[CodeGen] Generic Hardware Loop Support
Patch which introduces a target-independent framework for generating
hardware loops at the IR level. Most of the code has been taken from
PowerPC CTRLoops and PowerPC has been ported over to use this generic
pass. The target dependent parts have been moved into
TargetTransformInfo, via isHardwareLoopProfitable, with
HardwareLoopInfo introduced to transfer information from the backend.
Three generic intrinsics have been introduced:
- void @llvm.set_loop_iterations
Takes as a single operand, the number of iterations to be executed.
- i1 @llvm.loop_decrement(anyint)
Takes the maximum number of elements processed in an iteration of
the loop body and subtracts this from the total count. Returns
false when the loop should exit.
- anyint @llvm.loop_decrement_reg(anyint, anyint)
Takes the number of elements remaining to be processed as well as
the maximum numbe of elements processed in an iteration of the loop
body. Returns the updated number of elements remaining.
llvm-svn: 362774
diff --git a/llvm/test/CodeGen/PowerPC/ctrloop-intrin.ll b/llvm/test/CodeGen/PowerPC/ctrloop-intrin.ll
index 6ae5d33..9e18280 100644
--- a/llvm/test/CodeGen/PowerPC/ctrloop-intrin.ll
+++ b/llvm/test/CodeGen/PowerPC/ctrloop-intrin.ll
@@ -263,7 +263,7 @@
%8 = sub i64 0, %int_part_ptr.02534
%scevgep5 = getelementptr i8, i8* %call109, i64 %8
%scevgep56 = ptrtoint i8* %scevgep5 to i64
- call void @llvm.ppc.mtctr.i64(i64 %scevgep56)
+ call void @llvm.set.loop.iterations.i64(i64 %scevgep56)
br label %for.body.116
for.cond.cleanup: ; preds = %if.end.138, %if.end.105
@@ -298,8 +298,9 @@
%conv134 = trunc i32 %add133 to i8
%scevgep = getelementptr i8, i8* inttoptr (i64 -1 to i8*), i64 %call109.pn2
store i8 %conv134, i8* %scevgep, align 1, !tbaa !10
- %12 = call i1 @llvm.ppc.is.decremented.ctr.nonzero()
- br i1 %12, label %for.body.116, label %for.cond.cleanup.115
+ %12 = call i64 @llvm.loop.dec(i64 %scevgep56, i64 1)
+ %dec.cmp = icmp ne i64 %12, 0
+ br i1 %dec.cmp, label %for.body.116, label %for.cond.cleanup.115
if.then.136: ; preds = %for.cond.cleanup.115
%incdec.ptr137 = getelementptr inbounds i8, i8* %int_part_ptr.0253, i64 -1
@@ -323,10 +324,10 @@
declare i8* @memcpy(i8*, i8* nocapture readonly, i64) #1
; Function Attrs: nounwind
-declare void @llvm.ppc.mtctr.i64(i64) #0
+declare void @llvm.set.loop.iterations.i64(i64) #0
; Function Attrs: nounwind
-declare i1 @llvm.ppc.is.decremented.ctr.nonzero() #0
+declare i64 @llvm.loop.dec(i64, i64) #0
attributes #0 = { nounwind }
attributes #1 = { nounwind "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
diff --git a/llvm/test/CodeGen/PowerPC/ppc-passname.ll b/llvm/test/CodeGen/PowerPC/ppc-passname.ll
index 38bf60c..005f0a2 100644
--- a/llvm/test/CodeGen/PowerPC/ppc-passname.ll
+++ b/llvm/test/CodeGen/PowerPC/ppc-passname.ll
@@ -1,15 +1,3 @@
-; Test pass name: ppc-ctr-loops.
-; RUN: llc -mtriple=powerpc64le-unknown-unknown < %s -debug-pass=Structure -stop-before=ppc-ctr-loops -o /dev/null 2>&1 | FileCheck %s -check-prefix=STOP-BEFORE-CTR-LOOPS
-; STOP-BEFORE-CTR-LOOPS-NOT: -ppc-ctr-loops
-; STOP-BEFORE-CTR-LOOPS-NOT: "ppc-ctr-loops" pass is not registered.
-; STOP-BEFORE-CTR-LOOPS-NOT: PowerPC CTR Loops
-
-; RUN: llc -mtriple=powerpc64le-unknown-unknown < %s -debug-pass=Structure -stop-after=ppc-ctr-loops -o /dev/null 2>&1 | FileCheck %s -check-prefix=STOP-AFTER-CTR-LOOPS
-; STOP-AFTER-CTR-LOOPS: -ppc-ctr-loops
-; STOP-AFTER-CTR-LOOPS-NOT: "ppc-ctr-loops" pass is not registered.
-; STOP-AFTER-CTR-LOOPS: PowerPC CTR Loops
-
-
; Test pass name: ppc-loop-preinc-prep.
; RUN: llc -mtriple=powerpc64le-unknown-unknown < %s -debug-pass=Structure -stop-before=ppc-loop-preinc-prep -o /dev/null 2>&1 | FileCheck %s -check-prefix=STOP-BEFORE-LOOP-PREINC-PREP
; STOP-BEFORE-LOOP-PREINC-PREP-NOT: -ppc-loop-preinc-prep