Revert of Split rsqrt into rsqrt{0,1,2}, with increasing cost and precision on ARM (patchset #2 id:20001 of https://codereview.chromium.org/1109913002/)

Reason for revert:
arm64 typos

Original issue's description:
> Split rsqrt into rsqrt{0,1,2}, with increasing cost and precision on ARM
>
> This is a logical no-op.  Everything was using the equivalent of rsqrt1() before, and is now after.
>
> BUG=skia:
>
> Committed: https://skia.googlesource.com/skia/+/9de16283fdc8cc0d31a84f503578d0ecea4e8297

TBR=reed@google.com,mtklein@chromium.org
NOPRESUBMIT=true
NOTREECHECKS=true
NOTRY=true
BUG=skia:

Review URL: https://codereview.chromium.org/1105233003

2 files changed, 23 insertions, 36 deletions

diff --git a/src/opts/SkNx_neon.h b/src/opts/SkNx_neon.h
index f27c2b3856..6b216827a8 100644
--- a/src/opts/SkNx_neon.h
+++ b/src/opts/SkNx_neon.h
@@ -81,21 +81,20 @@ public:
     static SkNf Min(const SkNf& l, const SkNf& r) { return vmin_f32(l.fVec, r.fVec); }
     static SkNf Max(const SkNf& l, const SkNf& r) { return vmax_f32(l.fVec, r.fVec); }
 
-    SkNf rsqrt0() const { return vrsqrte_f32(fVec); }
-    SkNf rsqrt1() const {
-        float32x2_t est0 = this->rsqrt0().fVec;
-        return vmul_f32(vrsqrts_f32(fVec, vmul_f32(est0, est0)), est0);
-    }
-    SkNf rsqrt2() const {
-        float32x2_t est1 = this->rsqrt1().fVec;
-        return vmul_f32(vrsqrts_f32(fVec, vmul_f32(est1, est1)), est1);
+    SkNf rsqrt() const {
+        float32x2_t est0 = vrsqrte_f32(fVec),
+                    est1 = vmul_f32(vrsqrts_f32(fVec, vmul_f32(est0, est0)), est0);
+        return est1;
     }
 
     SkNf sqrt() const {
     #if defined(SK_CPU_ARM64)
         return vsqrt_f32(fVec);
     #else
-        return *this * this->rsqrt2();
+        float32x2_t est1 = this->rsqrt().fVec,
+        // An extra step of Newton's method to refine the estimate of 1/sqrt(this).
+                    est2 = vmul_f32(vrsqrts_f32(fVec, vmul_f32(est1, est1)), est1);
+        return vmul_f32(fVec, est2);
     #endif
     }
 
@@ -152,15 +151,10 @@ public:
     static SkNf Max(const SkNf& l, const SkNf& r) { return vmaxq_f64(l.fVec, r.fVec); }
 
     SkNf  sqrt() const { return vsqrtq_f64(fVec);  }
-
-    SkNf rsqrt0() const { return vrsqrteq_f64(fVec); }
-    SkNf rsqrt1() const {
-        float32x4_t est0 = this->rsqrt0().fVec;
-        return vmulq_f64(vrsqrtsq_f64(fVec, vmulq_f64(est0, est0)), est0);
-    }
-    SkNf rsqrt2() const {
-        float32x4_t est1 = this->rsqrt1().fVec;
-        return vmulq_f64(vrsqrtsq_f64(fVec, vmulq_f64(est1, est1)), est1);
+    SkNf rsqrt() const {
+        float64x2_t est0 = vrsqrteq_f64(fVec),
+                    est1 = vmulq_f64(vrsqrtsq_f64(fVec, vmulq_f64(est0, est0)), est0);
+        return est1;
     }
 
     SkNf approxInvert() const {
@@ -275,21 +269,20 @@ public:
     static SkNf Min(const SkNf& l, const SkNf& r) { return vminq_f32(l.fVec, r.fVec); }
     static SkNf Max(const SkNf& l, const SkNf& r) { return vmaxq_f32(l.fVec, r.fVec); }
 
-    SkNf rsqrt0() const { return vrsqrteq_f32(fVec); }
-    SkNf rsqrt1() const {
-        float32x4_t est0 = this->rsqrt0().fVec;
-        return vmulq_f32(vrsqrtsq_f32(fVec, vmulq_f32(est0, est0)), est0);
-    }
-    SkNf rsqrt2() const {
-        float32x4_t est1 = this->rsqrt1().fVec;
-        return vmulq_f32(vrsqrtsq_f32(fVec, vmulq_f32(est1, est1)), est1);
+    SkNf rsqrt() const {
+        float32x4_t est0 = vrsqrteq_f32(fVec),
+                    est1 = vmulq_f32(vrsqrtsq_f32(fVec, vmulq_f32(est0, est0)), est0);
+        return est1;
     }
 
     SkNf sqrt() const {
     #if defined(SK_CPU_ARM64)
         return vsqrtq_f32(fVec);
     #else
-        return *this * this->rsqrt2();
+        float32x4_t est1 = this->rsqrt().fVec,
+        // An extra step of Newton's method to refine the estimate of 1/sqrt(this).
+                    est2 = vmulq_f32(vrsqrtsq_f32(fVec, vmulq_f32(est1, est1)), est1);
+        return vmulq_f32(fVec, est2);
     #endif
     }
 
diff --git a/src/opts/SkNx_sse.h b/src/opts/SkNx_sse.h
index cbe624ba2d..2608525bd0 100644
--- a/src/opts/SkNx_sse.h
+++ b/src/opts/SkNx_sse.h
@@ -82,9 +82,7 @@ public:
     static SkNf Max(const SkNf& l, const SkNf& r) { return _mm_max_ps(l.fVec, r.fVec); }
 
     SkNf  sqrt() const { return _mm_sqrt_ps (fVec);  }
-    SkNf rsqrt0() const { return _mm_rsqrt_ps(fVec); }
-    SkNf rsqrt1() const { return this->rsqrt0(); }
-    SkNf rsqrt2() const { return this->rsqrt1(); }
+    SkNf rsqrt() const { return _mm_rsqrt_ps(fVec); }
 
     SkNf       invert() const { return SkNf(1) / *this; }
     SkNf approxInvert() const { return _mm_rcp_ps(fVec); }
@@ -128,9 +126,7 @@ public:
     static SkNf Max(const SkNf& l, const SkNf& r) { return _mm_max_pd(l.fVec, r.fVec); }
 
     SkNf  sqrt() const { return _mm_sqrt_pd(fVec);  }
-    SkNf rsqrt0() const { return _mm_cvtps_pd(_mm_rsqrt_ps(_mm_cvtpd_ps(fVec))); }
-    SkNf rsqrt1() const { return this->rsqrt0(); }
-    SkNf rsqrt2() const { return this->rsqrt1(); }
+    SkNf rsqrt() const { return _mm_cvtps_pd(_mm_rsqrt_ps(_mm_cvtpd_ps(fVec))); }
 
     SkNf       invert() const { return SkNf(1) / *this; }
     SkNf approxInvert() const { return _mm_cvtps_pd(_mm_rcp_ps(_mm_cvtpd_ps(fVec))); }
@@ -214,9 +210,7 @@ public:
     static SkNf Max(const SkNf& l, const SkNf& r) { return _mm_max_ps(l.fVec, r.fVec); }
 
     SkNf  sqrt() const { return _mm_sqrt_ps (fVec);  }
-    SkNf rsqrt0() const { return _mm_rsqrt_ps(fVec); }
-    SkNf rsqrt1() const { return this->rsqrt0(); }
-    SkNf rsqrt2() const { return this->rsqrt1(); }
+    SkNf rsqrt() const { return _mm_rsqrt_ps(fVec); }
 
     SkNf       invert() const { return SkNf(1) / *this; }
     SkNf approxInvert() const { return _mm_rcp_ps(fVec); }