Previous to this patch we only materialized 0.0 and all other floating point values would be loaded from the TOC. This patch adds materialization for the floating point values that can be represented as integers in [-16.0, 15.0]. For example we will now materialize 3.0 and -5.0 but not 4.7. Reviewed By: nemanjai, lei, #powerpc Differential Revision: https://reviews.llvm.org/D138844
46 lines
1.4 KiB
LLVM
46 lines
1.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -verify-machineinstrs < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr7 -mattr=+vsx -disable-ppc-vsx-fma-mutation=false | FileCheck %s
|
|
|
|
declare double @llvm.sqrt.f64(double)
|
|
|
|
; Test several VSX FMA mutation opportunities.
|
|
|
|
; This is reasonable transformation since it eliminates extra register copy.
|
|
define double @foo3_fmf(double %a) nounwind {
|
|
; CHECK-LABEL: foo3_fmf:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: xstsqrtdp 0, 1
|
|
; CHECK-NEXT: bc 12, 2, .LBB0_2
|
|
; CHECK-NEXT: # %bb.1:
|
|
; CHECK-NEXT: vspltisw 2, -3
|
|
; CHECK-NEXT: xsrsqrtedp 0, 1
|
|
; CHECK-NEXT: addis 3, 2, .LCPI0_0@toc@ha
|
|
; CHECK-NEXT: lfs 4, .LCPI0_0@toc@l(3)
|
|
; CHECK-NEXT: xvcvsxwdp 2, 34
|
|
; CHECK-NEXT: xsmuldp 3, 1, 0
|
|
; CHECK-NEXT: fmr 5, 2
|
|
; CHECK-NEXT: xsmaddadp 5, 3, 0
|
|
; CHECK-NEXT: xsmuldp 0, 0, 4
|
|
; CHECK-NEXT: xsmuldp 0, 0, 5
|
|
; CHECK-NEXT: xsmuldp 1, 1, 0
|
|
; CHECK-NEXT: xsmaddadp 2, 1, 0
|
|
; CHECK-NEXT: xsmuldp 0, 1, 4
|
|
; CHECK-NEXT: xsmuldp 1, 0, 2
|
|
; CHECK-NEXT: blr
|
|
; CHECK-NEXT: .LBB0_2:
|
|
; CHECK-NEXT: xssqrtdp 1, 1
|
|
; CHECK-NEXT: blr
|
|
%r = call contract reassoc afn ninf double @llvm.sqrt.f64(double %a)
|
|
ret double %r
|
|
}
|
|
|
|
define double @foo3_safe(double %a) nounwind {
|
|
; CHECK-LABEL: foo3_safe:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: xssqrtdp 1, 1
|
|
; CHECK-NEXT: blr
|
|
%r = call double @llvm.sqrt.f64(double %a)
|
|
ret double %r
|
|
}
|
|
|