Removing sqrtd2 and sqrtf4 from list of vectorizable function with MASSV

[masoud.ataei]

Summary

Under -O3 and -Ofast, the MASSV conversion prevents the sqrt call to be inlined.
Inline sqrt is faster than MASSV call on leppc.

[pjeeva01]

This comment was removed by pjeeva01.

[pjeeva01]

llvm/test/Transforms/LoopVectorize/PowerPC/massv-calls.ll

237

I think modifying this and the following tests to ensure following calls are not generated would be useful.

__sqrtd2_massv{{.*}}<2 x double>
__sqrtf4_massv{{.*}}<4 x float>

[masoud.ataei]

Checking sqrtd2_massv and sqrtf4_massv is not generated.

[masoud.ataei]

Addressed.

[pjeeva01]

LGTM

llvm/include/llvm/Analysis/VecFuncs.def

 
 // Floating-Point Arithmetic and Auxiliary Functions
 TLI_DEFINE_VECFUNC("cbrt", "__cbrtd2_massv", FIXED(2))
 TLI_DEFINE_VECFUNC("cbrtf", "__cbrtf4_massv", FIXED(4))
 TLI_DEFINE_VECFUNC("pow", "__powd2_massv", FIXED(2))
 TLI_DEFINE_VECFUNC("llvm.pow.f64", "__powd2_massv", FIXED(2))
 TLI_DEFINE_VECFUNC("powf", "__powf4_massv", FIXED(4))
 TLI_DEFINE_VECFUNC("llvm.pow.f32", "__powf4_massv", FIXED(4))
-TLI_DEFINE_VECFUNC("sqrt", "__sqrtd2_massv", FIXED(2))
-TLI_DEFINE_VECFUNC("llvm.sqrt.f64", "__sqrtd2_massv", FIXED(2))
-TLI_DEFINE_VECFUNC("sqrtf", "__sqrtf4_massv", FIXED(4))
-TLI_DEFINE_VECFUNC("llvm.sqrt.f32", "__sqrtf4_massv", FIXED(4))
 
 // Exponential and Logarithmic Functions
 TLI_DEFINE_VECFUNC("exp", "__expd2_massv", FIXED(2))
 TLI_DEFINE_VECFUNC("llvm.exp.f64", "__expd2_massv", FIXED(2))
 TLI_DEFINE_VECFUNC("expf", "__expf4_massv", FIXED(4))
 TLI_DEFINE_VECFUNC("llvm.exp.f32", "__expf4_massv", FIXED(4))
 TLI_DEFINE_VECFUNC("exp2", "__exp2d2_massv", FIXED(2))
 TLI_DEFINE_VECFUNC("llvm.exp2.f64", "__exp2d2_massv", FIXED(2))

llvm/test/CodeGen/PowerPC/lower-massv.ll

 ; RUN: llc -verify-machineinstrs -mcpu=pwr9  < %s -mtriple=powerpc64le-unknown-linux-gnu | FileCheck -check-prefixes=CHECK-PWR9,CHECK-ALL %s 
 ; RUN: llc -verify-machineinstrs -mcpu=pwr8  < %s -mtriple=powerpc64le-unknown-linux-gnu | FileCheck -check-prefixes=CHECK-PWR8,CHECK-ALL %s 
 ; RUN: llc -verify-machineinstrs -mcpu=pwr8  < %s -mtriple=powerpc64le-unknown-linux-gnu | FileCheck --check-prefix=CHECK-ALL %s 
 
 declare <2 x double> @__cbrtd2_massv(<2 x double>)
 declare <4 x float> @__cbrtf4_massv(<4 x float>)
 
 declare <2 x double> @__powd2_massv(<2 x double>, <2 x double>)
 declare <4 x float> @__powf4_massv(<4 x float>, <4 x float>)
 
-declare <2 x double> @__sqrtd2_massv(<2 x double>)
-declare <4 x float> @__sqrtf4_massv(<4 x float>)
-
 declare <2 x double> @__expd2_massv(<2 x double>)
 declare <4 x float> @__expf4_massv(<4 x float>)
 
 declare <2 x double> @__exp2d2_massv(<2 x double>)
 declare <4 x float> @__exp2f4_massv(<4 x float>)
 
 declare <2 x double> @__expm1d2_massv(<2 x double>)
 declare <4 x float> @__expm1f4_massv(<4 x float>)

 ; CHECK-PWR8: bl __powf4_P8
 ; CHECK-NOT: bl __powf4_massv
 ; CHECK-ALL: blr
 ;
  %1 = call <4 x float> @__powf4_massv(<4 x float> %opnd1, <4 x float> %opnd2)
   ret <4 x float> %1 
 }
 
-; sqrt
-define <2 x double>  @sqrt_f64_massv(<2 x double> %opnd) {
-; CHECK-ALL-LABEL: @sqrt_f64_massv
-; CHECK-PWR9: bl __sqrtd2_P9
-; CHECK-PWR8: bl __sqrtd2_P8
-; CHECK-NOT: bl __sqrtd2_massv
-; CHECK-ALL: blr
-;
-  %1 = call <2 x double> @__sqrtd2_massv(<2 x double> %opnd)
-  ret <2 x double> %1 
-}
-
-define <4 x float>  @sqrt_f32_massv(<4 x float> %opnd) {
-; CHECK-ALL-LABEL: @sqrt_f32_massv
-; CHECK-PWR9: bl __sqrtf4_P9
-; CHECK-PWR8: bl __sqrtf4_P8
-; CHECK-NOT: bl __sqrtf4_massv
-; CHECK-ALL: blr
-;
-  %1 = call <4 x float> @__sqrtf4_massv(<4 x float> %opnd)
-  ret <4 x float> %1 
-}
-
 ; exp
 define <2 x double>  @exp_f64_massv(<2 x double> %opnd) {
 ; CHECK-ALL-LABEL: @exp_f64_massv
 ; CHECK-PWR9: bl __expd2_P9
 ; CHECK-PWR8: bl __expd2_P8
 ; CHECK-NOT: bl __expd2_massv
 ; CHECK-ALL: blr
 ;

llvm/test/Transforms/LoopVectorize/PowerPC/massv-calls.ll

for.body:
   %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 @sqrt_f64(double* nocapture %varray) {
 ; CHECK-LABEL: @sqrt_f64(
-; CHECK: __sqrtd2_massv{{.*}}<2 x double>
+; CHECK-NOT: __sqrtd2_massv{{.*}}<2 x double>
 ; 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 @sqrt(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 @sqrt_f32(float* nocapture %varray) {
 ; CHECK-LABEL: @sqrt_f32(
-; CHECK: __sqrtf4_massv{{.*}}<4 x float>
+; CHECK-NOT: __sqrtf4_massv{{.*}}<4 x float>
 ; 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