2c7786e94a
This is a follow up to 924907bc6, and is mostly motivated by consistency but does include one additional optimization. In general, we prefer 0.0 over -0.0 as the identity value for an fadd. We use that value in several places, but don't in others. So, let's be consistent and use the same identity (when nsz allows) everywhere. This creates a bunch of test churn, but due to 924907bc6, most of that churn doesn't actually indicate a change in codegen. The exception is that this change enables the use of 0.0 for nsz, but *not* reasoc, fadd reductions. Or said differently, it allows the neutral value of an ordered fadd reduction to be 0.0.
56 lines
2.3 KiB
LLVM
56 lines
2.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -vector-library=MASSV -force-vector-interleave=1 \
|
|
; RUN: -vectorizer-maximize-bandwidth -passes='default<O2>,inject-tli-mappings,loop-vectorize' \
|
|
; RUN: -mtriple=powerpc64le-unknown-linux -S -mcpu=pwr9 2>&1 | FileCheck %s
|
|
|
|
define dso_local double @test(ptr %Arr) {
|
|
; CHECK-LABEL: @test(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
|
|
; CHECK: vector.body:
|
|
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <2 x double> [ zeroinitializer, [[ENTRY]] ], [ [[TMP3:%.*]], [[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds float, ptr [[ARR:%.*]], i64 [[INDEX]]
|
|
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <2 x float>, ptr [[TMP0]], align 4
|
|
; CHECK-NEXT: [[TMP1:%.*]] = fpext <2 x float> [[WIDE_LOAD]] to <2 x double>
|
|
; CHECK-NEXT: [[TMP2:%.*]] = tail call fast <2 x double> @__sind2(<2 x double> [[TMP1]])
|
|
; CHECK-NEXT: [[TMP3]] = fadd fast <2 x double> [[TMP2]], [[VEC_PHI]]
|
|
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
|
|
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], 128
|
|
; CHECK-NEXT: br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
|
|
; CHECK: middle.block:
|
|
; CHECK-NEXT: [[DOTLCSSA:%.*]] = phi <2 x double> [ [[TMP3]], [[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[TMP5:%.*]] = tail call fast double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> [[DOTLCSSA]])
|
|
; CHECK-NEXT: ret double [[TMP5]]
|
|
;
|
|
entry:
|
|
br label %for.cond
|
|
|
|
for.cond:
|
|
%Sum.0 = phi double [ 0.000000e+00, %entry ], [ %add, %for.inc ]
|
|
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
|
|
%cmp = icmp slt i32 %i.0, 128
|
|
br i1 %cmp, label %for.body, label %for.cond.cleanup
|
|
|
|
for.cond.cleanup:
|
|
br label %for.end
|
|
|
|
for.body:
|
|
%idxprom = sext i32 %i.0 to i64
|
|
%arrayidx = getelementptr inbounds float, ptr %Arr, i64 %idxprom
|
|
%0 = load float, ptr %arrayidx, align 4
|
|
%conv = fpext float %0 to double
|
|
%1 = call fast double @llvm.sin.f64(double %conv)
|
|
%add = fadd fast double %Sum.0, %1
|
|
br label %for.inc
|
|
|
|
for.inc:
|
|
%inc = add nsw i32 %i.0, 1
|
|
br label %for.cond
|
|
|
|
for.end:
|
|
ret double %Sum.0
|
|
}
|
|
|
|
declare double @llvm.sin.f64(double)
|