[PowerPC] Fold i1 extensions with other ops
Consider this function from our README.txt file:
int foo(int a, int b) { return (a < b) << 4; }
We now explicitly track CR bits by default, so the comment in the README.txt
about not really having a SETCC is no longer accurate, but we did generate this
somewhat silly code:
cmpw 0, 3, 4
li 3, 0
li 12, 1
isel 3, 12, 3, 0
sldi 3, 3, 4
blr
which generates the zext as a select between 0 and 1, and then shifts the
result by a constant amount. Here we preprocess the DAG in order to fold the
results of operations on an extension of an i1 value into the SELECT_I[48]
pseudo instruction when the resulting constant can be materialized using one
instruction (just like the 0 and 1). This was not implemented as a DAGCombine
because the resulting code would have been anti-canonical and depends on
replacing chained user nodes, which does not fit well into the lowering
paradigm. Now we generate:
cmpw 0, 3, 4
li 3, 0
li 12, 16
isel 3, 12, 3, 0
blr
which is less silly.
llvm-svn: 225203
diff --git a/llvm/test/CodeGen/PowerPC/i1-ext-fold.ll b/llvm/test/CodeGen/PowerPC/i1-ext-fold.ll
new file mode 100644
index 0000000..19bd8ff
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/i1-ext-fold.ll
@@ -0,0 +1,54 @@
+; RUN: llc -mcpu=pwr7 < %s | FileCheck %s
+target datalayout = "E-m:e-i64:64-n32:64"
+target triple = "powerpc64-unknown-linux-gnu"
+
+; Function Attrs: nounwind readnone
+define signext i32 @foo(i32 signext %a, i32 signext %b) #0 {
+entry:
+ %cmp = icmp slt i32 %a, %b
+ %conv = zext i1 %cmp to i32
+ %shl = shl nuw nsw i32 %conv, 4
+ ret i32 %shl
+
+; CHECK-LABEL: @foo
+; CHECK-DAG: cmpw
+; CHECK-DAG: li [[REG1:[0-9]+]], 0
+; CHECK-DAG: li [[REG2:[0-9]+]], 16
+; CHECK: isel 3, [[REG2]], [[REG1]],
+; CHECK: blr
+}
+
+; Function Attrs: nounwind readnone
+define signext i32 @foo2(i32 signext %a, i32 signext %b) #0 {
+entry:
+ %cmp = icmp slt i32 %a, %b
+ %conv = zext i1 %cmp to i32
+ %shl = shl nuw nsw i32 %conv, 4
+ %add1 = or i32 %shl, 5
+ ret i32 %add1
+
+; CHECK-LABEL: @foo2
+; CHECK-DAG: cmpw
+; CHECK-DAG: li [[REG1:[0-9]+]], 5
+; CHECK-DAG: li [[REG2:[0-9]+]], 21
+; CHECK: isel 3, [[REG2]], [[REG1]],
+; CHECK: blr
+}
+
+; Function Attrs: nounwind readnone
+define signext i32 @foo3(i32 signext %a, i32 signext %b) #0 {
+entry:
+ %cmp = icmp sle i32 %a, %b
+ %conv = zext i1 %cmp to i32
+ %shl = shl nuw nsw i32 %conv, 4
+ ret i32 %shl
+
+; CHECK-LABEL: @foo3
+; CHECK-DAG: cmpw
+; CHECK-DAG: li [[REG1:[0-9]+]], 16
+; CHECK: isel 3, 0, [[REG1]],
+; CHECK: blr
+}
+
+attributes #0 = { nounwind readnone }
+