a0086add2e
1. Better sorting of scalars to be gathered. Trying to insert constants/arguments/instructions-out-of-loop at first and only then the instructions which are inside the loop. It improves hoisting of invariant insertelements instructions. 2. Better detection of shuffle candidates in gathering function. 3. The cost of insertelement for constants is 0. Part of D57059. Differential Revision: https://reviews.llvm.org/D103458
94 lines
4.3 KiB
LLVM
94 lines
4.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -basic-aa -slp-vectorizer -dce -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7 | FileCheck %s
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-apple-macosx10.8.0"
|
|
|
|
%struct.GPar.0.16.26 = type { [0 x double], double }
|
|
|
|
@d = external global double, align 8
|
|
|
|
declare %struct.GPar.0.16.26* @Rf_gpptr(...)
|
|
|
|
define void @Rf_GReset() {
|
|
; CHECK-LABEL: @Rf_GReset(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[TMP0:%.*]] = load double, double* @d, align 8
|
|
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x double> poison, double [[TMP0]], i32 1
|
|
; CHECK-NEXT: [[TMP2:%.*]] = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, [[TMP1]]
|
|
; CHECK-NEXT: br i1 icmp eq (%struct.GPar.0.16.26* (...)* inttoptr (i64 115 to %struct.GPar.0.16.26* (...)*), %struct.GPar.0.16.26* (...)* @Rf_gpptr), label [[IF_THEN:%.*]], label [[IF_END7:%.*]]
|
|
; CHECK: if.then:
|
|
; CHECK-NEXT: [[TMP3:%.*]] = fsub <2 x double> [[TMP2]], poison
|
|
; CHECK-NEXT: [[TMP4:%.*]] = fdiv <2 x double> [[TMP3]], poison
|
|
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <2 x double> [[TMP4]], i32 0
|
|
; CHECK-NEXT: [[TMP6:%.*]] = extractelement <2 x double> [[TMP4]], i32 1
|
|
; CHECK-NEXT: [[CMP:%.*]] = fcmp ogt double [[TMP5]], [[TMP6]]
|
|
; CHECK-NEXT: br i1 [[CMP]], label [[IF_THEN6:%.*]], label [[IF_END7]]
|
|
; CHECK: if.then6:
|
|
; CHECK-NEXT: br label [[IF_END7]]
|
|
; CHECK: if.end7:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%sub = fsub double -0.000000e+00, undef
|
|
%0 = load double, double* @d, align 8
|
|
%sub1 = fsub double -0.000000e+00, %0
|
|
br i1 icmp eq (%struct.GPar.0.16.26* (...)* inttoptr (i64 115 to %struct.GPar.0.16.26* (...)*), %struct.GPar.0.16.26* (...)* @Rf_gpptr), label %if.then, label %if.end7
|
|
|
|
if.then: ; preds = %entry
|
|
%sub2 = fsub double %sub, undef
|
|
%div.i = fdiv double %sub2, undef
|
|
%sub4 = fsub double %sub1, undef
|
|
%div.i16 = fdiv double %sub4, undef
|
|
%cmp = fcmp ogt double %div.i, %div.i16
|
|
br i1 %cmp, label %if.then6, label %if.end7
|
|
|
|
if.then6: ; preds = %if.then
|
|
br label %if.end7
|
|
|
|
if.end7: ; preds = %if.then6, %if.then, %entry
|
|
%g.0 = phi double [ 0.000000e+00, %if.then6 ], [ %sub, %if.then ], [ %sub, %entry ]
|
|
ret void
|
|
}
|
|
|
|
define void @Rf_GReset_unary_fneg() {
|
|
; CHECK-LABEL: @Rf_GReset_unary_fneg(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[TMP0:%.*]] = load double, double* @d, align 8
|
|
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x double> poison, double [[TMP0]], i32 1
|
|
; CHECK-NEXT: [[TMP2:%.*]] = fneg <2 x double> [[TMP1]]
|
|
; CHECK-NEXT: br i1 icmp eq (%struct.GPar.0.16.26* (...)* inttoptr (i64 115 to %struct.GPar.0.16.26* (...)*), %struct.GPar.0.16.26* (...)* @Rf_gpptr), label [[IF_THEN:%.*]], label [[IF_END7:%.*]]
|
|
; CHECK: if.then:
|
|
; CHECK-NEXT: [[TMP3:%.*]] = fsub <2 x double> [[TMP2]], poison
|
|
; CHECK-NEXT: [[TMP4:%.*]] = fdiv <2 x double> [[TMP3]], poison
|
|
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <2 x double> [[TMP4]], i32 0
|
|
; CHECK-NEXT: [[TMP6:%.*]] = extractelement <2 x double> [[TMP4]], i32 1
|
|
; CHECK-NEXT: [[CMP:%.*]] = fcmp ogt double [[TMP5]], [[TMP6]]
|
|
; CHECK-NEXT: br i1 [[CMP]], label [[IF_THEN6:%.*]], label [[IF_END7]]
|
|
; CHECK: if.then6:
|
|
; CHECK-NEXT: br label [[IF_END7]]
|
|
; CHECK: if.end7:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%sub = fneg double undef
|
|
%0 = load double, double* @d, align 8
|
|
%sub1 = fneg double %0
|
|
br i1 icmp eq (%struct.GPar.0.16.26* (...)* inttoptr (i64 115 to %struct.GPar.0.16.26* (...)*), %struct.GPar.0.16.26* (...)* @Rf_gpptr), label %if.then, label %if.end7
|
|
|
|
if.then: ; preds = %entry
|
|
%sub2 = fsub double %sub, undef
|
|
%div.i = fdiv double %sub2, undef
|
|
%sub4 = fsub double %sub1, undef
|
|
%div.i16 = fdiv double %sub4, undef
|
|
%cmp = fcmp ogt double %div.i, %div.i16
|
|
br i1 %cmp, label %if.then6, label %if.end7
|
|
|
|
if.then6: ; preds = %if.then
|
|
br label %if.end7
|
|
|
|
if.end7: ; preds = %if.then6, %if.then, %entry
|
|
%g.0 = phi double [ 0.000000e+00, %if.then6 ], [ %sub, %if.then ], [ %sub, %entry ]
|
|
ret void
|
|
}
|