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-truncateNconv.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

1406 lines
45 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: -verify-machineinstrs -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s \
; RUN: | FileCheck %s
; RUN: llc -relocation-model=pic -mcpu=pwr8 -mtriple=powerpc64le-unknown-unknown \
; RUN: -verify-machineinstrs -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s \
; RUN: | FileCheck %s -check-prefix=CHECK-P8
@f128Array = global [4 x fp128] [fp128 0xL00000000000000004004C00000000000,
fp128 0xLF000000000000000400808AB851EB851,
fp128 0xL5000000000000000400E0C26324C8366,
fp128 0xL8000000000000000400A24E2E147AE14],
align 16
; Function Attrs: norecurse nounwind readonly
define i64 @qpConv2sdw(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2sdw:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: xscvqpsdz v2, v2
; CHECK-NEXT: mfvsrd r3, v2
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2sdw:
; 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 __fixkfdi
; 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 i64
ret i64 %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2sdw_02(i64* nocapture %res) local_unnamed_addr #1 {
; CHECK-LABEL: qpConv2sdw_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC0@toc@ha
; CHECK-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-NEXT: lxv v2, 32(r4)
; CHECK-NEXT: xscvqpsdz v2, v2
; CHECK-NEXT: stxsd v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2sdw_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: addi r4, r4, 32
; CHECK-P8-NEXT: lvx v2, 0, r4
; CHECK-P8-NEXT: bl __fixkfdi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: std r3, 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* getelementptr inbounds
([4 x fp128], [4 x fp128]* @f128Array, i64 0,
i64 2), align 16
%conv = fptosi fp128 %0 to i64
store i64 %conv, i64* %res, align 8
ret void
}
; Function Attrs: norecurse nounwind readonly
define i64 @qpConv2sdw_03(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2sdw_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, .LC0@toc@ha
; CHECK-NEXT: ld r3, .LC0@toc@l(r3)
; CHECK-NEXT: lxv v3, 16(r3)
; CHECK-NEXT: xsaddqp v2, v2, v3
; CHECK-NEXT: xscvqpsdz v2, v2
; CHECK-NEXT: mfvsrd r3, v2
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2sdw_03:
; 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: addis r4, r2, .LC0@toc@ha
; CHECK-P8-NEXT: lvx v2, 0, r3
; CHECK-P8-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-P8-NEXT: addi r4, r4, 16
; CHECK-P8-NEXT: lvx v3, 0, r4
; CHECK-P8-NEXT: bl __addkf3
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: bl __fixkfdi
; 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
%1 = load fp128, fp128* getelementptr inbounds
([4 x fp128], [4 x fp128]* @f128Array, i64 0,
i64 1), align 16
%add = fadd fp128 %0, %1
%conv = fptosi fp128 %add to i64
ret i64 %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2sdw_04(fp128* nocapture readonly %a,
; CHECK-LABEL: qpConv2sdw_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: xscvqpsdz v2, v2
; CHECK-NEXT: stxsd v2, 0(r5)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2sdw_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 __fixkfdi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: std r3, 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
fp128* nocapture readonly %b, i64* nocapture %res) {
entry:
%0 = load fp128, fp128* %a, align 16
%1 = load fp128, fp128* %b, align 16
%add = fadd fp128 %0, %1
%conv = fptosi fp128 %add to i64
store i64 %conv, i64* %res, align 8
ret void
}
; Function Attrs: norecurse nounwind
define void @qpConv2sdw_testXForm(i64* nocapture %res, i32 signext %idx) {
; CHECK-LABEL: qpConv2sdw_testXForm:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r5, r2, .LC0@toc@ha
; CHECK-NEXT: sldi r4, r4, 3
; CHECK-NEXT: ld r5, .LC0@toc@l(r5)
; CHECK-NEXT: lxv v2, 32(r5)
; CHECK-NEXT: xscvqpsdz v2, v2
; CHECK-NEXT: stxsdx v2, r3, r4
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2sdw_testXForm:
; 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, .LC0@toc@ha
; CHECK-P8-NEXT: mr r29, r3
; CHECK-P8-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-P8-NEXT: addi r4, r4, 32
; CHECK-P8-NEXT: lvx v2, 0, r4
; CHECK-P8-NEXT: bl __fixkfdi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: sldi r4, r30, 3
; CHECK-P8-NEXT: stdx r3, r29, r4
; 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 2), align 16
%conv = fptosi fp128 %0 to i64
%idxprom = sext i32 %idx to i64
%arrayidx = getelementptr inbounds i64, i64* %res, i64 %idxprom
store i64 %conv, i64* %arrayidx, align 8
ret void
}
; Function Attrs: norecurse nounwind readonly
define i64 @qpConv2udw(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2udw:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: xscvqpudz v2, v2
; CHECK-NEXT: mfvsrd r3, v2
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2udw:
; 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 __fixunskfdi
; 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 i64
ret i64 %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2udw_02(i64* nocapture %res) {
; CHECK-LABEL: qpConv2udw_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC0@toc@ha
; CHECK-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-NEXT: lxv v2, 32(r4)
; CHECK-NEXT: xscvqpudz v2, v2
; CHECK-NEXT: stxsd v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2udw_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: addi r4, r4, 32
; CHECK-P8-NEXT: lvx v2, 0, r4
; CHECK-P8-NEXT: bl __fixunskfdi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: std r3, 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* getelementptr inbounds
([4 x fp128], [4 x fp128]* @f128Array, i64 0,
i64 2), align 16
%conv = fptoui fp128 %0 to i64
store i64 %conv, i64* %res, align 8
ret void
}
; Function Attrs: norecurse nounwind readonly
define i64 @qpConv2udw_03(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2udw_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, .LC0@toc@ha
; CHECK-NEXT: ld r3, .LC0@toc@l(r3)
; CHECK-NEXT: lxv v3, 16(r3)
; CHECK-NEXT: xsaddqp v2, v2, v3
; CHECK-NEXT: xscvqpudz v2, v2
; CHECK-NEXT: mfvsrd r3, v2
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2udw_03:
; 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: addis r4, r2, .LC0@toc@ha
; CHECK-P8-NEXT: lvx v2, 0, r3
; CHECK-P8-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-P8-NEXT: addi r4, r4, 16
; CHECK-P8-NEXT: lvx v3, 0, r4
; CHECK-P8-NEXT: bl __addkf3
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: bl __fixunskfdi
; 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
%1 = load fp128, fp128* getelementptr inbounds
([4 x fp128], [4 x fp128]* @f128Array, i64 0,
i64 1), align 16
%add = fadd fp128 %0, %1
%conv = fptoui fp128 %add to i64
ret i64 %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2udw_04(fp128* nocapture readonly %a,
; CHECK-LABEL: qpConv2udw_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: xscvqpudz v2, v2
; CHECK-NEXT: stxsd v2, 0(r5)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2udw_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 __fixunskfdi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: std r3, 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
fp128* nocapture readonly %b, i64* nocapture %res) {
entry:
%0 = load fp128, fp128* %a, align 16
%1 = load fp128, fp128* %b, align 16
%add = fadd fp128 %0, %1
%conv = fptoui fp128 %add to i64
store i64 %conv, i64* %res, align 8
ret void
}
; Function Attrs: norecurse nounwind
define void @qpConv2udw_testXForm(i64* nocapture %res, i32 signext %idx) {
; CHECK-LABEL: qpConv2udw_testXForm:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r5, r2, .LC0@toc@ha
; CHECK-NEXT: sldi r4, r4, 3
; CHECK-NEXT: ld r5, .LC0@toc@l(r5)
; CHECK-NEXT: lxv v2, 0(r5)
; CHECK-NEXT: xscvqpudz v2, v2
; CHECK-NEXT: stxsdx v2, r3, r4
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2udw_testXForm:
; 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, .LC0@toc@ha
; CHECK-P8-NEXT: mr r29, r3
; CHECK-P8-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-P8-NEXT: lvx v2, 0, r4
; CHECK-P8-NEXT: bl __fixunskfdi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: sldi r4, r30, 3
; CHECK-P8-NEXT: stdx r3, r29, r4
; 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 = fptoui fp128 %0 to i64
%idxprom = sext i32 %idx to i64
%arrayidx = getelementptr inbounds i64, i64* %res, i64 %idxprom
store i64 %conv, i64* %arrayidx, align 8
ret void
}
; Function Attrs: norecurse nounwind readonly
define signext i32 @qpConv2sw(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2sw:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: xscvqpswz v2, v2
; CHECK-NEXT: mfvsrwz r3, v2
; CHECK-NEXT: extsw r3, r3
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2sw:
; 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: extsw r3, 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 fp128, fp128* %a, align 16
%conv = fptosi fp128 %0 to i32
ret i32 %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2sw_02(i32* nocapture %res) {
; CHECK-LABEL: qpConv2sw_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC0@toc@ha
; CHECK-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-NEXT: lxv v2, 32(r4)
; CHECK-NEXT: xscvqpswz v2, v2
; CHECK-NEXT: stxsiwx v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2sw_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: addi r4, r4, 32
; CHECK-P8-NEXT: lvx v2, 0, r4
; CHECK-P8-NEXT: bl __fixkfsi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stw r3, 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* getelementptr inbounds
([4 x fp128], [4 x fp128]* @f128Array, i64 0,
i64 2), align 16
%conv = fptosi fp128 %0 to i32
store i32 %conv, i32* %res, align 4
ret void
}
; Function Attrs: norecurse nounwind readonly
define signext i32 @qpConv2sw_03(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2sw_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, .LC0@toc@ha
; CHECK-NEXT: ld r3, .LC0@toc@l(r3)
; CHECK-NEXT: lxv v3, 16(r3)
; CHECK-NEXT: xsaddqp v2, v2, v3
; CHECK-NEXT: xscvqpswz v2, v2
; CHECK-NEXT: mfvsrwz r3, v2
; CHECK-NEXT: extsw r3, r3
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2sw_03:
; 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: addis r4, r2, .LC0@toc@ha
; CHECK-P8-NEXT: lvx v2, 0, r3
; CHECK-P8-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-P8-NEXT: addi r4, r4, 16
; CHECK-P8-NEXT: lvx v3, 0, r4
; CHECK-P8-NEXT: bl __addkf3
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: bl __fixkfsi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: extsw r3, 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 fp128, fp128* %a, align 16
%1 = load fp128, fp128* getelementptr inbounds
([4 x fp128], [4 x fp128]* @f128Array, i64 0,
i64 1), align 16
%add = fadd fp128 %0, %1
%conv = fptosi fp128 %add to i32
ret i32 %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2sw_04(fp128* nocapture readonly %a,
; CHECK-LABEL: qpConv2sw_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: xscvqpswz v2, v2
; CHECK-NEXT: stxsiwx v2, 0, r5
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2sw_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 __fixkfsi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stw r3, 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
fp128* nocapture readonly %b, i32* nocapture %res) {
entry:
%0 = load fp128, fp128* %a, align 16
%1 = load fp128, fp128* %b, align 16
%add = fadd fp128 %0, %1
%conv = fptosi fp128 %add to i32
store i32 %conv, i32* %res, align 4
ret void
}
; Function Attrs: norecurse nounwind readonly
define zeroext i32 @qpConv2uw(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2uw:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: xscvqpuwz v2, v2
; CHECK-NEXT: mfvsrwz r3, v2
; CHECK-NEXT: clrldi r3, r3, 32
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2uw:
; 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 __fixunskfsi
; 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 i32
ret i32 %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2uw_02(i32* nocapture %res) {
; CHECK-LABEL: qpConv2uw_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC0@toc@ha
; CHECK-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-NEXT: lxv v2, 32(r4)
; CHECK-NEXT: xscvqpuwz v2, v2
; CHECK-NEXT: stxsiwx v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2uw_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: addi r4, r4, 32
; CHECK-P8-NEXT: lvx v2, 0, r4
; CHECK-P8-NEXT: bl __fixunskfsi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stw r3, 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* getelementptr inbounds
([4 x fp128], [4 x fp128]* @f128Array, i64 0,
i64 2), align 16
%conv = fptoui fp128 %0 to i32
store i32 %conv, i32* %res, align 4
ret void
}
; Function Attrs: norecurse nounwind readonly
define zeroext i32 @qpConv2uw_03(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2uw_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, .LC0@toc@ha
; CHECK-NEXT: ld r3, .LC0@toc@l(r3)
; CHECK-NEXT: lxv v3, 16(r3)
; CHECK-NEXT: xsaddqp v2, v2, v3
; CHECK-NEXT: xscvqpuwz v2, v2
; CHECK-NEXT: mfvsrwz r3, v2
; CHECK-NEXT: clrldi r3, r3, 32
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2uw_03:
; 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: addis r4, r2, .LC0@toc@ha
; CHECK-P8-NEXT: lvx v2, 0, r3
; CHECK-P8-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-P8-NEXT: addi r4, r4, 16
; CHECK-P8-NEXT: lvx v3, 0, r4
; CHECK-P8-NEXT: bl __addkf3
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: bl __fixunskfsi
; 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
%1 = load fp128, fp128* getelementptr inbounds
([4 x fp128], [4 x fp128]* @f128Array, i64 0,
i64 1), align 16
%add = fadd fp128 %0, %1
%conv = fptoui fp128 %add to i32
ret i32 %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2uw_04(fp128* nocapture readonly %a,
; CHECK-LABEL: qpConv2uw_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: xscvqpuwz v2, v2
; CHECK-NEXT: stxsiwx v2, 0, r5
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2uw_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 __fixunskfsi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stw r3, 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
fp128* nocapture readonly %b, i32* nocapture %res) {
entry:
%0 = load fp128, fp128* %a, align 16
%1 = load fp128, fp128* %b, align 16
%add = fadd fp128 %0, %1
%conv = fptoui fp128 %add to i32
store i32 %conv, i32* %res, align 4
ret void
}
; Function Attrs: norecurse nounwind readonly
define signext i16 @qpConv2shw(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2shw:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: xscvqpswz v2, v2
; CHECK-NEXT: mfvsrwz r3, v2
; CHECK-NEXT: extsw r3, r3
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2shw:
; 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: extsw r3, 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 fp128, fp128* %a, align 16
%conv = fptosi fp128 %0 to i16
ret i16 %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2shw_02(i16* nocapture %res) {
; CHECK-LABEL: qpConv2shw_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC0@toc@ha
; CHECK-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-NEXT: lxv v2, 32(r4)
; CHECK-NEXT: xscvqpswz v2, v2
; CHECK-NEXT: stxsihx v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2shw_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: addi r4, r4, 32
; CHECK-P8-NEXT: lvx v2, 0, r4
; CHECK-P8-NEXT: bl __fixkfsi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: sth r3, 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* getelementptr inbounds
([4 x fp128], [4 x fp128]* @f128Array,
i64 0, i64 2), align 16
%conv = fptosi fp128 %0 to i16
store i16 %conv, i16* %res, align 2
ret void
}
; Function Attrs: norecurse nounwind readonly
define signext i16 @qpConv2shw_03(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2shw_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, .LC0@toc@ha
; CHECK-NEXT: ld r3, .LC0@toc@l(r3)
; CHECK-NEXT: lxv v3, 16(r3)
; CHECK-NEXT: xsaddqp v2, v2, v3
; CHECK-NEXT: xscvqpswz v2, v2
; CHECK-NEXT: mfvsrwz r3, v2
; CHECK-NEXT: extsw r3, r3
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2shw_03:
; 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: addis r4, r2, .LC0@toc@ha
; CHECK-P8-NEXT: lvx v2, 0, r3
; CHECK-P8-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-P8-NEXT: addi r4, r4, 16
; CHECK-P8-NEXT: lvx v3, 0, r4
; CHECK-P8-NEXT: bl __addkf3
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: bl __fixkfsi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: extsw r3, 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 fp128, fp128* %a, align 16
%1 = load fp128, fp128* getelementptr inbounds
([4 x fp128], [4 x fp128]* @f128Array,
i64 0, i64 1), align 16
%add = fadd fp128 %0, %1
%conv = fptosi fp128 %add to i16
ret i16 %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2shw_04(fp128* nocapture readonly %a,
; CHECK-LABEL: qpConv2shw_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: xscvqpswz v2, v2
; CHECK-NEXT: stxsihx v2, 0, r5
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2shw_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 __fixkfsi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: sth r3, 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
fp128* nocapture readonly %b, i16* nocapture %res) {
entry:
%0 = load fp128, fp128* %a, align 16
%1 = load fp128, fp128* %b, align 16
%add = fadd fp128 %0, %1
%conv = fptosi fp128 %add to i16
store i16 %conv, i16* %res, align 2
ret void
}
; Function Attrs: norecurse nounwind readonly
define zeroext i16 @qpConv2uhw(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2uhw:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: xscvqpswz v2, v2
; CHECK-NEXT: mfvsrwz r3, v2
; CHECK-NEXT: clrldi r3, r3, 32
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2uhw:
; 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 i16
ret i16 %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2uhw_02(i16* nocapture %res) {
; CHECK-LABEL: qpConv2uhw_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC0@toc@ha
; CHECK-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-NEXT: lxv v2, 32(r4)
; CHECK-NEXT: xscvqpuwz v2, v2
; CHECK-NEXT: stxsihx v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2uhw_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: addi r4, r4, 32
; CHECK-P8-NEXT: lvx v2, 0, r4
; CHECK-P8-NEXT: bl __fixkfsi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: sth r3, 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* getelementptr inbounds
([4 x fp128], [4 x fp128]* @f128Array,
i64 0, i64 2), align 16
%conv = fptoui fp128 %0 to i16
store i16 %conv, i16* %res, align 2
ret void
}
; Function Attrs: norecurse nounwind readonly
define zeroext i16 @qpConv2uhw_03(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2uhw_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, .LC0@toc@ha
; CHECK-NEXT: ld r3, .LC0@toc@l(r3)
; CHECK-NEXT: lxv v3, 16(r3)
; CHECK-NEXT: xsaddqp v2, v2, v3
; CHECK-NEXT: xscvqpswz v2, v2
; CHECK-NEXT: mfvsrwz r3, v2
; CHECK-NEXT: clrldi r3, r3, 32
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2uhw_03:
; 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: addis r4, r2, .LC0@toc@ha
; CHECK-P8-NEXT: lvx v2, 0, r3
; CHECK-P8-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-P8-NEXT: addi r4, r4, 16
; CHECK-P8-NEXT: lvx v3, 0, r4
; CHECK-P8-NEXT: bl __addkf3
; CHECK-P8-NEXT: nop
; 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
%1 = load fp128, fp128* getelementptr inbounds
([4 x fp128], [4 x fp128]* @f128Array,
i64 0, i64 1), align 16
%add = fadd fp128 %0, %1
%conv = fptoui fp128 %add to i16
ret i16 %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2uhw_04(fp128* nocapture readonly %a,
; CHECK-LABEL: qpConv2uhw_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: xscvqpuwz v2, v2
; CHECK-NEXT: stxsihx v2, 0, r5
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2uhw_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 __fixkfsi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: sth r3, 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
fp128* nocapture readonly %b, i16* nocapture %res) {
entry:
%0 = load fp128, fp128* %a, align 16
%1 = load fp128, fp128* %b, align 16
%add = fadd fp128 %0, %1
%conv = fptoui fp128 %add to i16
store i16 %conv, i16* %res, align 2
ret void
}
; Function Attrs: norecurse nounwind readonly
define signext i8 @qpConv2sb(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2sb:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: xscvqpswz v2, v2
; CHECK-NEXT: mfvsrwz r3, v2
; CHECK-NEXT: extsw r3, r3
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2sb:
; 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: extsw r3, 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 fp128, fp128* %a, align 16
%conv = fptosi fp128 %0 to i8
ret i8 %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2sb_02(i8* nocapture %res) {
; CHECK-LABEL: qpConv2sb_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC0@toc@ha
; CHECK-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-NEXT: lxv v2, 32(r4)
; CHECK-NEXT: xscvqpswz v2, v2
; CHECK-NEXT: stxsibx v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2sb_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: addi r4, r4, 32
; CHECK-P8-NEXT: lvx v2, 0, r4
; CHECK-P8-NEXT: bl __fixkfsi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stb r3, 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* getelementptr inbounds
([4 x fp128], [4 x fp128]* @f128Array,
i64 0, i64 2), align 16
%conv = fptosi fp128 %0 to i8
store i8 %conv, i8* %res, align 1
ret void
}
; Function Attrs: norecurse nounwind readonly
define signext i8 @qpConv2sb_03(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2sb_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, .LC0@toc@ha
; CHECK-NEXT: ld r3, .LC0@toc@l(r3)
; CHECK-NEXT: lxv v3, 16(r3)
; CHECK-NEXT: xsaddqp v2, v2, v3
; CHECK-NEXT: xscvqpswz v2, v2
; CHECK-NEXT: mfvsrwz r3, v2
; CHECK-NEXT: extsw r3, r3
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2sb_03:
; 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: addis r4, r2, .LC0@toc@ha
; CHECK-P8-NEXT: lvx v2, 0, r3
; CHECK-P8-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-P8-NEXT: addi r4, r4, 16
; CHECK-P8-NEXT: lvx v3, 0, r4
; CHECK-P8-NEXT: bl __addkf3
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: bl __fixkfsi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: extsw r3, 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 fp128, fp128* %a, align 16
%1 = load fp128, fp128* getelementptr inbounds
([4 x fp128], [4 x fp128]* @f128Array,
i64 0, i64 1), align 16
%add = fadd fp128 %0, %1
%conv = fptosi fp128 %add to i8
ret i8 %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2sb_04(fp128* nocapture readonly %a,
; CHECK-LABEL: qpConv2sb_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: xscvqpswz v2, v2
; CHECK-NEXT: stxsibx v2, 0, r5
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2sb_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 __fixkfsi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stb r3, 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
fp128* nocapture readonly %b, i8* nocapture %res) {
entry:
%0 = load fp128, fp128* %a, align 16
%1 = load fp128, fp128* %b, align 16
%add = fadd fp128 %0, %1
%conv = fptosi fp128 %add to i8
store i8 %conv, i8* %res, align 1
ret void
}
; Function Attrs: norecurse nounwind readonly
define zeroext i8 @qpConv2ub(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2ub:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: xscvqpswz v2, v2
; CHECK-NEXT: mfvsrwz r3, v2
; CHECK-NEXT: clrldi r3, r3, 32
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2ub:
; 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 i8
ret i8 %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2ub_02(i8* nocapture %res) {
; CHECK-LABEL: qpConv2ub_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC0@toc@ha
; CHECK-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-NEXT: lxv v2, 32(r4)
; CHECK-NEXT: xscvqpuwz v2, v2
; CHECK-NEXT: stxsibx v2, 0, r3
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2ub_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: addi r4, r4, 32
; CHECK-P8-NEXT: lvx v2, 0, r4
; CHECK-P8-NEXT: bl __fixkfsi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stb r3, 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* getelementptr inbounds
([4 x fp128], [4 x fp128]* @f128Array,
i64 0, i64 2), align 16
%conv = fptoui fp128 %0 to i8
store i8 %conv, i8* %res, align 1
ret void
}
; Function Attrs: norecurse nounwind readonly
define zeroext i8 @qpConv2ub_03(fp128* nocapture readonly %a) {
; CHECK-LABEL: qpConv2ub_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, .LC0@toc@ha
; CHECK-NEXT: ld r3, .LC0@toc@l(r3)
; CHECK-NEXT: lxv v3, 16(r3)
; CHECK-NEXT: xsaddqp v2, v2, v3
; CHECK-NEXT: xscvqpswz v2, v2
; CHECK-NEXT: mfvsrwz r3, v2
; CHECK-NEXT: clrldi r3, r3, 32
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2ub_03:
; 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: addis r4, r2, .LC0@toc@ha
; CHECK-P8-NEXT: lvx v2, 0, r3
; CHECK-P8-NEXT: ld r4, .LC0@toc@l(r4)
; CHECK-P8-NEXT: addi r4, r4, 16
; CHECK-P8-NEXT: lvx v3, 0, r4
; CHECK-P8-NEXT: bl __addkf3
; CHECK-P8-NEXT: nop
; 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
%1 = load fp128, fp128* getelementptr inbounds
([4 x fp128], [4 x fp128]* @f128Array,
i64 0, i64 1), align 16
%add = fadd fp128 %0, %1
%conv = fptoui fp128 %add to i8
ret i8 %conv
}
; Function Attrs: norecurse nounwind
define void @qpConv2ub_04(fp128* nocapture readonly %a,
; CHECK-LABEL: qpConv2ub_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: xscvqpuwz v2, v2
; CHECK-NEXT: stxsibx v2, 0, r5
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: qpConv2ub_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 __fixkfsi
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stb r3, 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
fp128* nocapture readonly %b, i8* nocapture %res) {
entry:
%0 = load fp128, fp128* %a, align 16
%1 = load fp128, fp128* %b, align 16
%add = fadd fp128 %0, %1
%conv = fptoui fp128 %add to i8
store i8 %conv, i8* %res, align 1
ret void
}
Reference in New Issue View Git Blame Copy Permalink