LABEL: name: copyprop1
+# CHECK: bb.0:
+# CHECK-NEXT: %rax = COPY %rdi
+# CHECK-NEXT: NOOP implicit %rax
+# CHECK-NEXT: NOOP implicit %rax, implicit %rdi
+name: copyprop1
+body: |
+  bb.0:
+    %rax = COPY %rdi
+    NOOP implicit killed %rax
+    %rax = COPY %rdi
+    NOOP implicit %rax, implicit %rdi
+...
+---
+# CHECK-LABEL: name: copyprop2
+# CHECK: bb.0:
+# CHECK-NEXT: %rax = COPY %rdi
+# CHECK-NEXT: NOOP implicit %ax
+# CHECK-NEXT: CALL64pcrel32 @foo, csr_64_rt_mostregs
+# CHECK-NOT: %rax = COPY %rdi
+# CHECK-NEXT: NOOP implicit %rax, implicit %rdi
+name: copyprop2
+body: |
+  bb.0:
+    %rax = COPY %rdi
+    NOOP implicit killed %ax
+    CALL64pcrel32 @foo, csr_64_rt_mostregs
+    %rax = COPY %rdi
+    NOOP implicit %rax, implicit %rdi
+...
+---
 # The second copy is not redundant if the source register (%rax) is clobbered
 # even if the dest (%rbp) is not.
 # CHECK-LABEL: name: nocopyprop0
@@ -112,3 +150,66 @@ body: |
     %rax = COPY %rbp
     NOOP implicit %rax, implicit %rbp
 ...
+---
+# The second copy is not redundant if the source register (%rax) is clobbered
+# even if the dest (%rbp) is not.
+# CHECK-LABEL: name: nocopyprop2
+# CHECK: bb.0:
+# CHECK-NEXT: %rax = COPY %rbp
+# CHECK-NEXT: CALL64pcrel32 @foo, csr_64, implicit %rax, implicit %rbp
+# CHECK-NEXT: %rax = COPY %rbp
+# CHECK-NEXT: NOOP implicit %rax, implicit %rbp
+name: nocopyprop2
+body: |
+  bb.0:
+    %rax = COPY %rbp
+    CALL64pcrel32 @foo, csr_64, implicit %rax, implicit %rbp
+    %rax = COPY %rbp
+    NOOP implicit %rax, implicit %rbp
+...
+---
+# The second copy is not redundant if the dest register (%rax) is clobbered
+# even if the source (%rbp) is not.
+# CHECK-LABEL: name: nocopyprop3
+# CHECK: bb.0:
+# CHECK-NEXT: %rbp = COPY %rax
+# CHECK-NEXT: CALL64pcrel32 @foo, csr_64, implicit %rax, implicit %rbp
+# CHECK-NEXT: %rbp = COPY %rax
+# CHECK-NEXT: NOOP implicit %rax, implicit %rbp
+name: nocopyprop3
+body: |
+  bb.0:
+    %rbp = COPY %rax
+    CALL64pcrel32 @foo, csr_64, implicit %rax, implicit %rbp
+    %rbp = COPY %rax
+    NOOP implicit %rax, implicit %rbp
+...
+---
+# A reserved register may change its value so the 2nd copy is not redundant.
+# CHECK-LABEL: name: nocopyprop4
+# CHECK: bb.0:
+# CHECK-NEXT: %rax = COPY %rip
+# CHECK-NEXT: NOOP implicit %rax
+# CHECK-NEXT: %rax = COPY %rip
+# CHECK-NEXT: NOOP implicit %rax
+name: nocopyprop4
+body: |
+  bb.0:
+    %rax = COPY %rip
+    NOOP implicit %rax
+    %rax = COPY %rip
+    NOOP implicit %rax
+...
+---
+# Writing to a reserved register may have additional effects (slightly illegal
+# testcase because writing to %rip like this should make the instruction a jump)
+# CHECK-LABEL: name: nocopyprop5
+# CHECK: bb.0:
+# CHECK-NEXT: %rip = COPY %rax
+# CHECK-NEXT: %rip = COPY %rax
+name: nocopyprop5
+body: |
+  bb.0:
+    %rip = COPY %rax
+    %rip = COPY %rax
+...