caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
ef2cdfe393d01cd4935c806387ac912b5a2c8ced
clang-p2996/llvm/test/CodeGen/PowerPC/f128-conv.ll
Amy Kwan ba627a32e1 [PowerPC] Update Refactored Load/Store Implementation, XForm VSX Patterns, and Tests 
This patch includes the following updates to the load/store refactoring effort introduced in D93370:
 - Update various VSX patterns that use to "force" an XForm, to instead just XForm.
   This allows the ability for the patterns to compute the most optimal addressing
   mode (and to produce a DForm instruction when possible)
- Update pattern and test case for the LXVD2X/STXVD2X intrinsics
- Update LIT test cases that use to use the XForm instruction to use the DForm instruction

Differential Revision: https://reviews.llvm.org/D95115
2021-07-16 09:28:48 -05:00

2210 lines
69 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -relocation-model=pic -mcpu=pwr9 -mtriple=powerpc64le-unknown-unknown \
; RUN: -ppc-vsr-nums-as-vr -verify-machineinstrs -ppc-asm-full-reg-names < %s \
; RUN: | FileCheck %s
; RUN: llc -relocation-model=pic -mcpu=pwr8 -mtriple=powerpc64le-unknown-unknown \
; RUN: -ppc-vsr-nums-as-vr -verify-machineinstrs -ppc-asm-full-reg-names < %s \
; RUN: | FileCheck %s -check-prefix=CHECK-P8
@mem = global [5 x i64] [i64 56, i64 63, i64 3, i64 5, i64 6], align 8
@umem = global [5 x i64] [i64 560, i64 100, i64 34, i64 2, i64 5], align 8
@swMem = global [5 x i32] [i32 5, i32 2, i32 3, i32 4, i32 0], align 4
@uwMem = global [5 x i32] [i32 5, i32 2, i32 3, i32 4, i32 0], align 4
@uhwMem = local_unnamed_addr global [5 x i16] [i16 5, i16 2, i16 3, i16 4, i16 0], align 2
@ubMem = local_unnamed_addr global [5 x i8] c"\05\02\03\04\00", align 1
; Function Attrs: norecurse nounwind
define void @sdwConv2qp(fp128* nocapture %a, i64 %b) {
; CHECK-LABEL: sdwConv2qp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: mtvsrd v2, r4
; CHECK-NEXT: xscvsdqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: sdwConv2qp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatdikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = sitofp i64 %b to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @sdwConv2qp_01(fp128* nocapture %a, i128 %b) {
; CHECK-LABEL: sdwConv2qp_01:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: mflr r0
; CHECK-NEXT: .cfi_def_cfa_offset 48
; CHECK-NEXT: .cfi_offset lr, 16
; CHECK-NEXT: .cfi_offset r30, -16
; CHECK-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r0, 16(r1)
; CHECK-NEXT: stdu r1, -48(r1)
; CHECK-NEXT: mr r30, r3
; CHECK-NEXT: mr r3, r4
; CHECK-NEXT: mr r4, r5
; CHECK-NEXT: bl __floattikf
; CHECK-NEXT: nop
; CHECK-NEXT: stxv v2, 0(r30)
; CHECK-NEXT: addi r1, r1, 48
; CHECK-NEXT: ld r0, 16(r1)
; CHECK-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-NEXT: mtlr r0
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: sdwConv2qp_01:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: mr r4, r5
; CHECK-P8-NEXT: bl __floattikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = sitofp i128 %b to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @sdwConv2qp_02(fp128* nocapture %a) {
; CHECK-LABEL: sdwConv2qp_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC0@toc@ha
; CHECK-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-NEXT: lxsd v2, 16(r4)
; CHECK-NEXT: xscvsdqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: sdwConv2qp_02:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: addis r4, r2, .LC0@toc@ha
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-P8-NEXT: ld r4, 16(r4)
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatdikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load i64, i64* getelementptr inbounds
([5 x i64], [5 x i64]* @mem, i64 0, i64 2), align 8
%conv = sitofp i64 %0 to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @sdwConv2qp_03(fp128* nocapture %a, i64* nocapture readonly %b) {
; CHECK-LABEL: sdwConv2qp_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxsd v2, 0(r4)
; CHECK-NEXT: xscvsdqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: sdwConv2qp_03:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: ld r4, 0(r4)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatdikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load i64, i64* %b, align 8
%conv = sitofp i64 %0 to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @sdwConv2qp_04(fp128* nocapture %a, i1 %b) {
; CHECK-LABEL: sdwConv2qp_04:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: andi. r4, r4, 1
; CHECK-NEXT: li r4, 0
; CHECK-NEXT: li r5, -1
; CHECK-NEXT: iselgt r4, r5, r4
; CHECK-NEXT: mtvsrwa v2, r4
; CHECK-NEXT: xscvsdqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: sdwConv2qp_04:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: andi. r3, r4, 1
; CHECK-P8-NEXT: li r4, -1
; CHECK-P8-NEXT: li r3, 0
; CHECK-P8-NEXT: iselgt r3, r4, r3
; CHECK-P8-NEXT: bl __floatsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = sitofp i1 %b to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @udwConv2qp(fp128* nocapture %a, i64 %b) {
; CHECK-LABEL: udwConv2qp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: mtvsrd v2, r4
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: udwConv2qp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatundikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = uitofp i64 %b to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @udwConv2qp_01(fp128* nocapture %a, i128 %b) {
; CHECK-LABEL: udwConv2qp_01:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: mflr r0
; CHECK-NEXT: .cfi_def_cfa_offset 48
; CHECK-NEXT: .cfi_offset lr, 16
; CHECK-NEXT: .cfi_offset r30, -16
; CHECK-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r0, 16(r1)
; CHECK-NEXT: stdu r1, -48(r1)
; CHECK-NEXT: mr r30, r3
; CHECK-NEXT: mr r3, r4
; CHECK-NEXT: mr r4, r5
; CHECK-NEXT: bl __floatuntikf
; CHECK-NEXT: nop
; CHECK-NEXT: stxv v2, 0(r30)
; CHECK-NEXT: addi r1, r1, 48
; CHECK-NEXT: ld r0, 16(r1)
; CHECK-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-NEXT: mtlr r0
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: udwConv2qp_01:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: mr r4, r5
; CHECK-P8-NEXT: bl __floatuntikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = uitofp i128 %b to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @udwConv2qp_02(fp128* nocapture %a) {
; CHECK-LABEL: udwConv2qp_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC1@toc@ha
; CHECK-NEXT: ld r4, .LC1@toc@l(r4)
; CHECK-NEXT: lxsd v2, 32(r4)
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: udwConv2qp_02:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: addis r4, r2, .LC1@toc@ha
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: ld r4, .LC1@toc@l(r4)
; CHECK-P8-NEXT: ld r4, 32(r4)
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatundikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load i64, i64* getelementptr inbounds
([5 x i64], [5 x i64]* @umem, i64 0, i64 4), align 8
%conv = uitofp i64 %0 to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @udwConv2qp_03(fp128* nocapture %a, i64* nocapture readonly %b) {
; CHECK-LABEL: udwConv2qp_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxsd v2, 0(r4)
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: udwConv2qp_03:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: ld r4, 0(r4)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatundikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load i64, i64* %b, align 8
%conv = uitofp i64 %0 to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @udwConv2qp_04(fp128* nocapture %a, i1 %b) {
; CHECK-LABEL: udwConv2qp_04:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: clrlwi r4, r4, 31
; CHECK-NEXT: mtvsrwa v2, r4
; CHECK-NEXT: xscvsdqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: udwConv2qp_04:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: clrldi r3, r4, 63
; CHECK-P8-NEXT: bl __floatsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = uitofp i1 %b to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define fp128* @sdwConv2qp_testXForm(fp128* returned %sink,
; CHECK-LABEL: sdwConv2qp_testXForm:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lis r5, 1
; CHECK-NEXT: ori r5, r5, 7797
; CHECK-NEXT: lxsdx v2, r4, r5
; CHECK-NEXT: xscvsdqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: sdwConv2qp_testXForm:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: lis r5, 1
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: ori r5, r5, 7797
; CHECK-P8-NEXT: ldx r4, r4, r5
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatdikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: mr r3, r30
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
i8* nocapture readonly %a) {
entry:
%add.ptr = getelementptr inbounds i8, i8* %a, i64 73333
%0 = bitcast i8* %add.ptr to i64*
%1 = load i64, i64* %0, align 8
%conv = sitofp i64 %1 to fp128
store fp128 %conv, fp128* %sink, align 16
ret fp128* %sink
}
; Function Attrs: norecurse nounwind
define fp128* @udwConv2qp_testXForm(fp128* returned %sink,
; CHECK-LABEL: udwConv2qp_testXForm:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lis r5, 1
; CHECK-NEXT: ori r5, r5, 7797
; CHECK-NEXT: lxsdx v2, r4, r5
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: udwConv2qp_testXForm:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: lis r5, 1
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: ori r5, r5, 7797
; CHECK-P8-NEXT: ldx r4, r4, r5
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatundikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: mr r3, r30
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
i8* nocapture readonly %a) {
entry:
%add.ptr = getelementptr inbounds i8, i8* %a, i64 73333
%0 = bitcast i8* %add.ptr to i64*
%1 = load i64, i64* %0, align 8
%conv = uitofp i64 %1 to fp128
store fp128 %conv, fp128* %sink, align 16
ret fp128* %sink
}
; Function Attrs: norecurse nounwind
define void @swConv2qp(fp128* nocapture %a, i32 signext %b) {
; CHECK-LABEL: swConv2qp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: mtvsrwa v2, r4
; CHECK-NEXT: xscvsdqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: swConv2qp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = sitofp i32 %b to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @swConv2qp_02(fp128* nocapture %a, i32* nocapture readonly %b) {
; CHECK-LABEL: swConv2qp_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxsiwax v2, 0, r4
; CHECK-NEXT: xscvsdqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: swConv2qp_02:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: lwa r4, 0(r4)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load i32, i32* %b, align 4
%conv = sitofp i32 %0 to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @swConv2qp_03(fp128* nocapture %a) {
; CHECK-LABEL: swConv2qp_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC2@toc@ha
; CHECK-NEXT: ld r4, .LC2@toc@l(r4)
; CHECK-NEXT: addi r4, r4, 12
; CHECK-NEXT: lxsiwax v2, 0, r4
; CHECK-NEXT: xscvsdqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: swConv2qp_03:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: addis r4, r2, .LC2@toc@ha
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: ld r4, .LC2@toc@l(r4)
; CHECK-P8-NEXT: lwa r4, 12(r4)
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load i32, i32* getelementptr inbounds
([5 x i32], [5 x i32]* @swMem, i64 0, i64 3), align 4
%conv = sitofp i32 %0 to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @uwConv2qp(fp128* nocapture %a, i32 zeroext %b) {
; CHECK-LABEL: uwConv2qp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: mtvsrwz v2, r4
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: uwConv2qp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatunsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = uitofp i32 %b to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @uwConv2qp_02(fp128* nocapture %a, i32* nocapture readonly %b) {
; CHECK-LABEL: uwConv2qp_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxsiwzx v2, 0, r4
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: uwConv2qp_02:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: lwz r4, 0(r4)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatunsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load i32, i32* %b, align 4
%conv = uitofp i32 %0 to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @uwConv2qp_03(fp128* nocapture %a) {
; CHECK-LABEL: uwConv2qp_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC3@toc@ha
; CHECK-NEXT: ld r4, .LC3@toc@l(r4)
; CHECK-NEXT: addi r4, r4, 12
; CHECK-NEXT: lxsiwzx v2, 0, r4
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: uwConv2qp_03:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: addis r4, r2, .LC3@toc@ha
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: ld r4, .LC3@toc@l(r4)
; CHECK-P8-NEXT: lwz r4, 12(r4)
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatunsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load i32, i32* getelementptr inbounds
([5 x i32], [5 x i32]* @uwMem, i64 0, i64 3), align 4
%conv = uitofp i32 %0 to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @uwConv2qp_04(fp128* nocapture %a,
; CHECK-LABEL: uwConv2qp_04:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lwz r5, 0(r5)
; CHECK-NEXT: add r4, r5, r4
; CHECK-NEXT: mtvsrwz v2, r4
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: uwConv2qp_04:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: lwz r3, 0(r5)
; CHECK-P8-NEXT: add r3, r3, r4
; CHECK-P8-NEXT: clrldi r3, r3, 32
; CHECK-P8-NEXT: bl __floatunsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
i32 zeroext %b, i32* nocapture readonly %c) {
entry:
%0 = load i32, i32* %c, align 4
%add = add i32 %0, %b
%conv = uitofp i32 %add to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @uhwConv2qp(fp128* nocapture %a, i16 zeroext %b) {
; CHECK-LABEL: uhwConv2qp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: mtvsrwz v2, r4
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: uhwConv2qp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatunsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = uitofp i16 %b to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @uhwConv2qp_02(fp128* nocapture %a, i16* nocapture readonly %b) {
; CHECK-LABEL: uhwConv2qp_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxsihzx v2, 0, r4
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: uhwConv2qp_02:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: lhz r4, 0(r4)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatunsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load i16, i16* %b, align 2
%conv = uitofp i16 %0 to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @uhwConv2qp_03(fp128* nocapture %a) {
; CHECK-LABEL: uhwConv2qp_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC4@toc@ha
; CHECK-NEXT: ld r4, .LC4@toc@l(r4)
; CHECK-NEXT: addi r4, r4, 6
; CHECK-NEXT: lxsihzx v2, 0, r4
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: uhwConv2qp_03:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: addis r4, r2, .LC4@toc@ha
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: ld r4, .LC4@toc@l(r4)
; CHECK-P8-NEXT: lhz r4, 6(r4)
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatunsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load i16, i16* getelementptr inbounds
([5 x i16], [5 x i16]* @uhwMem, i64 0, i64 3), align 2
%conv = uitofp i16 %0 to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @uhwConv2qp_04(fp128* nocapture %a, i16 zeroext %b,
; CHECK-LABEL: uhwConv2qp_04:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lhz r5, 0(r5)
; CHECK-NEXT: add r4, r5, r4
; CHECK-NEXT: mtvsrwa v2, r4
; CHECK-NEXT: xscvsdqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: uhwConv2qp_04:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: lhz r3, 0(r5)
; CHECK-P8-NEXT: add r3, r3, r4
; CHECK-P8-NEXT: clrldi r3, r3, 32
; CHECK-P8-NEXT: bl __floatsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
i16* nocapture readonly %c) {
entry:
%conv = zext i16 %b to i32
%0 = load i16, i16* %c, align 2
%conv1 = zext i16 %0 to i32
%add = add nuw nsw i32 %conv1, %conv
%conv2 = sitofp i32 %add to fp128
store fp128 %conv2, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @ubConv2qp(fp128* nocapture %a, i8 zeroext %b) {
; CHECK-LABEL: ubConv2qp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: mtvsrwz v2, r4
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: ubConv2qp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatunsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = uitofp i8 %b to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @ubConv2qp_02(fp128* nocapture %a, i8* nocapture readonly %b) {
; CHECK-LABEL: ubConv2qp_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxsibzx v2, 0, r4
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: ubConv2qp_02:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: lbz r4, 0(r4)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatunsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load i8, i8* %b, align 1
%conv = uitofp i8 %0 to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @ubConv2qp_03(fp128* nocapture %a) {
; CHECK-LABEL: ubConv2qp_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC5@toc@ha
; CHECK-NEXT: ld r4, .LC5@toc@l(r4)
; CHECK-NEXT: addi r4, r4, 2
; CHECK-NEXT: lxsibzx v2, 0, r4
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: ubConv2qp_03:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: addis r4, r2, .LC5@toc@ha
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: ld r4, .LC5@toc@l(r4)
; CHECK-P8-NEXT: lbz r4, 2(r4)
; CHECK-P8-NEXT: mr r3, r4
; CHECK-P8-NEXT: bl __floatunsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load i8, i8* getelementptr inbounds
([5 x i8], [5 x i8]* @ubMem, i64 0, i64 2), align 1
%conv = uitofp i8 %0 to fp128
store fp128 %conv, fp128* %a, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @ubConv2qp_04(fp128* nocapture %a, i8 zeroext %b,
; CHECK-LABEL: ubConv2qp_04:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lbz r5, 0(r5)
; CHECK-NEXT: add r4, r5, r4
; CHECK-NEXT: mtvsrwa v2, r4
; CHECK-NEXT: xscvsdqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: ubConv2qp_04:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: lbz r3, 0(r5)
; CHECK-P8-NEXT: add r3, r3, r4
; CHECK-P8-NEXT: clrldi r3, r3, 32
; CHECK-P8-NEXT: bl __floatsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
i8* nocapture readonly %c) {
entry:
%conv = zext i8 %b to i32
%0 = load i8, i8* %c, align 1
%conv1 = zext i8 %0 to i32
%add = add nuw nsw i32 %conv1, %conv
%conv2 = sitofp i32 %add to fp128
store fp128 %conv2, fp128* %a, align 16
ret void
}
; Convert QP to DP
@f128Array = global [4 x fp128]
[fp128 0xL00000000000000004004C00000000000,
fp128 0xLF000000000000000400808AB851EB851,
fp128 0xL5000000000000000400E0C26324C8366,
fp128 0xL8000000000000000400A24E2E147AE14], align 16
@f128global = global fp128 0xL300000000000000040089CA8F5C28F5C, align 16
; Function Attrs: norecurse nounwind readonly
define double @qpConv2dp(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2dp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: xscvqpdp v2, v2
; CHECK-NEXT: xscpsgndp f1, v2, v2
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2dp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: lvx v2, 0, r3
; CHECK-P8-NEXT: bl __trunckfdf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load fp128, fp128* %a, align 16
%conv = fptrunc fp128 %0 to double
ret double %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2dp_02(double* nocapture %res) {
; CHECK-LABEL: qpConv2dp_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC6@toc@ha
; CHECK-NEXT: ld r4, .LC6@toc@l(r4)
; CHECK-NEXT: lxv v2, 0(r4)
; CHECK-NEXT: xscvqpdp v2, v2
; CHECK-NEXT: stxsd v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2dp_02:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: addis r4, r2, .LC6@toc@ha
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: ld r4, .LC6@toc@l(r4)
; CHECK-P8-NEXT: lvx v2, 0, r4
; CHECK-P8-NEXT: bl __trunckfdf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stfd f1, 0(r30)
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load fp128, fp128* @f128global, align 16
%conv = fptrunc fp128 %0 to double
store double %conv, double* %res, align 8
ret void
}
; Function Attrs: norecurse nounwind
define void @qpConv2dp_03(double* nocapture %res, i32 signext %idx) {
; CHECK-LABEL: qpConv2dp_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r5, r2, .LC7@toc@ha
; CHECK-NEXT: sldi r4, r4, 3
; CHECK-NEXT: ld r5, .LC7@toc@l(r5)
; CHECK-NEXT: lxv v2, 0(r5)
; CHECK-NEXT: xscvqpdp v2, v2
; CHECK-NEXT: stxsdx v2, r3, r4
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2dp_03:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 64
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r29, -24
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r29, -24(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -64(r1)
; CHECK-P8-NEXT: mr r30, r4
; CHECK-P8-NEXT: addis r4, r2, .LC7@toc@ha
; CHECK-P8-NEXT: mr r29, r3
; CHECK-P8-NEXT: ld r4, .LC7@toc@l(r4)
; CHECK-P8-NEXT: lvx v2, 0, r4
; CHECK-P8-NEXT: bl __trunckfdf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: sldi r3, r30, 3
; CHECK-P8-NEXT: stfdx f1, r29, r3
; CHECK-P8-NEXT: addi r1, r1, 64
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: ld r29, -24(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load fp128, fp128* getelementptr inbounds ([4 x fp128], [4 x fp128]* @f128Array, i64 0, i64 0), align 16
%conv = fptrunc fp128 %0 to double
%idxprom = sext i32 %idx to i64
%arrayidx = getelementptr inbounds double, double* %res, i64 %idxprom
store double %conv, double* %arrayidx, align 8
ret void
}
; Function Attrs: norecurse nounwind
define void @qpConv2dp_04(fp128* nocapture readonly %a, fp128* nocapture readonly %b, double* nocapture %res) {
; CHECK-LABEL: qpConv2dp_04:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: lxv v3, 0(r4)
; CHECK-NEXT: xsaddqp v2, v2, v3
; CHECK-NEXT: xscvqpdp v2, v2
; CHECK-NEXT: stxsd v2, 0(r5)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2dp_04:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: lvx v2, 0, r3
; CHECK-P8-NEXT: lvx v3, 0, r4
; CHECK-P8-NEXT: mr r30, r5
; CHECK-P8-NEXT: bl __addkf3
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: bl __trunckfdf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stfd f1, 0(r30)
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load fp128, fp128* %a, align 16
%1 = load fp128, fp128* %b, align 16
%add = fadd fp128 %0, %1
%conv = fptrunc fp128 %add to double
store double %conv, double* %res, align 8
ret void
}
; Convert QP to SP
; Function Attrs: norecurse nounwind readonly
define float @qpConv2sp(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2sp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: xscvqpdpo v2, v2
; CHECK-NEXT: xsrsp f1, v2
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2sp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: lvx v2, 0, r3
; CHECK-P8-NEXT: bl __trunckfsf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load fp128, fp128* %a, align 16
%conv = fptrunc fp128 %0 to float
ret float %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2sp_02(float* nocapture %res) {
; CHECK-LABEL: qpConv2sp_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC6@toc@ha
; CHECK-NEXT: ld r4, .LC6@toc@l(r4)
; CHECK-NEXT: lxv v2, 0(r4)
; CHECK-NEXT: xscvqpdpo v2, v2
; CHECK-NEXT: xsrsp f0, v2
; CHECK-NEXT: stfs f0, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2sp_02:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: addis r4, r2, .LC6@toc@ha
; CHECK-P8-NEXT: mr r30, r3
; CHECK-P8-NEXT: ld r4, .LC6@toc@l(r4)
; CHECK-P8-NEXT: lvx v2, 0, r4
; CHECK-P8-NEXT: bl __trunckfsf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stfs f1, 0(r30)
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load fp128, fp128* @f128global, align 16
%conv = fptrunc fp128 %0 to float
store float %conv, float* %res, align 4
ret void
}
; Function Attrs: norecurse nounwind
define void @qpConv2sp_03(float* nocapture %res, i32 signext %idx) {
; CHECK-LABEL: qpConv2sp_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r5, r2, .LC7@toc@ha
; CHECK-NEXT: sldi r4, r4, 2
; CHECK-NEXT: ld r5, .LC7@toc@l(r5)
; CHECK-NEXT: lxv v2, 48(r5)
; CHECK-NEXT: xscvqpdpo v2, v2
; CHECK-NEXT: xsrsp f0, v2
; CHECK-NEXT: stfsx f0, r3, r4
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2sp_03:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 64
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r29, -24
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r29, -24(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -64(r1)
; CHECK-P8-NEXT: mr r30, r4
; CHECK-P8-NEXT: addis r4, r2, .LC7@toc@ha
; CHECK-P8-NEXT: mr r29, r3
; CHECK-P8-NEXT: ld r4, .LC7@toc@l(r4)
; CHECK-P8-NEXT: addi r4, r4, 48
; CHECK-P8-NEXT: lvx v2, 0, r4
; CHECK-P8-NEXT: bl __trunckfsf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: sldi r3, r30, 2
; CHECK-P8-NEXT: stfsx f1, r29, r3
; CHECK-P8-NEXT: addi r1, r1, 64
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: ld r29, -24(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load fp128, fp128* getelementptr inbounds ([4 x fp128], [4 x fp128]* @f128Array, i64 0, i64 3), align 16
%conv = fptrunc fp128 %0 to float
%idxprom = sext i32 %idx to i64
%arrayidx = getelementptr inbounds float, float* %res, i64 %idxprom
store float %conv, float* %arrayidx, align 4
ret void
}
; Function Attrs: norecurse nounwind
define void @qpConv2sp_04(fp128* nocapture readonly %a, fp128* nocapture readonly %b, float* nocapture %res) {
; CHECK-LABEL: qpConv2sp_04:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: lxv v3, 0(r4)
; CHECK-NEXT: xsaddqp v2, v2, v3
; CHECK-NEXT: xscvqpdpo v2, v2
; CHECK-NEXT: xsrsp f0, v2
; CHECK-NEXT: stfs f0, 0(r5)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2sp_04:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: lvx v2, 0, r3
; CHECK-P8-NEXT: lvx v3, 0, r4
; CHECK-P8-NEXT: mr r30, r5
; CHECK-P8-NEXT: bl __addkf3
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: bl __trunckfsf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stfs f1, 0(r30)
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load fp128, fp128* %a, align 16
%1 = load fp128, fp128* %b, align 16
%add = fadd fp128 %0, %1
%conv = fptrunc fp128 %add to float
store float %conv, float* %res, align 4
ret void
}
@f128Glob = common global fp128 0xL00000000000000000000000000000000, align 16
; Function Attrs: norecurse nounwind readnone
define fp128 @dpConv2qp(double %a) {
; CHECK-LABEL: dpConv2qp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xscpsgndp v2, f1, f1
; CHECK-NEXT: xscvdpqp v2, v2
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: dpConv2qp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: bl __extenddfkf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = fpext double %a to fp128
ret fp128 %conv
}
; Function Attrs: norecurse nounwind
define void @dpConv2qp_02(double* nocapture readonly %a) {
; CHECK-LABEL: dpConv2qp_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxsd v2, 0(r3)
; CHECK-NEXT: addis r3, r2, .LC8@toc@ha
; CHECK-NEXT: ld r3, .LC8@toc@l(r3)
; CHECK-NEXT: xscvdpqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: dpConv2qp_02:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: lfd f1, 0(r3)
; CHECK-P8-NEXT: bl __extenddfkf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addis r3, r2, .LC8@toc@ha
; CHECK-P8-NEXT: ld r3, .LC8@toc@l(r3)
; CHECK-P8-NEXT: stvx v2, 0, r3
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load double, double* %a, align 8
%conv = fpext double %0 to fp128
store fp128 %conv, fp128* @f128Glob, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @dpConv2qp_02b(double* nocapture readonly %a, i32 signext %idx) {
; CHECK-LABEL: dpConv2qp_02b:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: sldi r4, r4, 3
; CHECK-NEXT: lxsdx v2, r3, r4
; CHECK-NEXT: addis r3, r2, .LC8@toc@ha
; CHECK-NEXT: ld r3, .LC8@toc@l(r3)
; CHECK-NEXT: xscvdpqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: dpConv2qp_02b:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: sldi r4, r4, 3
; CHECK-P8-NEXT: lfdx f1, r3, r4
; CHECK-P8-NEXT: bl __extenddfkf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addis r3, r2, .LC8@toc@ha
; CHECK-P8-NEXT: ld r3, .LC8@toc@l(r3)
; CHECK-P8-NEXT: stvx v2, 0, r3
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%idxprom = sext i32 %idx to i64
%arrayidx = getelementptr inbounds double, double* %a, i64 %idxprom
%0 = load double, double* %arrayidx, align 8
%conv = fpext double %0 to fp128
store fp128 %conv, fp128* @f128Glob, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @dpConv2qp_03(fp128* nocapture %res, i32 signext %idx, double %a) {
; CHECK-LABEL: dpConv2qp_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xscpsgndp v2, f1, f1
; CHECK-NEXT: sldi r4, r4, 4
; CHECK-NEXT: xscvdpqp v2, v2
; CHECK-NEXT: stxvx v2, r3, r4
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: dpConv2qp_03:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 64
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r29, -24
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r29, -24(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -64(r1)
; CHECK-P8-NEXT: mr r30, r4
; CHECK-P8-NEXT: mr r29, r3
; CHECK-P8-NEXT: bl __extenddfkf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: sldi r3, r30, 4
; CHECK-P8-NEXT: stvx v2, r29, r3
; CHECK-P8-NEXT: addi r1, r1, 64
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: ld r29, -24(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = fpext double %a to fp128
%idxprom = sext i32 %idx to i64
%arrayidx = getelementptr inbounds fp128, fp128* %res, i64 %idxprom
store fp128 %conv, fp128* %arrayidx, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @dpConv2qp_04(double %a, fp128* nocapture %res) {
; CHECK-LABEL: dpConv2qp_04:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xscpsgndp v2, f1, f1
; CHECK-NEXT: xscvdpqp v2, v2
; CHECK-NEXT: stxv v2, 0(r4)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: dpConv2qp_04:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: mr r30, r4
; CHECK-P8-NEXT: bl __extenddfkf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = fpext double %a to fp128
store fp128 %conv, fp128* %res, align 16
ret void
}
; Function Attrs: norecurse nounwind readnone
define fp128 @spConv2qp(float %a) {
; CHECK-LABEL: spConv2qp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xscpsgndp v2, f1, f1
; CHECK-NEXT: xscvdpqp v2, v2
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: spConv2qp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: bl __extendsfkf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = fpext float %a to fp128
ret fp128 %conv
}
; Function Attrs: norecurse nounwind
define void @spConv2qp_02(float* nocapture readonly %a) {
; CHECK-LABEL: spConv2qp_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxssp v2, 0(r3)
; CHECK-NEXT: addis r3, r2, .LC8@toc@ha
; CHECK-NEXT: ld r3, .LC8@toc@l(r3)
; CHECK-NEXT: xscvdpqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: spConv2qp_02:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: lfs f1, 0(r3)
; CHECK-P8-NEXT: bl __extendsfkf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addis r3, r2, .LC8@toc@ha
; CHECK-P8-NEXT: ld r3, .LC8@toc@l(r3)
; CHECK-P8-NEXT: stvx v2, 0, r3
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load float, float* %a, align 4
%conv = fpext float %0 to fp128
store fp128 %conv, fp128* @f128Glob, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @spConv2qp_02b(float* nocapture readonly %a, i32 signext %idx) {
; CHECK-LABEL: spConv2qp_02b:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: sldi r4, r4, 2
; CHECK-NEXT: lxsspx v2, r3, r4
; CHECK-NEXT: addis r3, r2, .LC8@toc@ha
; CHECK-NEXT: ld r3, .LC8@toc@l(r3)
; CHECK-NEXT: xscvdpqp v2, v2
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: spConv2qp_02b:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: sldi r4, r4, 2
; CHECK-P8-NEXT: lfsx f1, r3, r4
; CHECK-P8-NEXT: bl __extendsfkf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addis r3, r2, .LC8@toc@ha
; CHECK-P8-NEXT: ld r3, .LC8@toc@l(r3)
; CHECK-P8-NEXT: stvx v2, 0, r3
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%idxprom = sext i32 %idx to i64
%arrayidx = getelementptr inbounds float, float* %a, i64 %idxprom
%0 = load float, float* %arrayidx, align 4
%conv = fpext float %0 to fp128
store fp128 %conv, fp128* @f128Glob, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @spConv2qp_03(fp128* nocapture %res, i32 signext %idx, float %a) {
; CHECK-LABEL: spConv2qp_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xscpsgndp v2, f1, f1
; CHECK-NEXT: sldi r4, r4, 4
; CHECK-NEXT: xscvdpqp v2, v2
; CHECK-NEXT: stxvx v2, r3, r4
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: spConv2qp_03:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 64
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r29, -24
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r29, -24(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -64(r1)
; CHECK-P8-NEXT: mr r30, r4
; CHECK-P8-NEXT: mr r29, r3
; CHECK-P8-NEXT: bl __extendsfkf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: sldi r3, r30, 4
; CHECK-P8-NEXT: stvx v2, r29, r3
; CHECK-P8-NEXT: addi r1, r1, 64
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: ld r29, -24(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = fpext float %a to fp128
%idxprom = sext i32 %idx to i64
%arrayidx = getelementptr inbounds fp128, fp128* %res, i64 %idxprom
store fp128 %conv, fp128* %arrayidx, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @spConv2qp_04(float %a, fp128* nocapture %res) {
; CHECK-LABEL: spConv2qp_04:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xscpsgndp v2, f1, f1
; CHECK-NEXT: xscvdpqp v2, v2
; CHECK-NEXT: stxv v2, 0(r4)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: spConv2qp_04:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: mr r30, r4
; CHECK-P8-NEXT: bl __extendsfkf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = fpext float %a to fp128
store fp128 %conv, fp128* %res, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @cvdp2sw2qp(double %val, fp128* nocapture %res) {
; CHECK-LABEL: cvdp2sw2qp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xscvdpsxws v2, f1
; CHECK-NEXT: vextsw2d v2, v2
; CHECK-NEXT: xscvsdqp v2, v2
; CHECK-NEXT: stxv v2, 0(r4)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: cvdp2sw2qp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: xscvdpsxws f0, f1
; CHECK-P8-NEXT: mr r30, r4
; CHECK-P8-NEXT: mffprwz r3, f0
; CHECK-P8-NEXT: extsw r3, r3
; CHECK-P8-NEXT: bl __floatsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = fptosi double %val to i32
%conv1 = sitofp i32 %conv to fp128
store fp128 %conv1, fp128* %res, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @cvdp2sdw2qp(double %val, fp128* nocapture %res) {
; CHECK-LABEL: cvdp2sdw2qp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xscvdpsxds v2, f1
; CHECK-NEXT: xscvsdqp v2, v2
; CHECK-NEXT: stxv v2, 0(r4)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: cvdp2sdw2qp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: xscvdpsxds f0, f1
; CHECK-P8-NEXT: mr r30, r4
; CHECK-P8-NEXT: mffprd r3, f0
; CHECK-P8-NEXT: bl __floatdikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = fptosi double %val to i64
%conv1 = sitofp i64 %conv to fp128
store fp128 %conv1, fp128* %res, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @cvsp2sw2qp(float %val, fp128* nocapture %res) {
; CHECK-LABEL: cvsp2sw2qp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xscvdpsxws v2, f1
; CHECK-NEXT: vextsw2d v2, v2
; CHECK-NEXT: xscvsdqp v2, v2
; CHECK-NEXT: stxv v2, 0(r4)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: cvsp2sw2qp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: xscvdpsxws f0, f1
; CHECK-P8-NEXT: mr r30, r4
; CHECK-P8-NEXT: mffprwz r3, f0
; CHECK-P8-NEXT: extsw r3, r3
; CHECK-P8-NEXT: bl __floatsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = fptosi float %val to i32
%conv1 = sitofp i32 %conv to fp128
store fp128 %conv1, fp128* %res, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @cvsp2sdw2qp(float %val, fp128* nocapture %res) {
; CHECK-LABEL: cvsp2sdw2qp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xscvdpsxds v2, f1
; CHECK-NEXT: xscvsdqp v2, v2
; CHECK-NEXT: stxv v2, 0(r4)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: cvsp2sdw2qp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: xscvdpsxds f0, f1
; CHECK-P8-NEXT: mr r30, r4
; CHECK-P8-NEXT: mffprd r3, f0
; CHECK-P8-NEXT: bl __floatdikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = fptosi float %val to i64
%conv1 = sitofp i64 %conv to fp128
store fp128 %conv1, fp128* %res, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @cvdp2uw2qp(double %val, fp128* nocapture %res) {
; CHECK-LABEL: cvdp2uw2qp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xscvdpuxws f0, f1
; CHECK-NEXT: xxextractuw v2, vs0, 8
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r4)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: cvdp2uw2qp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: xscvdpuxws f0, f1
; CHECK-P8-NEXT: mr r30, r4
; CHECK-P8-NEXT: mffprwz r3, f0
; CHECK-P8-NEXT: clrldi r3, r3, 32
; CHECK-P8-NEXT: bl __floatunsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = fptoui double %val to i32
%conv1 = uitofp i32 %conv to fp128
store fp128 %conv1, fp128* %res, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @cvdp2udw2qp(double %val, fp128* nocapture %res) {
; CHECK-LABEL: cvdp2udw2qp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xscvdpuxds v2, f1
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r4)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: cvdp2udw2qp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: xscvdpuxds f0, f1
; CHECK-P8-NEXT: mr r30, r4
; CHECK-P8-NEXT: mffprd r3, f0
; CHECK-P8-NEXT: bl __floatundikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = fptoui double %val to i64
%conv1 = uitofp i64 %conv to fp128
store fp128 %conv1, fp128* %res, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @cvsp2uw2qp(float %val, fp128* nocapture %res) {
; CHECK-LABEL: cvsp2uw2qp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xscvdpuxws f0, f1
; CHECK-NEXT: xxextractuw v2, vs0, 8
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r4)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: cvsp2uw2qp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: xscvdpuxws f0, f1
; CHECK-P8-NEXT: mr r30, r4
; CHECK-P8-NEXT: mffprwz r3, f0
; CHECK-P8-NEXT: clrldi r3, r3, 32
; CHECK-P8-NEXT: bl __floatunsikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = fptoui float %val to i32
%conv1 = uitofp i32 %conv to fp128
store fp128 %conv1, fp128* %res, align 16
ret void
}
; Function Attrs: norecurse nounwind
define void @cvsp2udw2qp(float %val, fp128* nocapture %res) {
; CHECK-LABEL: cvsp2udw2qp:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xscvdpuxds v2, f1
; CHECK-NEXT: xscvudqp v2, v2
; CHECK-NEXT: stxv v2, 0(r4)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: cvsp2udw2qp:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: xscvdpuxds f0, f1
; CHECK-P8-NEXT: mr r30, r4
; CHECK-P8-NEXT: mffprd r3, f0
; CHECK-P8-NEXT: bl __floatundikf
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stvx v2, 0, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%conv = fptoui float %val to i64
%conv1 = uitofp i64 %conv to fp128
store fp128 %conv1, fp128* %res, align 16
ret void
}
; Function Attrs: norecurse nounwind readonly
define i128 @qpConv2i128(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2i128:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: mflr r0
; CHECK-NEXT: std r0, 16(r1)
; CHECK-NEXT: stdu r1, -32(r1)
; CHECK-NEXT: .cfi_def_cfa_offset 32
; CHECK-NEXT: .cfi_offset lr, 16
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: bl __fixkfti
; CHECK-NEXT: nop
; CHECK-NEXT: addi r1, r1, 32
; CHECK-NEXT: ld r0, 16(r1)
; CHECK-NEXT: mtlr r0
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2i128:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: lvx v2, 0, r3
; CHECK-P8-NEXT: bl __fixkfti
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load fp128, fp128* %a, align 16
%conv = fptosi fp128 %0 to i128
ret i128 %conv
}
; Function Attrs: norecurse nounwind readonly
define i128 @qpConv2ui128(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2ui128:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: mflr r0
; CHECK-NEXT: std r0, 16(r1)
; CHECK-NEXT: stdu r1, -32(r1)
; CHECK-NEXT: .cfi_def_cfa_offset 32
; CHECK-NEXT: .cfi_offset lr, 16
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: bl __fixunskfti
; CHECK-NEXT: nop
; CHECK-NEXT: addi r1, r1, 32
; CHECK-NEXT: ld r0, 16(r1)
; CHECK-NEXT: mtlr r0
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2ui128:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: lvx v2, 0, r3
; CHECK-P8-NEXT: bl __fixunskfti
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load fp128, fp128* %a, align 16
%conv = fptoui fp128 %0 to i128
ret i128 %conv
}
; Function Attrs: norecurse nounwind readonly
define i1 @qpConv2ui1(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2ui1:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: xscvqpswz v2, v2
; CHECK-NEXT: mfvsrwz r3, v2
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2ui1:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: lvx v2, 0, r3
; CHECK-P8-NEXT: bl __fixkfsi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load fp128, fp128* %a, align 16
%conv = fptoui fp128 %0 to i1
ret i1 %conv
}
; Function Attrs: norecurse nounwind readonly
define i1 @qpConv2si1(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2si1:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: xscvqpswz v2, v2
; CHECK-NEXT: mfvsrwz r3, v2
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2si1:
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: lvx v2, 0, r3
; CHECK-P8-NEXT: bl __fixkfsi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
entry:
%0 = load fp128, fp128* %a, align 16
%conv = fptosi fp128 %0 to i1
ret i1 %conv
}
Reference in New Issue View Git Blame Copy Permalink