[PowerPC] Promote the i1 to i64 for SINT_TO_FP/FP_TO_SINT

i1 is the native type for PowerPC if crbits is enabled. However, we need
to promote the i1 to i64 as we didn't have the pattern for i1.

Reviewed By: Qiu Chao Fang

Differential Revision: https://reviews.llvm.org/D92067

diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
index 2d8dfb6..1864dc7 100644 (file)
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -234,6 +234,20 @@ PPCTargetLowering::PPCTargetLowering(const PPCTargetMachine &TM,
       setOperationAction(ISD::UINT_TO_FP, MVT::i1, Promote);
       AddPromotedToType(ISD::UINT_TO_FP, MVT::i1,
                         isPPC64 ? MVT::i64 : MVT::i32);
+
+      setOperationAction(ISD::STRICT_FP_TO_SINT, MVT::i1, Promote);
+      AddPromotedToType(ISD::STRICT_FP_TO_SINT, MVT::i1,
+                        isPPC64 ? MVT::i64 : MVT::i32);
+      setOperationAction(ISD::STRICT_FP_TO_UINT, MVT::i1, Promote);
+      AddPromotedToType(ISD::STRICT_FP_TO_UINT, MVT::i1,
+                        isPPC64 ? MVT::i64 : MVT::i32);
+
+      setOperationAction(ISD::FP_TO_SINT, MVT::i1, Promote);
+      AddPromotedToType(ISD::FP_TO_SINT, MVT::i1,
+                        isPPC64 ? MVT::i64 : MVT::i32);
+      setOperationAction(ISD::FP_TO_UINT, MVT::i1, Promote);
+      AddPromotedToType(ISD::FP_TO_UINT, MVT::i1,
+                        isPPC64 ? MVT::i64 : MVT::i32);
     } else {
       setOperationAction(ISD::STRICT_SINT_TO_FP, MVT::i1, Custom);
       setOperationAction(ISD::STRICT_UINT_TO_FP, MVT::i1, Custom);

diff --git a/llvm/test/CodeGen/PowerPC/f128-conv.ll b/llvm/test/CodeGen/PowerPC/f128-conv.ll
index 29cbe2d..f8c6c97 100644 (file)
--- a/llvm/test/CodeGen/PowerPC/f128-conv.ll
+++ b/llvm/test/CodeGen/PowerPC/f128-conv.ll
@@ -182,6 +182,47 @@ entry:
 }
 
 ; 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:    clrldi r3, r4, 63
+; CHECK-P8-NEXT:    neg r3, r3
+; CHECK-P8-NEXT:    bl __floatsikf
+; CHECK-P8-NEXT:    nop
+; CHECK-P8-NEXT:    std r4, 8(r30)
+; 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:
+  %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
@@ -350,6 +391,43 @@ entry:
 }
 
 ; 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 __floatunsikf
+; CHECK-P8-NEXT:    nop
+; CHECK-P8-NEXT:    std r4, 8(r30)
+; 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:
+  %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
@@ -2136,3 +2214,64 @@ entry:
   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:    ld r5, 0(r3)
+; CHECK-P8-NEXT:    ld r4, 8(r3)
+; CHECK-P8-NEXT:    mr r3, r5
+; 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 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:    ld r5, 0(r3)
+; CHECK-P8-NEXT:    ld r4, 8(r3)
+; CHECK-P8-NEXT:    mr r3, r5
+; 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
+}

diff --git a/llvm/test/CodeGen/PowerPC/fp-strict-conv-f128.ll b/llvm/test/CodeGen/PowerPC/fp-strict-conv-f128.ll
index bb3a2cb..02cd5cf 100644 (file)
--- a/llvm/test/CodeGen/PowerPC/fp-strict-conv-f128.ll
+++ b/llvm/test/CodeGen/PowerPC/fp-strict-conv-f128.ll
@@ -9,28 +9,36 @@
 ; RUN:   < %s -mtriple=powerpc64le-unknown-linux -mcpu=pwr8 -mattr=-vsx \
 ; RUN:   | FileCheck %s -check-prefix=NOVSX
 
+declare i1 @llvm.experimental.constrained.fptosi.i1.f128(fp128, metadata)
 declare i32 @llvm.experimental.constrained.fptosi.i32.f128(fp128, metadata)
 declare i64 @llvm.experimental.constrained.fptosi.i64.f128(fp128, metadata)
 declare i64 @llvm.experimental.constrained.fptoui.i64.f128(fp128, metadata)
 declare i32 @llvm.experimental.constrained.fptoui.i32.f128(fp128, metadata)
+declare i1 @llvm.experimental.constrained.fptoui.i1.f128(fp128, metadata)
 
+declare i1 @llvm.experimental.constrained.fptosi.i1.ppcf128(ppc_fp128, metadata)
 declare i32 @llvm.experimental.constrained.fptosi.i32.ppcf128(ppc_fp128, metadata)
 declare i64 @llvm.experimental.constrained.fptosi.i64.ppcf128(ppc_fp128, metadata)
 declare i64 @llvm.experimental.constrained.fptoui.i64.ppcf128(ppc_fp128, metadata)
 declare i32 @llvm.experimental.constrained.fptoui.i32.ppcf128(ppc_fp128, metadata)
+declare i1 @llvm.experimental.constrained.fptoui.i1.ppcf128(ppc_fp128, metadata)
 
 declare i128 @llvm.experimental.constrained.fptosi.i128.ppcf128(ppc_fp128, metadata)
 declare i128 @llvm.experimental.constrained.fptoui.i128.ppcf128(ppc_fp128, metadata)
 declare i128 @llvm.experimental.constrained.fptosi.i128.f128(fp128, metadata)
 declare i128 @llvm.experimental.constrained.fptoui.i128.f128(fp128, metadata)
 
+declare fp128 @llvm.experimental.constrained.sitofp.f128.i1(i1, metadata, metadata)
 declare fp128 @llvm.experimental.constrained.sitofp.f128.i32(i32, metadata, metadata)
 declare fp128 @llvm.experimental.constrained.sitofp.f128.i64(i64, metadata, metadata)
+declare fp128 @llvm.experimental.constrained.uitofp.f128.i1(i1, metadata, metadata)
 declare fp128 @llvm.experimental.constrained.uitofp.f128.i32(i32, metadata, metadata)
 declare fp128 @llvm.experimental.constrained.uitofp.f128.i64(i64, metadata, metadata)
 
+declare ppc_fp128 @llvm.experimental.constrained.sitofp.ppcf128.i1(i1, metadata, metadata)
 declare ppc_fp128 @llvm.experimental.constrained.sitofp.ppcf128.i32(i32, metadata, metadata)
 declare ppc_fp128 @llvm.experimental.constrained.sitofp.ppcf128.i64(i64, metadata, metadata)
+declare ppc_fp128 @llvm.experimental.constrained.uitofp.ppcf128.i1(i1, metadata, metadata)
 declare ppc_fp128 @llvm.experimental.constrained.uitofp.ppcf128.i32(i32, metadata, metadata)
 declare ppc_fp128 @llvm.experimental.constrained.uitofp.ppcf128.i64(i64, metadata, metadata)
 
@@ -128,6 +136,84 @@ entry:
   ret i128 %conv
 }
 
+define i1 @q_to_s1(fp128 %m) #0 {
+; P8-LABEL: q_to_s1:
+; P8:       # %bb.0: # %entry
+; P8-NEXT:    mflr r0
+; P8-NEXT:    std r0, 16(r1)
+; P8-NEXT:    stdu r1, -112(r1)
+; P8-NEXT:    .cfi_def_cfa_offset 112
+; P8-NEXT:    .cfi_offset lr, 16
+; P8-NEXT:    bl __fixkfsi
+; P8-NEXT:    nop
+; P8-NEXT:    addi r1, r1, 112
+; P8-NEXT:    ld r0, 16(r1)
+; P8-NEXT:    mtlr r0
+; P8-NEXT:    blr
+;
+; P9-LABEL: q_to_s1:
+; P9:       # %bb.0: # %entry
+; P9-NEXT:    xscvqpswz v2, v2
+; P9-NEXT:    mfvsrwz r3, v2
+; P9-NEXT:    blr
+;
+; NOVSX-LABEL: q_to_s1:
+; NOVSX:       # %bb.0: # %entry
+; NOVSX-NEXT:    mflr r0
+; NOVSX-NEXT:    std r0, 16(r1)
+; NOVSX-NEXT:    stdu r1, -32(r1)
+; NOVSX-NEXT:    .cfi_def_cfa_offset 32
+; NOVSX-NEXT:    .cfi_offset lr, 16
+; NOVSX-NEXT:    bl __fixkfsi
+; NOVSX-NEXT:    nop
+; NOVSX-NEXT:    addi r1, r1, 32
+; NOVSX-NEXT:    ld r0, 16(r1)
+; NOVSX-NEXT:    mtlr r0
+; NOVSX-NEXT:    blr
+entry:
+  %conv = tail call i1 @llvm.experimental.constrained.fptosi.i1.f128(fp128 %m, metadata !"fpexcept.strict") #0
+  ret i1 %conv
+}
+
+define i1 @q_to_u1(fp128 %m) #0 {
+; P8-LABEL: q_to_u1:
+; P8:       # %bb.0: # %entry
+; P8-NEXT:    mflr r0
+; P8-NEXT:    std r0, 16(r1)
+; P8-NEXT:    stdu r1, -112(r1)
+; P8-NEXT:    .cfi_def_cfa_offset 112
+; P8-NEXT:    .cfi_offset lr, 16
+; P8-NEXT:    bl __fixunskfsi
+; P8-NEXT:    nop
+; P8-NEXT:    addi r1, r1, 112
+; P8-NEXT:    ld r0, 16(r1)
+; P8-NEXT:    mtlr r0
+; P8-NEXT:    blr
+;
+; P9-LABEL: q_to_u1:
+; P9:       # %bb.0: # %entry
+; P9-NEXT:    xscvqpswz v2, v2
+; P9-NEXT:    mfvsrwz r3, v2
+; P9-NEXT:    blr
+;
+; NOVSX-LABEL: q_to_u1:
+; NOVSX:       # %bb.0: # %entry
+; NOVSX-NEXT:    mflr r0
+; NOVSX-NEXT:    std r0, 16(r1)
+; NOVSX-NEXT:    stdu r1, -32(r1)
+; NOVSX-NEXT:    .cfi_def_cfa_offset 32
+; NOVSX-NEXT:    .cfi_offset lr, 16
+; NOVSX-NEXT:    bl __fixunskfsi
+; NOVSX-NEXT:    nop
+; NOVSX-NEXT:    addi r1, r1, 32
+; NOVSX-NEXT:    ld r0, 16(r1)
+; NOVSX-NEXT:    mtlr r0
+; NOVSX-NEXT:    blr
+entry:
+  %conv = tail call i1 @llvm.experimental.constrained.fptoui.i1.f128(fp128 %m, metadata !"fpexcept.strict") #0
+  ret i1 %conv
+}
+
 define i128 @ppcq_to_i128(ppc_fp128 %m) #0 {
 ; P8-LABEL: ppcq_to_i128:
 ; P8:       # %bb.0: # %entry
@@ -527,10 +613,10 @@ define zeroext i32 @ppcq_to_u32(ppc_fp128 %m) #0 {
 ; P8-NEXT:    .cfi_def_cfa_offset 128
 ; P8-NEXT:    .cfi_offset lr, 16
 ; P8-NEXT:    .cfi_offset r30, -16
-; P8-NEXT:    addis r3, r2, .LCPI11_0@toc@ha
+; P8-NEXT:    addis r3, r2, .LCPI13_0@toc@ha
 ; P8-NEXT:    xxlxor f3, f3, f3
 ; P8-NEXT:    std r30, 112(r1) # 8-byte Folded Spill
-; P8-NEXT:    lfs f0, .LCPI11_0@toc@l(r3)
+; P8-NEXT:    lfs f0, .LCPI13_0@toc@l(r3)
 ; P8-NEXT:    fcmpo cr0, f2, f3
 ; P8-NEXT:    lis r3, -32768
 ; P8-NEXT:    xxlxor f3, f3, f3
@@ -539,10 +625,10 @@ define zeroext i32 @ppcq_to_u32(ppc_fp128 %m) #0 {
 ; P8-NEXT:    crandc 4*cr5+gt, 4*cr1+lt, 4*cr1+eq
 ; P8-NEXT:    cror 4*cr5+lt, 4*cr5+gt, 4*cr5+lt
 ; P8-NEXT:    isel r30, 0, r3, 4*cr5+lt
-; P8-NEXT:    bc 12, 4*cr5+lt, .LBB11_2
+; P8-NEXT:    bc 12, 4*cr5+lt, .LBB13_2
 ; P8-NEXT:  # %bb.1: # %entry
 ; P8-NEXT:    fmr f3, f0
-; P8-NEXT:  .LBB11_2: # %entry
+; P8-NEXT:  .LBB13_2: # %entry
 ; P8-NEXT:    xxlxor f4, f4, f4
 ; P8-NEXT:    bl __gcc_qsub
 ; P8-NEXT:    nop
@@ -570,9 +656,9 @@ define zeroext i32 @ppcq_to_u32(ppc_fp128 %m) #0 {
 ; P9-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; P9-NEXT:    std r0, 16(r1)
 ; P9-NEXT:    stdu r1, -48(r1)
-; P9-NEXT:    addis r3, r2, .LCPI11_0@toc@ha
+; P9-NEXT:    addis r3, r2, .LCPI13_0@toc@ha
 ; P9-NEXT:    xxlxor f3, f3, f3
-; P9-NEXT:    lfs f0, .LCPI11_0@toc@l(r3)
+; P9-NEXT:    lfs f0, .LCPI13_0@toc@l(r3)
 ; P9-NEXT:    fcmpo cr1, f2, f3
 ; P9-NEXT:    lis r3, -32768
 ; P9-NEXT:    fcmpo cr0, f1, f0
@@ -581,10 +667,10 @@ define zeroext i32 @ppcq_to_u32(ppc_fp128 %m) #0 {
 ; P9-NEXT:    crandc 4*cr5+gt, lt, eq
 ; P9-NEXT:    cror 4*cr5+lt, 4*cr5+gt, 4*cr5+lt
 ; P9-NEXT:    isel r30, 0, r3, 4*cr5+lt
-; P9-NEXT:    bc 12, 4*cr5+lt, .LBB11_2
+; P9-NEXT:    bc 12, 4*cr5+lt, .LBB13_2
 ; P9-NEXT:  # %bb.1: # %entry
 ; P9-NEXT:    fmr f3, f0
-; P9-NEXT:  .LBB11_2: # %entry
+; P9-NEXT:  .LBB13_2: # %entry
 ; P9-NEXT:    xxlxor f4, f4, f4
 ; P9-NEXT:    bl __gcc_qsub
 ; P9-NEXT:    nop
@@ -613,20 +699,20 @@ define zeroext i32 @ppcq_to_u32(ppc_fp128 %m) #0 {
 ; NOVSX-NEXT:    .cfi_def_cfa_offset 48
 ; NOVSX-NEXT:    .cfi_offset lr, 16
 ; NOVSX-NEXT:    .cfi_offset cr2, 8
-; NOVSX-NEXT:    addis r3, r2, .LCPI11_0@toc@ha
-; NOVSX-NEXT:    addis r4, r2, .LCPI11_1@toc@ha
-; NOVSX-NEXT:    lfs f0, .LCPI11_0@toc@l(r3)
-; NOVSX-NEXT:    lfs f4, .LCPI11_1@toc@l(r4)
+; NOVSX-NEXT:    addis r3, r2, .LCPI13_0@toc@ha
+; NOVSX-NEXT:    addis r4, r2, .LCPI13_1@toc@ha
+; NOVSX-NEXT:    lfs f0, .LCPI13_0@toc@l(r3)
+; NOVSX-NEXT:    lfs f4, .LCPI13_1@toc@l(r4)
 ; NOVSX-NEXT:    fcmpo cr0, f1, f0
 ; NOVSX-NEXT:    fcmpo cr1, f2, f4
 ; NOVSX-NEXT:    fmr f3, f4
 ; NOVSX-NEXT:    crand 4*cr5+lt, eq, 4*cr1+lt
 ; NOVSX-NEXT:    crandc 4*cr5+gt, lt, eq
 ; NOVSX-NEXT:    cror 4*cr2+lt, 4*cr5+gt, 4*cr5+lt
-; NOVSX-NEXT:    bc 12, 4*cr2+lt, .LBB11_2
+; NOVSX-NEXT:    bc 12, 4*cr2+lt, .LBB13_2
 ; NOVSX-NEXT:  # %bb.1: # %entry
 ; NOVSX-NEXT:    fmr f3, f0
-; NOVSX-NEXT:  .LBB11_2: # %entry
+; NOVSX-NEXT:  .LBB13_2: # %entry
 ; NOVSX-NEXT:    bl __gcc_qsub
 ; NOVSX-NEXT:    nop
 ; NOVSX-NEXT:    mffs f0
@@ -653,6 +739,142 @@ entry:
   ret i32 %conv
 }
 
+define fp128 @i1_to_q(i1 signext %m) #0 {
+; P8-LABEL: i1_to_q:
+; P8:       # %bb.0: # %entry
+; P8-NEXT:    mflr r0
+; P8-NEXT:    std r0, 16(r1)
+; P8-NEXT:    stdu r1, -112(r1)
+; P8-NEXT:    .cfi_def_cfa_offset 112
+; P8-NEXT:    .cfi_offset lr, 16
+; P8-NEXT:    bl __floatsikf
+; P8-NEXT:    nop
+; P8-NEXT:    addi r1, r1, 112
+; P8-NEXT:    ld r0, 16(r1)
+; P8-NEXT:    mtlr r0
+; P8-NEXT:    blr
+;
+; P9-LABEL: i1_to_q:
+; P9:       # %bb.0: # %entry
+; P9-NEXT:    mtvsrwa v2, r3
+; P9-NEXT:    xscvsdqp v2, v2
+; P9-NEXT:    blr
+;
+; NOVSX-LABEL: i1_to_q:
+; NOVSX:       # %bb.0: # %entry
+; NOVSX-NEXT:    mflr r0
+; NOVSX-NEXT:    std r0, 16(r1)
+; NOVSX-NEXT:    stdu r1, -32(r1)
+; NOVSX-NEXT:    .cfi_def_cfa_offset 32
+; NOVSX-NEXT:    .cfi_offset lr, 16
+; NOVSX-NEXT:    bl __floatsikf
+; NOVSX-NEXT:    nop
+; NOVSX-NEXT:    addi r1, r1, 32
+; NOVSX-NEXT:    ld r0, 16(r1)
+; NOVSX-NEXT:    mtlr r0
+; NOVSX-NEXT:    blr
+entry:
+  %conv = tail call fp128 @llvm.experimental.constrained.sitofp.f128.i1(i1 %m, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
+  ret fp128 %conv
+}
+
+define fp128 @u1_to_q(i1 zeroext %m) #0 {
+; P8-LABEL: u1_to_q:
+; P8:       # %bb.0: # %entry
+; P8-NEXT:    mflr r0
+; P8-NEXT:    std r0, 16(r1)
+; P8-NEXT:    stdu r1, -112(r1)
+; P8-NEXT:    .cfi_def_cfa_offset 112
+; P8-NEXT:    .cfi_offset lr, 16
+; P8-NEXT:    bl __floatunsikf
+; P8-NEXT:    nop
+; P8-NEXT:    addi r1, r1, 112
+; P8-NEXT:    ld r0, 16(r1)
+; P8-NEXT:    mtlr r0
+; P8-NEXT:    blr
+;
+; P9-LABEL: u1_to_q:
+; P9:       # %bb.0: # %entry
+; P9-NEXT:    mtvsrwa v2, r3
+; P9-NEXT:    xscvsdqp v2, v2
+; P9-NEXT:    blr
+;
+; NOVSX-LABEL: u1_to_q:
+; NOVSX:       # %bb.0: # %entry
+; NOVSX-NEXT:    mflr r0
+; NOVSX-NEXT:    std r0, 16(r1)
+; NOVSX-NEXT:    stdu r1, -32(r1)
+; NOVSX-NEXT:    .cfi_def_cfa_offset 32
+; NOVSX-NEXT:    .cfi_offset lr, 16
+; NOVSX-NEXT:    bl __floatunsikf
+; NOVSX-NEXT:    nop
+; NOVSX-NEXT:    addi r1, r1, 32
+; NOVSX-NEXT:    ld r0, 16(r1)
+; NOVSX-NEXT:    mtlr r0
+; NOVSX-NEXT:    blr
+entry:
+  %conv = tail call fp128 @llvm.experimental.constrained.uitofp.f128.i1(i1 %m, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
+  ret fp128 %conv
+}
+
+define ppc_fp128 @i1_to_ppcq(i1 signext %m) #0 {
+; P8-LABEL: i1_to_ppcq:
+; P8:       # %bb.0: # %entry
+; P8-NEXT:    mtfprwa f0, r3
+; P8-NEXT:    xxlxor f2, f2, f2
+; P8-NEXT:    xscvsxddp f1, f0
+; P8-NEXT:    blr
+;
+; P9-LABEL: i1_to_ppcq:
+; P9:       # %bb.0: # %entry
+; P9-NEXT:    mtfprwa f0, r3
+; P9-NEXT:    xxlxor f2, f2, f2
+; P9-NEXT:    xscvsxddp f1, f0
+; P9-NEXT:    blr
+;
+; NOVSX-LABEL: i1_to_ppcq:
+; NOVSX:       # %bb.0: # %entry
+; NOVSX-NEXT:    addi r4, r1, -4
+; NOVSX-NEXT:    stw r3, -4(r1)
+; NOVSX-NEXT:    addis r3, r2, .LCPI16_0@toc@ha
+; NOVSX-NEXT:    lfiwax f0, 0, r4
+; NOVSX-NEXT:    lfs f2, .LCPI16_0@toc@l(r3)
+; NOVSX-NEXT:    fcfid f1, f0
+; NOVSX-NEXT:    blr
+entry:
+  %conv = tail call ppc_fp128 @llvm.experimental.constrained.sitofp.ppcf128.i1(i1 %m, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
+  ret ppc_fp128 %conv
+}
+
+define ppc_fp128 @u1_to_ppcq(i1 zeroext %m) #0 {
+; P8-LABEL: u1_to_ppcq:
+; P8:       # %bb.0: # %entry
+; P8-NEXT:    mtfprwa f0, r3
+; P8-NEXT:    xxlxor f2, f2, f2
+; P8-NEXT:    xscvsxddp f1, f0
+; P8-NEXT:    blr
+;
+; P9-LABEL: u1_to_ppcq:
+; P9:       # %bb.0: # %entry
+; P9-NEXT:    mtfprwa f0, r3
+; P9-NEXT:    xxlxor f2, f2, f2
+; P9-NEXT:    xscvsxddp f1, f0
+; P9-NEXT:    blr
+;
+; NOVSX-LABEL: u1_to_ppcq:
+; NOVSX:       # %bb.0: # %entry
+; NOVSX-NEXT:    addi r4, r1, -4
+; NOVSX-NEXT:    stw r3, -4(r1)
+; NOVSX-NEXT:    addis r3, r2, .LCPI17_0@toc@ha
+; NOVSX-NEXT:    lfiwax f0, 0, r4
+; NOVSX-NEXT:    lfs f2, .LCPI17_0@toc@l(r3)
+; NOVSX-NEXT:    fcfid f1, f0
+; NOVSX-NEXT:    blr
+entry:
+  %conv = tail call ppc_fp128 @llvm.experimental.constrained.uitofp.ppcf128.i1(i1 %m, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
+  ret ppc_fp128 %conv
+}
+
 define fp128 @i32_to_q(i32 signext %m) #0 {
 ; P8-LABEL: i32_to_q:
 ; P8:       # %bb.0: # %entry

diff --git a/llvm/test/CodeGen/PowerPC/fp-to-int-to-fp.ll b/llvm/test/CodeGen/PowerPC/fp-to-int-to-fp.ll
index 26832ef..b7aec7e 100644 (file)
--- a/llvm/test/CodeGen/PowerPC/fp-to-int-to-fp.ll
+++ b/llvm/test/CodeGen/PowerPC/fp-to-int-to-fp.ll
@@ -194,5 +194,137 @@ entry:
 
 }
 
+; Function Attrs: nounwind readnone
+define i1 @f64_to_si1(double %X) #0 {
+; FPCVT-LABEL: f64_to_si1:
+; FPCVT:       # %bb.0: # %entry
+; FPCVT-NEXT:    fctiwz 0, 1
+; FPCVT-NEXT:    addi 3, 1, -4
+; FPCVT-NEXT:    stfiwx 0, 0, 3
+; FPCVT-NEXT:    lwz 3, -4(1)
+; FPCVT-NEXT:    blr
+;
+; PPC64-LABEL: f64_to_si1:
+; PPC64:       # %bb.0: # %entry
+; PPC64-NEXT:    addi 3, 1, -4
+; PPC64-NEXT:    fctiwz 0, 1
+; PPC64-NEXT:    stfiwx 0, 0, 3
+; PPC64-NEXT:    lwz 3, -4(1)
+; PPC64-NEXT:    blr
+;
+; PWR9-LABEL: f64_to_si1:
+; PWR9:       # %bb.0: # %entry
+; PWR9-NEXT:    xscvdpsxws 0, 1
+; PWR9-NEXT:    mffprwz 3, 0
+; PWR9-NEXT:    blr
+entry:
+  %conv = fptosi double %X to i1
+  ret i1 %conv
+
+}
+
+; Function Attrs: nounwind readnone
+define i1 @f64_to_ui1(double %X) #0 {
+; FPCVT-LABEL: f64_to_ui1:
+; FPCVT:       # %bb.0: # %entry
+; FPCVT-NEXT:    fctiwz 0, 1
+; FPCVT-NEXT:    addi 3, 1, -4
+; FPCVT-NEXT:    stfiwx 0, 0, 3
+; FPCVT-NEXT:    lwz 3, -4(1)
+; FPCVT-NEXT:    blr
+;
+; PPC64-LABEL: f64_to_ui1:
+; PPC64:       # %bb.0: # %entry
+; PPC64-NEXT:    addi 3, 1, -4
+; PPC64-NEXT:    fctiwz 0, 1
+; PPC64-NEXT:    stfiwx 0, 0, 3
+; PPC64-NEXT:    lwz 3, -4(1)
+; PPC64-NEXT:    blr
+;
+; PWR9-LABEL: f64_to_ui1:
+; PWR9:       # %bb.0: # %entry
+; PWR9-NEXT:    xscvdpsxws 0, 1
+; PWR9-NEXT:    mffprwz 3, 0
+; PWR9-NEXT:    blr
+entry:
+  %conv = fptoui double %X to i1
+  ret i1 %conv
+
+}
+
+; Function Attrs: nounwind readnone
+define double @si1_to_f64(i1 %X) #0 {
+; FPCVT-LABEL: si1_to_f64:
+; FPCVT:       # %bb.0: # %entry
+; FPCVT-NEXT:    andi. 3, 3, 1
+; FPCVT-NEXT:    li 4, 0
+; FPCVT-NEXT:    li 3, -1
+; FPCVT-NEXT:    iselgt 3, 3, 4
+; FPCVT-NEXT:    addi 4, 1, -4
+; FPCVT-NEXT:    stw 3, -4(1)
+; FPCVT-NEXT:    lfiwax 0, 0, 4
+; FPCVT-NEXT:    fcfid 1, 0
+; FPCVT-NEXT:    blr
+;
+; PPC64-LABEL: si1_to_f64:
+; PPC64:       # %bb.0: # %entry
+; PPC64-NEXT:    andi. 3, 3, 1
+; PPC64-NEXT:    li 4, -1
+; PPC64-NEXT:    li 3, 0
+; PPC64-NEXT:    bc 12, 1, .LBB6_1
+; PPC64-NEXT:    b .LBB6_2
+; PPC64-NEXT:  .LBB6_1: # %entry
+; PPC64-NEXT:    addi 3, 4, 0
+; PPC64-NEXT:  .LBB6_2: # %entry
+; PPC64-NEXT:    std 3, -8(1)
+; PPC64-NEXT:    lfd 0, -8(1)
+; PPC64-NEXT:    fcfid 1, 0
+; PPC64-NEXT:    blr
+;
+; PWR9-LABEL: si1_to_f64:
+; PWR9:       # %bb.0: # %entry
+; PWR9-NEXT:    andi. 3, 3, 1
+; PWR9-NEXT:    li 3, 0
+; PWR9-NEXT:    li 4, -1
+; PWR9-NEXT:    iselgt 3, 4, 3
+; PWR9-NEXT:    mtfprwa 0, 3
+; PWR9-NEXT:    xscvsxddp 1, 0
+; PWR9-NEXT:    blr
+entry:
+  %conv = sitofp i1 %X to double
+  ret double %conv
+
+}
+
+; Function Attrs: nounwind readnone
+define double @ui1_to_f64(i1 %X) #0 {
+; FPCVT-LABEL: ui1_to_f64:
+; FPCVT:       # %bb.0: # %entry
+; FPCVT-NEXT:    clrlwi 3, 3, 31
+; FPCVT-NEXT:    addi 4, 1, -4
+; FPCVT-NEXT:    stw 3, -4(1)
+; FPCVT-NEXT:    lfiwax 0, 0, 4
+; FPCVT-NEXT:    fcfid 1, 0
+; FPCVT-NEXT:    blr
+;
+; PPC64-LABEL: ui1_to_f64:
+; PPC64:       # %bb.0: # %entry
+; PPC64-NEXT:    clrldi 3, 3, 63
+; PPC64-NEXT:    std 3, -8(1)
+; PPC64-NEXT:    lfd 0, -8(1)
+; PPC64-NEXT:    fcfid 1, 0
+; PPC64-NEXT:    blr
+;
+; PWR9-LABEL: ui1_to_f64:
+; PWR9:       # %bb.0: # %entry
+; PWR9-NEXT:    clrlwi 3, 3, 31
+; PWR9-NEXT:    mtfprwa 0, 3
+; PWR9-NEXT:    xscvsxddp 1, 0
+; PWR9-NEXT:    blr
+entry:
+  %conv = uitofp i1 %X to double
+  ret double %conv
+
+}
 attributes #0 = { nounwind readnone "no-signed-zeros-fp-math"="true" }