As Dan pointed out, movzbl, movsbl, and friends are nicer than their alias

[oota-llvm.git] / test / CodeGen / X86 / sink-hoist.ll

diff --git a/test/CodeGen/X86/sink-hoist.ll b/test/CodeGen/X86/sink-hoist.ll
index 1da30ad26f56ffaefc7ea2d7c76c11c534a25b6c..31f41eebc5aa4e5d126357e03949fb75ec9f03ed 100644 (file)
--- a/test/CodeGen/X86/sink-hoist.ll
+++ b/test/CodeGen/X86/sink-hoist.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86-64 -asm-verbose=false | FileCheck %s
+; RUN: llc < %s -march=x86-64 -asm-verbose=false -mtriple=x86_64-unknown-linux-gnu -post-RA-scheduler=true | FileCheck %s
 
 ; Currently, floating-point selects are lowered to CFG triangles.
 ; This means that one side of the select is always unconditionally
@@ -6,10 +6,11 @@
 ; that it's conditionally evaluated.
 
 ; CHECK: foo:
-; CHECK:      divsd
 ; CHECK-NEXT: testb $1, %dil
-; CHECK-NEXT: jne
+; CHECK-NEXT: je
 ; CHECK-NEXT: divsd
+; CHECK-NEXT: ret
+; CHECK:      divsd
 
 define double @foo(double %x, double %y, i1 %c) nounwind {
   %a = fdiv double %x, 3.2
@@ -18,6 +19,24 @@ define double @foo(double %x, double %y, i1 %c) nounwind {
   ret double %z
 }
 
+; Make sure the critical edge is broken so the divsd is sunken below
+; the conditional branch.
+; rdar://8454886
+
+; CHECK: split:
+; CHECK-NEXT: testb $1, %dil
+; CHECK-NEXT: je
+; CHECK-NEXT: divsd
+; CHECK-NEXT: ret
+; CHECK:      movaps
+; CHECK-NEXT: ret
+define double @split(double %x, double %y, i1 %c) nounwind {
+  %a = fdiv double %x, 3.2
+  %z = select i1 %c, double %a, double %y
+  ret double %z
+}
+
+
 ; Hoist floating-point constant-pool loads out of loops.
 
 ; CHECK: bar:
@@ -44,26 +63,33 @@ return:
 
 ; Sink instructions with dead EFLAGS defs.
 
-; CHECK: zzz:
-; CHECK:      je
-; CHECK-NEXT: orb
+; FIXME: Unfail the zzz test if we can correctly mark pregs with the kill flag.
+; 
+; See <rdar://problem/8030636>. This test isn't valid after we made machine
+; sinking more conservative about sinking instructions that define a preg into a
+; block when we don't know if the preg is killed within the current block.
 
-define zeroext i8 @zzz(i8 zeroext %a, i8 zeroext %b) nounwind readnone {
-entry:
-  %tmp = zext i8 %a to i32                        ; <i32> [#uses=1]
-  %tmp2 = icmp eq i8 %a, 0                    ; <i1> [#uses=1]
-  %tmp3 = or i8 %b, -128                          ; <i8> [#uses=1]
-  %tmp4 = and i8 %b, 127                          ; <i8> [#uses=1]
-  %b_addr.0 = select i1 %tmp2, i8 %tmp4, i8 %tmp3 ; <i8> [#uses=1]
-  ret i8 %b_addr.0
-}
+
+; FIXMEHECK: zzz:
+; FIXMEHECK:      je
+; FIXMEHECK-NEXT: orb
+
+; define zeroext i8 @zzz(i8 zeroext %a, i8 zeroext %b) nounwind readnone {
+; entry:
+;   %tmp = zext i8 %a to i32                        ; <i32> [#uses=1]
+;   %tmp2 = icmp eq i8 %a, 0                    ; <i1> [#uses=1]
+;   %tmp3 = or i8 %b, -128                          ; <i8> [#uses=1]
+;   %tmp4 = and i8 %b, 127                          ; <i8> [#uses=1]
+;   %b_addr.0 = select i1 %tmp2, i8 %tmp4, i8 %tmp3 ; <i8> [#uses=1]
+;   ret i8 %b_addr.0
+; }
 
 ; Codegen should hoist and CSE these constants.
 
 ; CHECK: vv:
-; CHECK: LCPI4_0(%rip), %xmm0
-; CHECK: LCPI4_1(%rip), %xmm1
-; CHECK: LCPI4_2(%rip), %xmm2
+; CHECK: LCPI3_0(%rip), %xmm0
+; CHECK: LCPI3_1(%rip), %xmm1
+; CHECK: LCPI3_2(%rip), %xmm2
 ; CHECK: align
 ; CHECK-NOT: LCPI
 ; CHECK: ret
@@ -120,3 +146,29 @@ return:                                           ; preds = %bb60
 declare <4 x float> @llvm.x86.sse.cmp.ps(<4 x float>, <4 x float>, i8) nounwind readnone
 
 declare <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32>) nounwind readnone
+
+; CodeGen should use the correct register class when extracting
+; a load from a zero-extending load for hoisting.
+
+; CHECK: default_get_pch_validity:
+; CHECK: movl cl_options_count(%rip), %ecx
+
+@cl_options_count = external constant i32         ; <i32*> [#uses=2]
+
+define void @default_get_pch_validity() nounwind {
+entry:
+  %tmp4 = load i32* @cl_options_count, align 4    ; <i32> [#uses=1]
+  %tmp5 = icmp eq i32 %tmp4, 0                    ; <i1> [#uses=1]
+  br i1 %tmp5, label %bb6, label %bb2
+
+bb2:                                              ; preds = %bb2, %entry
+  %i.019 = phi i64 [ 0, %entry ], [ %tmp25, %bb2 ] ; <i64> [#uses=1]
+  %tmp25 = add i64 %i.019, 1                      ; <i64> [#uses=2]
+  %tmp11 = load i32* @cl_options_count, align 4   ; <i32> [#uses=1]
+  %tmp12 = zext i32 %tmp11 to i64                 ; <i64> [#uses=1]
+  %tmp13 = icmp ugt i64 %tmp12, %tmp25            ; <i1> [#uses=1]
+  br i1 %tmp13, label %bb2, label %bb6
+
+bb6:                                              ; preds = %bb2, %entry
+  ret void
+}