diff --git a/llvm/include/llvm/Analysis/VecFuncs.def b/llvm/include/llvm/Analysis/VecFuncs.def index 86bec0be7546..2f64b0fedc7a 100644 --- a/llvm/include/llvm/Analysis/VecFuncs.def +++ b/llvm/include/llvm/Analysis/VecFuncs.def @@ -245,6 +245,29 @@ TLI_DEFINE_VECFUNC("llvm.log.f32", "__svml_logf4", 4) TLI_DEFINE_VECFUNC("llvm.log.f32", "__svml_logf8", 8) TLI_DEFINE_VECFUNC("llvm.log.f32", "__svml_logf16", 16) +TLI_DEFINE_VECFUNC("exp2", "__svml_exp22", 2) +TLI_DEFINE_VECFUNC("exp2", "__svml_exp24", 4) +TLI_DEFINE_VECFUNC("exp2", "__svml_exp28", 8) + +TLI_DEFINE_VECFUNC("exp2f", "__svml_exp2f4", 4) +TLI_DEFINE_VECFUNC("exp2f", "__svml_exp2f8", 8) +TLI_DEFINE_VECFUNC("exp2f", "__svml_exp2f16", 16) + +TLI_DEFINE_VECFUNC("llvm.exp2.f64", "__svml_exp22", 2) +TLI_DEFINE_VECFUNC("llvm.exp2.f64", "__svml_exp24", 4) +TLI_DEFINE_VECFUNC("llvm.exp2.f64", "__svml_exp28", 8) + +TLI_DEFINE_VECFUNC("llvm.exp2.f32", "__svml_exp2f4", 4) +TLI_DEFINE_VECFUNC("llvm.exp2.f32", "__svml_exp2f8", 8) +TLI_DEFINE_VECFUNC("llvm.exp2.f32", "__svml_exp2f16", 16) + +TLI_DEFINE_VECFUNC("__exp2_finite", "__svml_exp22", 2) +TLI_DEFINE_VECFUNC("__exp2_finite", "__svml_exp24", 4) +TLI_DEFINE_VECFUNC("__exp2_finite", "__svml_exp28", 8) + +TLI_DEFINE_VECFUNC("__exp2f_finite", "__svml_exp2f4", 4) +TLI_DEFINE_VECFUNC("__exp2f_finite", "__svml_exp2f8", 8) +TLI_DEFINE_VECFUNC("__exp2f_finite", "__svml_exp2f16", 16) #else #error "Must choose which vector library functions are to be defined." diff --git a/llvm/test/Transforms/LoopVectorize/X86/svml-calls.ll b/llvm/test/Transforms/LoopVectorize/X86/svml-calls.ll index 8ff62f178d09..c1af2cb9f413 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/svml-calls.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/svml-calls.ll @@ -28,6 +28,12 @@ declare float @logf(float) #0 declare double @llvm.log.f64(double) #0 declare float @llvm.log.f32(float) #0 +declare double @exp2(double) #0 +declare float @exp2f(float) #0 +declare double @llvm.exp2.f64(double) #0 +declare float @llvm.exp2.f32(float) #0 +declare double @__exp2_finite(double) #0 +declare float @__exp2f_finite(float) #0 define void @sin_f64(double* nocapture %varray) { ; CHECK-LABEL: @sin_f64( @@ -497,5 +503,142 @@ for.end: ret void } -attributes #0 = { nounwind readnone } +define void @exp2_f64(double* nocapture %varray) { +; CHECK-LABEL: @exp2_f64( +; CHECK: [[TMP5:%.*]] = call <4 x double> @__svml_exp24(<4 x double> [[TMP4:%.*]]) +; CHECK: ret void +; +entry: + br label %for.body +for.body: + %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ] + %tmp = trunc i64 %iv to i32 + %conv = sitofp i32 %tmp to double + %call = tail call double @exp2(double %conv) + %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv + store double %call, double* %arrayidx, align 4 + %iv.next = add nuw nsw i64 %iv, 1 + %exitcond = icmp eq i64 %iv.next, 1000 + br i1 %exitcond, label %for.end, label %for.body + +for.end: + ret void +} + +define void @exp2_f32(float* nocapture %varray) { +; CHECK-LABEL: @exp2_f32( +; CHECK: [[TMP5:%.*]] = call <4 x float> @__svml_exp2f4(<4 x float> [[TMP4:%.*]]) +; CHECK: ret void +; +entry: + br label %for.body + +for.body: + %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ] + %tmp = trunc i64 %iv to i32 + %conv = sitofp i32 %tmp to float + %call = tail call float @exp2f(float %conv) + %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv + store float %call, float* %arrayidx, align 4 + %iv.next = add nuw nsw i64 %iv, 1 + %exitcond = icmp eq i64 %iv.next, 1000 + br i1 %exitcond, label %for.end, label %for.body + +for.end: + ret void +} + +define void @exp2_f64_intrinsic(double* nocapture %varray) { +; CHECK-LABEL: @exp2_f64_intrinsic( +; CHECK: [[TMP5:%.*]] = call <4 x double> @__svml_exp24(<4 x double> [[TMP4:%.*]]) +; CHECK: ret void +; +entry: + br label %for.body + +for.body: + %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ] + %tmp = trunc i64 %iv to i32 + %conv = sitofp i32 %tmp to double + %call = tail call double @llvm.exp2.f64(double %conv) + %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv + store double %call, double* %arrayidx, align 4 + %iv.next = add nuw nsw i64 %iv, 1 + %exitcond = icmp eq i64 %iv.next, 1000 + br i1 %exitcond, label %for.end, label %for.body + +for.end: + ret void +} + +define void @exp2_f32_intrinsic(float* nocapture %varray) { +; CHECK-LABEL: @exp2_f32_intrinsic( +; CHECK: [[TMP5:%.*]] = call <4 x float> @__svml_exp2f4(<4 x float> [[TMP4:%.*]]) +; CHECK: ret void +; +entry: + br label %for.body + +for.body: + %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ] + %tmp = trunc i64 %iv to i32 + %conv = sitofp i32 %tmp to float + %call = tail call float @llvm.exp2.f32(float %conv) + %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv + store float %call, float* %arrayidx, align 4 + %iv.next = add nuw nsw i64 %iv, 1 + %exitcond = icmp eq i64 %iv.next, 1000 + br i1 %exitcond, label %for.end, label %for.body + +for.end: + ret void +} + +define void @exp2f_finite(float* nocapture %varray) { +; CHECK-LABEL: @exp2f_finite( +; CHECK: [[TMP5:%.*]] = call <4 x float> @__svml_exp2f4(<4 x float> [[TMP4:%.*]]) +; CHECK: ret void +; +entry: + br label %for.body + +for.body: + %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ] + %tmp = trunc i64 %iv to i32 + %conv = sitofp i32 %tmp to float + %call = tail call float @__exp2f_finite(float %conv) + %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv + store float %call, float* %arrayidx, align 4 + %iv.next = add nuw nsw i64 %iv, 1 + %exitcond = icmp eq i64 %iv.next, 1000 + br i1 %exitcond, label %for.end, label %for.body + +for.end: + ret void +} + +define void @exp2_finite(double* nocapture %varray) { +; CHECK-LABEL: @exp2_finite( +; CHECK: [[TMP5:%.*]] = call <4 x double> @__svml_exp24(<4 x double> [[TMP4:%.*]]) +; CHECK: ret void +; +entry: + br label %for.body + +for.body: + %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ] + %tmp = trunc i64 %iv to i32 + %conv = sitofp i32 %tmp to double + %call = tail call double @__exp2_finite(double %conv) + %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv + store double %call, double* %arrayidx, align 4 + %iv.next = add nuw nsw i64 %iv, 1 + %exitcond = icmp eq i64 %iv.next, 1000 + br i1 %exitcond, label %for.end, label %for.body + +for.end: + ret void +} + +attributes #0 = { nounwind readnone }