From e2e589288fcac4fe8b5262eecfc7e3a47d256022 Mon Sep 17 00:00:00 2001
From: Sanjay Patel <spatel@rotateright.com>
Date: Tue, 11 Nov 2014 20:51:00 +0000
Subject: Use rcpss/rcpps (X86) to speed up reciprocal calcs (PR21385).

This is a first step for generating SSE rcp instructions for reciprocal
calcs when fast-math allows it. This is very similar to the rsqrt optimization
enabled in D5658 ( http://reviews.llvm.org/rL220570 ).

For now, be conservative and only enable this for AMD btver2 where performance
improves significantly both in terms of latency and throughput.

We may never enable this codegen for Intel Core* chips because the divider circuits
are just too fast. On SandyBridge, divss can be as fast as 10 cycles versus the 21
cycle critical path for the rcp + mul + sub + mul + add estimate.

Follow-on patches may allow configuration of the number of Newton-Raphson refinement
steps, add AVX512 support, and enable the optimization for more chips.

More background here: http://llvm.org/bugs/show_bug.cgi?id=21385

Differential Revision: http://reviews.llvm.org/D6175

llvm-svn: 221706
---
 llvm/test/CodeGen/X86/recip-fastmath.ll | 72 +++++++++++++++++++++++++++++++++
 1 file changed, 72 insertions(+)
 create mode 100644 llvm/test/CodeGen/X86/recip-fastmath.ll

(limited to 'llvm/test/CodeGen/X86/recip-fastmath.ll')

diff --git a/llvm/test/CodeGen/X86/recip-fastmath.ll b/llvm/test/CodeGen/X86/recip-fastmath.ll
new file mode 100644
index 00000000000..dd5563c965f
--- /dev/null
+++ b/llvm/test/CodeGen/X86/recip-fastmath.ll
@@ -0,0 +1,72 @@
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=core2 | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=btver2 | FileCheck %s --check-prefix=BTVER2
+
+; 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
+
+; BTVER2-LABEL: reciprocal_estimate:
+; BTVER2: vrcpss
+; BTVER2-NEXT: vmulss
+; BTVER2-NEXT: vsubss
+; BTVER2-NEXT: vmulss
+; BTVER2-NEXT: vaddss
+; BTVER2-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
+
+; BTVER2-LABEL: reciprocal_estimate_v4f32:
+; BTVER2: vrcpps
+; BTVER2-NEXT: vmulps
+; BTVER2-NEXT: vsubps
+; BTVER2-NEXT: vmulps
+; BTVER2-NEXT: vaddps
+; BTVER2-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
+
+; BTVER2-LABEL: reciprocal_estimate_v8f32:
+; BTVER2: vrcpps
+; BTVER2-NEXT: vmulps
+; BTVER2-NEXT: vsubps
+; BTVER2-NEXT: vmulps
+; BTVER2-NEXT: vaddps
+; BTVER2-NEXT: retq
+}
+
+attributes #0 = { "unsafe-fp-math"="true" }
-- 
cgit v1.2.3