[x86] set default reciprocal (division and square root) codegen to match GCC

[spatel]

Summary

D8982 ( checked in at http://reviews.llvm.org/rL239001 ) added command-line options to specify reciprocal estimate codegen.

This patch changes the default settings for x86 targets to allow recip codegen (except for scalar division because that breaks too much code) when using -ffast-math or its equivalent. This will match GCC behavior for this kind of codegen.

[spatel]

Ping.

[ahatanak]

I just want to make sure I understand where this is headed. The recip flag and refinement step are eventually going to be added to the IR fast-math flags and propagated to the DAG nodes, is that correct?

[spatel]

In D10396#191356, @ahatanak wrote:

I just want to make sure I understand where this is headed. The recip flag and refinement step are eventually going to be added to the IR fast-math flags and propagated to the DAG nodes, is that correct?

That's correct, assuming there are no showstoppers for FMF in the DAG. The alternative would be to add a function attribute for this. Without one of those solutions, it's my understanding that we can't specify recip codegen when using LTO.

[ahatanak]

OK, thanks. This looks fine to me.

lib/Target/X86/X86TargetMachine.cpp

: LLVMTargetMachine(T, computeDataLayout(Triple(TT)), TT, CPU, FS, Options,
       Subtarget(Triple(TT), CPU, FS, *this, Options.StackAlignmentOverride) {
   // Windows stack unwinder gets confused when execution flow "falls through"
   // after a call to 'noreturn' function.
   // To prevent that, we emit a trap for 'unreachable' IR instructions.
   // (which on X86, happens to be the 'ud2' instruction)
   if (Subtarget.isTargetWin64())
     this->Options.TrapUnreachable = true;
 
-  // TODO: By default, all reciprocal estimate operations are off because
-  // that matches the behavior before TargetRecip was added (except for btver2
-  // which used subtarget features to enable this type of codegen).
-  // We should change this to match GCC behavior where everything but
-  // scalar division estimates are turned on by default with -ffast-math.
-  this->Options.Reciprocals.setDefaults("all", false, 1);
+  // By default (and when -ffast-math is on), enable estimate codegen for
+  // everything except scalar division. By default, use 1 refinement step for
+  // all operations. Defaults may be overridden by using command-line options.
+  // Scalar division estimates are disabled because they break too much
+  // real-world code. These defaults match GCC behavior.
+  this->Options.Reciprocals.setDefaults("sqrtf", true, 1);
+  this->Options.Reciprocals.setDefaults("divf", false, 1);
+  this->Options.Reciprocals.setDefaults("vec-sqrtf", true, 1);
+  this->Options.Reciprocals.setDefaults("vec-divf", true, 1);
 
   initAsmInfo();
 }
 
 X86TargetMachine::~X86TargetMachine() {}
 
 const X86Subtarget *
 X86TargetMachine::getSubtargetImpl(const Function &F) const {

test/CodeGen/X86/recip-fastmath.ll

-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=sse2 | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=sse2 -recip=!divf,!vec-divf | FileCheck %s --check-prefix=NORECIP
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx -recip=divf,vec-divf | FileCheck %s --check-prefix=RECIP
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx -recip=divf:2,vec-divf:2 | FileCheck %s --check-prefix=REFINE
 
 ; If the target's divss/divps instructions are substantially
 ; slower than rcpss/rcpps with a Newton-Raphson refinement,
 ; we should generate the estimate sequence.
 
 ; See PR21385 ( http://llvm.org/bugs/show_bug.cgi?id=21385 )
 ; for details about the accuracy, speed, and implementation
 ; differences of x86 reciprocal estimates.
 
 define float @reciprocal_estimate(float %x) #0 {
   %div = fdiv fast float 1.0, %x
   ret float %div
 
-; CHECK-LABEL: reciprocal_estimate:
-; CHECK: movss
-; CHECK-NEXT: divss
-; CHECK-NEXT: movaps
-; CHECK-NEXT: retq
+; NORECIP-LABEL: reciprocal_estimate:
+; NORECIP: movss
+; NORECIP-NEXT: divss
+; NORECIP-NEXT: movaps
+; NORECIP-NEXT: retq
 
 ; RECIP-LABEL: reciprocal_estimate:
 ; RECIP: vrcpss
 ; RECIP: vmulss
 ; RECIP: vsubss
 ; RECIP: vmulss
 ; RECIP: vaddss
 ; RECIP-NEXT: retq

 ; REFINE: vaddss
 ; REFINE-NEXT: retq
 }
 
 define <4 x float> @reciprocal_estimate_v4f32(<4 x float> %x) #0 {
   %div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %x
   ret <4 x float> %div
 
-; CHECK-LABEL: reciprocal_estimate_v4f32:
-; CHECK: movaps
-; CHECK-NEXT: divps
-; CHECK-NEXT: movaps
-; CHECK-NEXT: retq
+; NORECIP-LABEL: reciprocal_estimate_v4f32:
+; NORECIP: movaps
+; NORECIP-NEXT: divps
+; NORECIP-NEXT: movaps
+; NORECIP-NEXT: retq
 
 ; RECIP-LABEL: reciprocal_estimate_v4f32:
 ; RECIP: vrcpps
 ; RECIP: vmulps
 ; RECIP: vsubps
 ; RECIP: vmulps
 ; RECIP: vaddps
 ; RECIP-NEXT: retq

 ; REFINE: vaddps
 ; REFINE-NEXT: retq
 }
 
 define <8 x float> @reciprocal_estimate_v8f32(<8 x float> %x) #0 {
   %div = fdiv fast <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %x
   ret <8 x float> %div
 
-; CHECK-LABEL: reciprocal_estimate_v8f32:
-; CHECK: movaps
-; CHECK: movaps
-; CHECK-NEXT: divps
-; CHECK-NEXT: divps
-; CHECK-NEXT: movaps
-; CHECK-NEXT: movaps
-; CHECK-NEXT: retq
+; NORECIP-LABEL: reciprocal_estimate_v8f32:
+; NORECIP: movaps
+; NORECIP: movaps
+; NORECIP-NEXT: divps
+; NORECIP-NEXT: divps
+; NORECIP-NEXT: movaps
+; NORECIP-NEXT: movaps
+; NORECIP-NEXT: retq
 
 ; RECIP-LABEL: reciprocal_estimate_v8f32:
 ; RECIP: vrcpps
 ; RECIP: vmulps
 ; RECIP: vsubps
 ; RECIP: vmulps
 ; RECIP: vaddps
 ; RECIP-NEXT: retq

test/CodeGen/X86/sqrt-fastmath.ll

-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=sse2 | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=sse2 -recip=!sqrtf,!vec-sqrtf,!divf,!vec-divf | FileCheck %s --check-prefix=NORECIP
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx -recip=sqrtf,vec-sqrtf | FileCheck %s --check-prefix=ESTIMATE
 
 declare double @__sqrt_finite(double) #0
 declare float @__sqrtf_finite(float) #0
 declare x86_fp80 @__sqrtl_finite(x86_fp80) #0
 declare float @llvm.sqrt.f32(float) #0
 declare <4 x float> @llvm.sqrt.v4f32(<4 x float>) #0
 declare <8 x float> @llvm.sqrt.v8f32(<8 x float>) #0
 
 
 define double @fd(double %d) #0 {
-; CHECK-LABEL: fd:
-; CHECK:       # BB#0:
-; CHECK-NEXT:    sqrtsd %xmm0, %xmm0
-; CHECK-NEXT:    retq
+; NORECIP-LABEL: fd:
+; NORECIP:       # BB#0:
+; NORECIP-NEXT:    sqrtsd %xmm0, %xmm0
+; NORECIP-NEXT:    retq
 ;
 ; ESTIMATE-LABEL: fd:
 ; ESTIMATE:       # BB#0:
 ; ESTIMATE-NEXT:    vsqrtsd %xmm0, %xmm0, %xmm0
 ; ESTIMATE-NEXT:    retq
   %call = tail call double @__sqrt_finite(double %d) #1
   ret double %call
 }
 
 
 define float @ff(float %f) #0 {
-; CHECK-LABEL: ff:
-; CHECK:       # BB#0:
-; CHECK-NEXT:    sqrtss %xmm0, %xmm0
-; CHECK-NEXT:    retq
+; NORECIP-LABEL: ff:
+; NORECIP:       # BB#0:
+; NORECIP-NEXT:    sqrtss %xmm0, %xmm0
+; NORECIP-NEXT:    retq
 ;
 ; ESTIMATE-LABEL: ff:
 ; ESTIMATE:       # BB#0:
 ; ESTIMATE-NEXT:    vrsqrtss %xmm0, %xmm0, %xmm1
 ; ESTIMATE-NEXT:    vmulss {{.*}}(%rip), %xmm1, %xmm2
 ; ESTIMATE-NEXT:    vmulss %xmm1, %xmm1, %xmm1
 ; ESTIMATE-NEXT:    vmulss %xmm0, %xmm1, %xmm1
 ; ESTIMATE-NEXT:    vaddss {{.*}}(%rip), %xmm1, %xmm1
 ; ESTIMATE-NEXT:    vmulss %xmm2, %xmm1, %xmm1
 ; ESTIMATE-NEXT:    vmulss %xmm1, %xmm0, %xmm1
 ; ESTIMATE-NEXT:    vxorps %xmm2, %xmm2, %xmm2
 ; ESTIMATE-NEXT:    vcmpeqss %xmm2, %xmm0, %xmm0
 ; ESTIMATE-NEXT:    vandnps %xmm1, %xmm0, %xmm0
 ; ESTIMATE-NEXT:    retq
   %call = tail call float @__sqrtf_finite(float %f) #1
   ret float %call
 }
 
 
 define x86_fp80 @fld(x86_fp80 %ld) #0 {
-; CHECK-LABEL: fld:
-; CHECK:       # BB#0:
-; CHECK-NEXT:    fldt {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    fsqrt
-; CHECK-NEXT:    retq
+; NORECIP-LABEL: fld:
+; NORECIP:       # BB#0:
+; NORECIP-NEXT:    fldt {{[0-9]+}}(%rsp)
+; NORECIP-NEXT:    fsqrt
+; NORECIP-NEXT:    retq
 ;
 ; ESTIMATE-LABEL: fld:
 ; ESTIMATE:       # BB#0:
 ; ESTIMATE-NEXT:    fldt {{[0-9]+}}(%rsp)
 ; ESTIMATE-NEXT:    fsqrt
 ; ESTIMATE-NEXT:    retq
   %call = tail call x86_fp80 @__sqrtl_finite(x86_fp80 %ld) #1
   ret x86_fp80 %call
 }
 
 
 
 define float @reciprocal_square_root(float %x) #0 {
-; CHECK-LABEL: reciprocal_square_root:
-; CHECK:       # BB#0:
-; CHECK-NEXT:    sqrtss %xmm0, %xmm1
-; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
-; CHECK-NEXT:    divss %xmm1, %xmm0
-; CHECK-NEXT:    retq
+; NORECIP-LABEL: reciprocal_square_root:
+; NORECIP:       # BB#0:
+; NORECIP-NEXT:    sqrtss %xmm0, %xmm1
+; NORECIP-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
+; NORECIP-NEXT:    divss %xmm1, %xmm0
+; NORECIP-NEXT:    retq
 ;
 ; ESTIMATE-LABEL: reciprocal_square_root:
 ; ESTIMATE:       # BB#0:
 ; ESTIMATE-NEXT:    vrsqrtss %xmm0, %xmm0, %xmm1
 ; ESTIMATE-NEXT:    vmulss {{.*}}(%rip), %xmm1, %xmm2
 ; ESTIMATE-NEXT:    vmulss %xmm1, %xmm1, %xmm1
 ; ESTIMATE-NEXT:    vmulss %xmm0, %xmm1, %xmm0
 ; ESTIMATE-NEXT:    vaddss {{.*}}(%rip), %xmm0, %xmm0
 ; ESTIMATE-NEXT:    vmulss %xmm2, %xmm0, %xmm0
 ; ESTIMATE-NEXT:    retq
   %sqrt = tail call float @llvm.sqrt.f32(float %x)
   %div = fdiv fast float 1.0, %sqrt
   ret float %div
 }
 
 define <4 x float> @reciprocal_square_root_v4f32(<4 x float> %x) #0 {
-; CHECK-LABEL: reciprocal_square_root_v4f32:
-; CHECK:       # BB#0:
-; CHECK-NEXT:    sqrtps %xmm0, %xmm1
-; CHECK-NEXT:    movaps {{.*#+}} xmm0 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
-; CHECK-NEXT:    divps %xmm1, %xmm0
-; CHECK-NEXT:    retq
+; NORECIP-LABEL: reciprocal_square_root_v4f32:
+; NORECIP:       # BB#0:
+; NORECIP-NEXT:    sqrtps %xmm0, %xmm1
+; NORECIP-NEXT:    movaps {{.*#+}} xmm0 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; NORECIP-NEXT:    divps %xmm1, %xmm0
+; NORECIP-NEXT:    retq
 ;
 ; ESTIMATE-LABEL: reciprocal_square_root_v4f32:
 ; ESTIMATE:       # BB#0:
 ; ESTIMATE-NEXT:    vrsqrtps %xmm0, %xmm1
 ; ESTIMATE-NEXT:    vmulps %xmm1, %xmm1, %xmm2
 ; ESTIMATE-NEXT:    vmulps %xmm0, %xmm2, %xmm0
 ; ESTIMATE-NEXT:    vaddps {{.*}}(%rip), %xmm0, %xmm0
 ; ESTIMATE-NEXT:    vmulps {{.*}}(%rip), %xmm1, %xmm1
 ; ESTIMATE-NEXT:    vmulps %xmm1, %xmm0, %xmm0
 ; ESTIMATE-NEXT:    retq
   %sqrt = tail call <4 x float> @llvm.sqrt.v4f32(<4 x float> %x)
   %div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %sqrt
   ret <4 x float> %div
 }
 
 define <8 x float> @reciprocal_square_root_v8f32(<8 x float> %x) #0 {
-; CHECK-LABEL: reciprocal_square_root_v8f32:
-; CHECK:       # BB#0:
-; CHECK-NEXT:    sqrtps %xmm1, %xmm2
-; CHECK-NEXT:    sqrtps %xmm0, %xmm3
-; CHECK-NEXT:    movaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
-; CHECK-NEXT:    movaps %xmm1, %xmm0
-; CHECK-NEXT:    divps %xmm3, %xmm0
-; CHECK-NEXT:    divps %xmm2, %xmm1
-; CHECK-NEXT:    retq
+; NORECIP-LABEL: reciprocal_square_root_v8f32:
+; NORECIP:       # BB#0:
+; NORECIP-NEXT:    sqrtps %xmm1, %xmm2
+; NORECIP-NEXT:    sqrtps %xmm0, %xmm3
+; NORECIP-NEXT:    movaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; NORECIP-NEXT:    movaps %xmm1, %xmm0
+; NORECIP-NEXT:    divps %xmm3, %xmm0
+; NORECIP-NEXT:    divps %xmm2, %xmm1
+; NORECIP-NEXT:    retq
 ;
 ; ESTIMATE-LABEL: reciprocal_square_root_v8f32:
 ; ESTIMATE:       # BB#0:
 ; ESTIMATE-NEXT:    vrsqrtps %ymm0, %ymm1
 ; ESTIMATE-NEXT:    vmulps %ymm1, %ymm1, %ymm2
 ; ESTIMATE-NEXT:    vmulps %ymm0, %ymm2, %ymm0
 ; ESTIMATE-NEXT:    vaddps {{.*}}(%rip), %ymm0, %ymm0
 ; ESTIMATE-NEXT:    vmulps {{.*}}(%rip), %ymm1, %ymm1