Scaling up values in ARMBaseInstrInfo::isProfitableToIfCvt() before they are scaled by a probability to avoid precision issue.

In ARMBaseInstrInfo::isProfitableToIfCvt(), there is a simple cost model in which the number of cycles is scaled by a probability to estimate the cost. However, when the number of cycles is small (which is usually the case), there is a precision issue after the computation. To avoid this issue, this patch scales those cycles by 1024 (chosen to make the multiplication a litter faster) before they are scaled by the probability. Other variables are also scaled up for the final comparison.

Differential Revision: http://reviews.llvm.org/D12742

llvm-svn: 248018

4 files changed, 9 insertions, 9 deletions

diff --git a/llvm/test/CodeGen/ARM/2013-10-11-select-stalls.ll b/llvm/test/CodeGen/ARM/2013-10-11-select-stalls.ll
index d6045c7b8c8..c41fe905aa8 100644
--- a/llvm/test/CodeGen/ARM/2013-10-11-select-stalls.ll
+++ b/llvm/test/CodeGen/ARM/2013-10-11-select-stalls.ll
@@ -1,8 +1,13 @@
 ; REQUIRES: asserts
-; RUN: llc < %s -mtriple=thumbv7-apple-ios -stats 2>&1 | not grep "Number of pipeline stalls"
+; RUN: llc < %s -mtriple=thumbv7-apple-ios -disable-ifcvt-diamond -stats 2>&1 | FileCheck %s
 ; Evaluate the two vld1.8 instructions in separate MBB's,
 ; instead of stalling on one and conditionally overwriting its result.
+;
+; Update: After if-conversion the two vld1.8 instructions are in the same MBB
+; again. So we disable this if-conversion to eliminate its influence to this
+; test.
 
+; CHECK-NOT: Number of pipeline stalls
 define <16 x i8> @multiselect(i32 %avail, i8* %foo, i8* %bar) {
 entry:
   %vld1 = call <16 x i8> @llvm.arm.neon.vld1.v16i8(i8* %foo, i32 1)
diff --git a/llvm/test/CodeGen/ARM/ifcvt4.ll b/llvm/test/CodeGen/ARM/ifcvt4.ll
index 8c6825aeda9..0a6b99fb89b 100644
--- a/llvm/test/CodeGen/ARM/ifcvt4.ll
+++ b/llvm/test/CodeGen/ARM/ifcvt4.ll
@@ -1,10 +1,8 @@
 ; RUN: llc -mtriple=arm-eabi %s -o - | FileCheck %s
 
-; Do not if-convert when branches go to the different loops.
 ; CHECK-LABEL: t:
-; CHECK-NOT: subgt
-; CHECK-NOT: suble
-; Don't use
+; CHECK: subgt
+; CHECK: suble
 define i32 @t(i32 %a, i32 %b) {
 entry:
 	%tmp1434 = icmp eq i32 %a, %b		; <i1> [#uses=1]
diff --git a/llvm/test/CodeGen/ARM/sjlj-prepare-critical-edge.ll b/llvm/test/CodeGen/ARM/sjlj-prepare-critical-edge.ll
index c7f47b0962d..a1abef9605c 100644
--- a/llvm/test/CodeGen/ARM/sjlj-prepare-critical-edge.ll
+++ b/llvm/test/CodeGen/ARM/sjlj-prepare-critical-edge.ll
@@ -77,8 +77,8 @@ declare void @terminatev()
 ; CHECK: blx __Znwm
 ; CHECK: {{.*}}@ %entry.do.body.i.i.i_crit_edge
 ; CHECK: str r0, [sp, [[OFFSET:#[0-9]+]]]
-; CHECK: ldr [[R0:r[0-9]+]], [sp, [[OFFSET]]]
 ; CHECK: {{.*}}@ %do.body.i.i.i
+; CHECK: ldr [[R0:r[0-9]+]], [sp, [[OFFSET]]]
 ; CHECK: cbz [[R0]]
 
 %"class.std::__1::basic_string" = type { %"class.std::__1::__compressed_pair" }
diff --git a/llvm/test/CodeGen/ARM/test-sharedidx.ll b/llvm/test/CodeGen/ARM/test-sharedidx.ll
index 77d0f30485d..db32f18d82c 100644
--- a/llvm/test/CodeGen/ARM/test-sharedidx.ll
+++ b/llvm/test/CodeGen/ARM/test-sharedidx.ll
@@ -59,9 +59,6 @@ for.body.1:                                       ; preds = %for.body
   br i1 %cmp.1, label %for.body.2, label %for.end
 
 for.body.2:                                       ; preds = %for.body.1
-; CHECK: %for.body.2
-; CHECK: ldrb {{r[0-9]+|lr}}, [{{r[0-9]+|lr}}, {{r[0-9]+|lr}}]!
-; CHECK: ldrb {{r[0-9]+|lr}}, [{{r[0-9]+|lr}}, {{r[0-9]+|lr}}]!
   %arrayidx.2 = getelementptr inbounds i8, i8* %a, i32 %add5.1
   %4 = load i8, i8* %arrayidx.2, align 1
   %conv6.2 = zext i8 %4 to i32