maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Expose the number of Newton-Raphson iterations applied to the hardware's reciprocal estimate as a parameter (x86). 

This is a follow-on to r221706 and r221731 and discussed in more detail in PR21385.

This patch also loosens the testcase checking for btver2. We know that the "1.0" will be loaded, but
we can't tell exactly when, so replace the CHECK-NEXT specifiers with plain CHECKs. The CHECK-NEXT
sequence relied on a quirk of post-RA-scheduling that may change independently of anything in these tests.

llvm-svn: 221819
This commit is contained in:
Sanjay Patel 2014-11-12 21:39:01 +00:00
parent 6d829bdbef
commit f6f7d5d1dd
2 changed files with 56 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -71,6 +71,12 @@ static cl::opt<bool> ExperimentalVectorShuffleLowering(
cl::desc("Enable an experimental vector shuffle lowering code path."),
cl::Hidden);
static cl::opt<int> ReciprocalEstimateRefinementSteps(
"x86-recip-refinement-steps", cl::init(1),
cl::desc("Specify the number of Newton-Raphson iterations applied to the "
"result of the hardware reciprocal estimate instruction."),
cl::NotHidden);
// Forward declarations.
static SDValue getMOVL(SelectionDAG &DAG, SDLoc dl, EVT VT, SDValue V1,
SDValue V2);
@ -14543,9 +14549,7 @@ SDValue X86TargetLowering::getRecipEstimate(SDValue Op,
// along with FMA, this could be a throughput win.
if ((Subtarget->hasSSE1() && (VT == MVT::f32 || VT == MVT::v4f32)) ||
(Subtarget->hasAVX() && VT == MVT::v8f32)) {
// TODO: Expose this as a user-configurable parameter to allow for
// speed vs. accuracy flexibility.
RefinementSteps = 1;
RefinementSteps = ReciprocalEstimateRefinementSteps;
return DCI.DAG.getNode(X86ISD::FRCP, SDLoc(Op), VT, Op);
}
return SDValue();

61
llvm/test/CodeGen/X86/recip-fastmath.ll
View File

@ -1,5 +1,6 @@
; 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
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+use-recip-est,+avx -x86-recip-refinement-steps=2 | FileCheck %s --check-prefix=REFINE
; If the target's divss/divps instructions are substantially
; slower than rcpss/rcpps with a Newton-Raphson refinement,
@ -21,11 +22,23 @@ define float @reciprocal_estimate(float %x) #0 {
; BTVER2-LABEL: reciprocal_estimate:
; BTVER2: vrcpss
; BTVER2-NEXT: vmulss
; BTVER2-NEXT: vsubss
; BTVER2-NEXT: vmulss
; BTVER2-NEXT: vaddss
; BTVER2: vmulss
; BTVER2: vsubss
; BTVER2: vmulss
; BTVER2: vaddss
; BTVER2-NEXT: retq
; REFINE-LABEL: reciprocal_estimate:
; REFINE: vrcpss
; REFINE: vmulss
; REFINE: vsubss
; REFINE: vmulss
; REFINE: vaddss
; REFINE: vmulss
; REFINE: vsubss
; REFINE: vmulss
; REFINE: vaddss
; REFINE-NEXT: retq
}
define <4 x float> @reciprocal_estimate_v4f32(<4 x float> %x) #0 {
@ -40,11 +53,23 @@ define <4 x float> @reciprocal_estimate_v4f32(<4 x float> %x) #0 {
; BTVER2-LABEL: reciprocal_estimate_v4f32:
; BTVER2: vrcpps
; BTVER2-NEXT: vmulps
; BTVER2-NEXT: vsubps
; BTVER2-NEXT: vmulps
; BTVER2-NEXT: vaddps
; BTVER2: vmulps
; BTVER2: vsubps
; BTVER2: vmulps
; BTVER2: vaddps
; BTVER2-NEXT: retq
; REFINE-LABEL: reciprocal_estimate_v4f32:
; REFINE: vrcpps
; REFINE: vmulps
; REFINE: vsubps
; REFINE: vmulps
; REFINE: vaddps
; REFINE: vmulps
; REFINE: vsubps
; REFINE: vmulps
; REFINE: vaddps
; REFINE-NEXT: retq
}
define <8 x float> @reciprocal_estimate_v8f32(<8 x float> %x) #0 {
@ -62,11 +87,23 @@ define <8 x float> @reciprocal_estimate_v8f32(<8 x float> %x) #0 {
; BTVER2-LABEL: reciprocal_estimate_v8f32:
; BTVER2: vrcpps
; BTVER2-NEXT: vmulps
; BTVER2-NEXT: vsubps
; BTVER2-NEXT: vmulps
; BTVER2-NEXT: vaddps
; BTVER2: vmulps
; BTVER2: vsubps
; BTVER2: vmulps
; BTVER2: vaddps
; BTVER2-NEXT: retq
; REFINE-LABEL: reciprocal_estimate_v8f32:
; REFINE: vrcpps
; REFINE: vmulps
; REFINE: vsubps
; REFINE: vmulps
; REFINE: vaddps
; REFINE: vmulps
; REFINE: vsubps
; REFINE: vmulps
; REFINE: vaddps
; REFINE-NEXT: retq
}
attributes #0 = { "unsafe-fp-math"="true" }