Skip to content

[GlobalISel] Support vector G_UNMERGE_VALUES in computeKnownBits. #112172

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 15, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 17 additions & 7 deletions llvm/lib/CodeGen/GlobalISel/GISelKnownBits.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -514,23 +514,33 @@ void GISelKnownBits::computeKnownBitsImpl(Register R, KnownBits &Known,
break;
}
case TargetOpcode::G_UNMERGE_VALUES: {
if (DstTy.isVector())
break;
unsigned NumOps = MI.getNumOperands();
Register SrcReg = MI.getOperand(NumOps - 1).getReg();
if (MRI.getType(SrcReg).isVector())
return; // TODO: Handle vectors.
LLT SrcTy = MRI.getType(SrcReg);

KnownBits SrcOpKnown;
computeKnownBitsImpl(SrcReg, SrcOpKnown, DemandedElts, Depth + 1);
if (SrcTy.isVector() && SrcTy.getScalarType() != DstTy.getScalarType())
return; // TODO: Handle vector->subelement unmerges

// Figure out the result operand index
unsigned DstIdx = 0;
for (; DstIdx != NumOps - 1 && MI.getOperand(DstIdx).getReg() != R;
++DstIdx)
;

Known = SrcOpKnown.extractBits(BitWidth, BitWidth * DstIdx);
APInt SubDemandedElts = DemandedElts;
if (SrcTy.isVector()) {
unsigned DstLanes = DstTy.isVector() ? DstTy.getNumElements() : 1;
SubDemandedElts =
DemandedElts.zext(SrcTy.getNumElements()).shl(DstIdx * DstLanes);
}

KnownBits SrcOpKnown;
computeKnownBitsImpl(SrcReg, SrcOpKnown, SubDemandedElts, Depth + 1);

if (SrcTy.isVector())
Known = SrcOpKnown;
else
Known = SrcOpKnown.extractBits(BitWidth, BitWidth * DstIdx);
break;
}
case TargetOpcode::G_BSWAP: {
Expand Down
252 changes: 125 additions & 127 deletions llvm/test/CodeGen/AMDGPU/GlobalISel/sdiv.i64.ll
Original file line number Diff line number Diff line change
Expand Up @@ -1184,73 +1184,74 @@ define <2 x i64> @v_sdiv_v2i64_oddk_denom(<2 x i64> %num) {
; GISEL-NEXT: v_rcp_iflag_f32_e32 v4, v4
; GISEL-NEXT: v_mul_f32_e32 v4, 0x5f7ffffc, v4
; GISEL-NEXT: v_mul_f32_e32 v5, 0x2f800000, v4
; GISEL-NEXT: v_trunc_f32_e32 v7, v5
; GISEL-NEXT: v_mac_f32_e32 v4, 0xcf800000, v7
; GISEL-NEXT: v_cvt_u32_f32_e32 v6, v4
; GISEL-NEXT: v_cvt_u32_f32_e32 v7, v7
; GISEL-NEXT: v_mad_u64_u32 v[4:5], s[4:5], s6, v6, 0
; GISEL-NEXT: v_mad_u64_u32 v[8:9], s[4:5], s6, v7, v[5:6]
; GISEL-NEXT: v_mul_lo_u32 v5, v7, v4
; GISEL-NEXT: v_mad_u64_u32 v[8:9], s[4:5], s7, v6, v[8:9]
; GISEL-NEXT: v_mul_hi_u32 v9, v6, v4
; GISEL-NEXT: v_mul_hi_u32 v4, v7, v4
; GISEL-NEXT: v_mul_lo_u32 v10, v6, v8
; GISEL-NEXT: v_mul_lo_u32 v11, v7, v8
; GISEL-NEXT: v_mul_hi_u32 v12, v6, v8
; GISEL-NEXT: v_trunc_f32_e32 v6, v5
; GISEL-NEXT: v_mac_f32_e32 v4, 0xcf800000, v6
; GISEL-NEXT: v_cvt_u32_f32_e32 v5, v4
; GISEL-NEXT: v_cvt_u32_f32_e32 v7, v6
; GISEL-NEXT: v_mad_u64_u32 v[8:9], s[4:5], s6, v5, 0
; GISEL-NEXT: v_mov_b32_e32 v4, v9
; GISEL-NEXT: v_mad_u64_u32 v[9:10], s[4:5], s6, v7, v[4:5]
; GISEL-NEXT: v_mul_lo_u32 v4, v7, v8
; GISEL-NEXT: v_mul_hi_u32 v6, v5, v8
; GISEL-NEXT: v_mad_u64_u32 v[9:10], s[4:5], s7, v5, v[9:10]
; GISEL-NEXT: v_mul_hi_u32 v8, v7, v8
; GISEL-NEXT: v_add_i32_e32 v5, vcc, v5, v10
; GISEL-NEXT: v_mul_lo_u32 v10, v5, v9
; GISEL-NEXT: v_mul_lo_u32 v11, v7, v9
; GISEL-NEXT: v_mul_hi_u32 v12, v5, v9
; GISEL-NEXT: v_mul_hi_u32 v9, v7, v9
; GISEL-NEXT: v_add_i32_e32 v4, vcc, v4, v10
; GISEL-NEXT: v_cndmask_b32_e64 v10, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v5, vcc, v5, v9
; GISEL-NEXT: v_cndmask_b32_e64 v5, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v5, vcc, v10, v5
; GISEL-NEXT: v_add_i32_e32 v4, vcc, v11, v4
; GISEL-NEXT: v_cndmask_b32_e64 v9, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v4, vcc, v4, v12
; GISEL-NEXT: v_add_i32_e32 v4, vcc, v4, v6
; GISEL-NEXT: v_cndmask_b32_e64 v4, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v4, vcc, v10, v4
; GISEL-NEXT: v_add_i32_e32 v6, vcc, v11, v8
; GISEL-NEXT: v_cndmask_b32_e64 v8, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v6, vcc, v6, v12
; GISEL-NEXT: v_cndmask_b32_e64 v10, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v9, vcc, v9, v10
; GISEL-NEXT: v_add_i32_e32 v4, vcc, v4, v5
; GISEL-NEXT: v_cndmask_b32_e64 v5, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v5, vcc, v9, v5
; GISEL-NEXT: v_add_i32_e32 v5, vcc, v8, v5
; GISEL-NEXT: v_add_i32_e32 v11, vcc, v6, v4
; GISEL-NEXT: v_add_i32_e32 v8, vcc, v8, v10
; GISEL-NEXT: v_add_i32_e32 v4, vcc, v6, v4
; GISEL-NEXT: v_cndmask_b32_e64 v6, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v6, vcc, v8, v6
; GISEL-NEXT: v_add_i32_e32 v6, vcc, v9, v6
; GISEL-NEXT: v_add_i32_e32 v11, vcc, v5, v4
; GISEL-NEXT: v_mad_u64_u32 v[8:9], s[4:5], s6, v11, 0
; GISEL-NEXT: v_addc_u32_e32 v5, vcc, v7, v5, vcc
; GISEL-NEXT: v_addc_u32_e32 v12, vcc, v7, v6, vcc
; GISEL-NEXT: v_mov_b32_e32 v4, v9
; GISEL-NEXT: v_mad_u64_u32 v[9:10], s[4:5], s6, v5, v[4:5]
; GISEL-NEXT: v_ashrrev_i32_e32 v4, 31, v1
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v0, v4
; GISEL-NEXT: v_mad_u64_u32 v[9:10], s[4:5], s6, v12, v[4:5]
; GISEL-NEXT: v_ashrrev_i32_e32 v6, 31, v1
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v0, v6
; GISEL-NEXT: v_mad_u64_u32 v[9:10], s[4:5], s7, v11, v[9:10]
; GISEL-NEXT: v_addc_u32_e32 v1, vcc, v1, v4, vcc
; GISEL-NEXT: v_xor_b32_e32 v10, v0, v4
; GISEL-NEXT: v_mul_lo_u32 v0, v5, v8
; GISEL-NEXT: v_mul_lo_u32 v12, v11, v9
; GISEL-NEXT: v_xor_b32_e32 v13, v1, v4
; GISEL-NEXT: v_addc_u32_e32 v1, vcc, v1, v6, vcc
; GISEL-NEXT: v_xor_b32_e32 v10, v0, v6
; GISEL-NEXT: v_mul_lo_u32 v0, v12, v8
; GISEL-NEXT: v_mul_lo_u32 v4, v11, v9
; GISEL-NEXT: v_xor_b32_e32 v13, v1, v6
; GISEL-NEXT: v_mul_hi_u32 v1, v11, v8
; GISEL-NEXT: v_mul_hi_u32 v8, v5, v8
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v0, v12
; GISEL-NEXT: v_cndmask_b32_e64 v12, 0, 1, vcc
; GISEL-NEXT: v_mul_hi_u32 v8, v12, v8
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v0, v4
; GISEL-NEXT: v_cndmask_b32_e64 v4, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v0, v1
; GISEL-NEXT: v_cndmask_b32_e64 v0, 0, 1, vcc
; GISEL-NEXT: v_mul_lo_u32 v1, v5, v9
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v12, v0
; GISEL-NEXT: v_mul_hi_u32 v12, v11, v9
; GISEL-NEXT: v_mul_lo_u32 v1, v12, v9
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v4, v0
; GISEL-NEXT: v_mul_hi_u32 v4, v11, v9
; GISEL-NEXT: v_add_i32_e32 v1, vcc, v1, v8
; GISEL-NEXT: v_cndmask_b32_e64 v8, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v1, vcc, v1, v12
; GISEL-NEXT: v_cndmask_b32_e64 v12, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v8, vcc, v8, v12
; GISEL-NEXT: v_mul_hi_u32 v9, v5, v9
; GISEL-NEXT: v_add_i32_e32 v1, vcc, v1, v4
; GISEL-NEXT: v_cndmask_b32_e64 v4, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v4, vcc, v8, v4
; GISEL-NEXT: v_mul_hi_u32 v8, v12, v9
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v1, v0
; GISEL-NEXT: v_cndmask_b32_e64 v1, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v1, vcc, v4, v1
; GISEL-NEXT: v_add_i32_e32 v1, vcc, v8, v1
; GISEL-NEXT: v_add_i32_e32 v1, vcc, v9, v1
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v11, v0
; GISEL-NEXT: v_addc_u32_e32 v1, vcc, v5, v1, vcc
; GISEL-NEXT: v_addc_u32_e32 v1, vcc, v12, v1, vcc
; GISEL-NEXT: v_mul_lo_u32 v8, v13, v0
; GISEL-NEXT: v_mul_lo_u32 v9, v10, v1
; GISEL-NEXT: v_mul_hi_u32 v11, v10, v0
; GISEL-NEXT: v_mul_hi_u32 v0, v13, v0
; GISEL-NEXT: v_mov_b32_e32 v5, 0x12d8fb
; GISEL-NEXT: v_mov_b32_e32 v4, 0x12d8fb
; GISEL-NEXT: v_add_i32_e32 v8, vcc, v8, v9
; GISEL-NEXT: v_cndmask_b32_e64 v9, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v8, vcc, v8, v11
Expand All @@ -1265,40 +1266,39 @@ define <2 x i64> @v_sdiv_v2i64_oddk_denom(<2 x i64> %num) {
; GISEL-NEXT: v_add_i32_e32 v9, vcc, v11, v9
; GISEL-NEXT: v_add_i32_e32 v11, vcc, v0, v8
; GISEL-NEXT: v_mul_hi_u32 v12, v13, v1
; GISEL-NEXT: v_mad_u64_u32 v[0:1], s[4:5], v5, v11, 0
; GISEL-NEXT: v_mad_u64_u32 v[0:1], s[4:5], v4, v11, 0
; GISEL-NEXT: v_cndmask_b32_e64 v8, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v8, vcc, v9, v8
; GISEL-NEXT: v_add_i32_e32 v12, vcc, v12, v8
; GISEL-NEXT: v_mad_u64_u32 v[8:9], s[4:5], v5, v12, v[1:2]
; GISEL-NEXT: v_mad_u64_u32 v[8:9], s[4:5], v4, v12, v[1:2]
; GISEL-NEXT: v_sub_i32_e32 v0, vcc, v10, v0
; GISEL-NEXT: v_mad_u64_u32 v[8:9], s[4:5], 0, v11, v[8:9]
; GISEL-NEXT: s_sub_u32 s6, 0, 0x12d8fb
; GISEL-NEXT: s_subb_u32 s7, 0, 0
; GISEL-NEXT: v_subb_u32_e64 v1, s[4:5], v13, v8, vcc
; GISEL-NEXT: v_sub_i32_e64 v8, s[4:5], v13, v8
; GISEL-NEXT: v_cmp_ge_u32_e64 s[4:5], v0, v5
; GISEL-NEXT: v_cmp_ge_u32_e64 s[4:5], v0, v4
; GISEL-NEXT: v_cndmask_b32_e64 v9, 0, -1, s[4:5]
; GISEL-NEXT: v_cmp_eq_u32_e64 s[4:5], 0, v1
; GISEL-NEXT: v_subbrev_u32_e32 v1, vcc, 0, v8, vcc
; GISEL-NEXT: v_sub_i32_e32 v8, vcc, v0, v5
; GISEL-NEXT: v_sub_i32_e32 v8, vcc, v0, v4
; GISEL-NEXT: v_cndmask_b32_e64 v10, -1, v9, s[4:5]
; GISEL-NEXT: v_subbrev_u32_e32 v9, vcc, 0, v1, vcc
; GISEL-NEXT: s_sub_u32 s6, 0, 0x12d8fb
; GISEL-NEXT: v_add_i32_e32 v13, vcc, 1, v11
; GISEL-NEXT: v_mad_u64_u32 v[0:1], s[4:5], s6, v6, 0
; GISEL-NEXT: v_mad_u64_u32 v[0:1], s[4:5], s6, v5, 0
; GISEL-NEXT: v_addc_u32_e32 v14, vcc, 0, v12, vcc
; GISEL-NEXT: v_cmp_ge_u32_e32 vcc, v8, v5
; GISEL-NEXT: v_cmp_ge_u32_e32 vcc, v8, v4
; GISEL-NEXT: v_cndmask_b32_e64 v8, 0, -1, vcc
; GISEL-NEXT: v_cmp_eq_u32_e32 vcc, 0, v9
; GISEL-NEXT: v_cndmask_b32_e32 v15, -1, v8, vcc
; GISEL-NEXT: v_mad_u64_u32 v[8:9], s[4:5], s6, v7, v[1:2]
; GISEL-NEXT: s_subb_u32 s7, 0, 0
; GISEL-NEXT: v_add_i32_e32 v1, vcc, 1, v13
; GISEL-NEXT: v_mad_u64_u32 v[8:9], s[4:5], s7, v6, v[8:9]
; GISEL-NEXT: v_mad_u64_u32 v[8:9], s[4:5], s7, v5, v[8:9]
; GISEL-NEXT: v_addc_u32_e32 v16, vcc, 0, v14, vcc
; GISEL-NEXT: v_cmp_ne_u32_e32 vcc, 0, v15
; GISEL-NEXT: v_cndmask_b32_e32 v9, v13, v1, vcc
; GISEL-NEXT: v_mul_lo_u32 v1, v7, v0
; GISEL-NEXT: v_mul_lo_u32 v13, v6, v8
; GISEL-NEXT: v_mul_hi_u32 v15, v6, v0
; GISEL-NEXT: v_mul_lo_u32 v13, v5, v8
; GISEL-NEXT: v_mul_hi_u32 v15, v5, v0
; GISEL-NEXT: v_cndmask_b32_e32 v14, v14, v16, vcc
; GISEL-NEXT: v_mul_hi_u32 v0, v7, v0
; GISEL-NEXT: v_add_i32_e32 v1, vcc, v1, v13
Expand All @@ -1307,7 +1307,7 @@ define <2 x i64> @v_sdiv_v2i64_oddk_denom(<2 x i64> %num) {
; GISEL-NEXT: v_cndmask_b32_e64 v1, 0, 1, vcc
; GISEL-NEXT: v_mul_lo_u32 v15, v7, v8
; GISEL-NEXT: v_add_i32_e32 v1, vcc, v13, v1
; GISEL-NEXT: v_mul_hi_u32 v13, v6, v8
; GISEL-NEXT: v_mul_hi_u32 v13, v5, v8
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v15, v0
; GISEL-NEXT: v_cndmask_b32_e64 v15, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v0, v13
Expand All @@ -1318,95 +1318,93 @@ define <2 x i64> @v_sdiv_v2i64_oddk_denom(<2 x i64> %num) {
; GISEL-NEXT: v_cndmask_b32_e64 v1, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v1, vcc, v13, v1
; GISEL-NEXT: v_add_i32_e32 v1, vcc, v8, v1
; GISEL-NEXT: v_add_i32_e32 v8, vcc, v6, v0
; GISEL-NEXT: v_add_i32_e32 v5, vcc, v5, v0
; GISEL-NEXT: v_addc_u32_e32 v13, vcc, v7, v1, vcc
; GISEL-NEXT: v_mad_u64_u32 v[0:1], s[4:5], s6, v8, 0
; GISEL-NEXT: v_mad_u64_u32 v[0:1], s[4:5], s6, v5, 0
; GISEL-NEXT: v_cmp_ne_u32_e32 vcc, 0, v10
; GISEL-NEXT: v_cndmask_b32_e32 v9, v11, v9, vcc
; GISEL-NEXT: v_mad_u64_u32 v[6:7], s[4:5], s6, v13, v[1:2]
; GISEL-NEXT: v_xor_b32_e32 v1, v9, v4
; GISEL-NEXT: v_cndmask_b32_e32 v7, v11, v9, vcc
; GISEL-NEXT: v_xor_b32_e32 v10, v7, v6
; GISEL-NEXT: v_mad_u64_u32 v[7:8], s[4:5], s6, v13, v[1:2]
; GISEL-NEXT: v_cndmask_b32_e32 v9, v12, v14, vcc
; GISEL-NEXT: v_xor_b32_e32 v1, v9, v6
; GISEL-NEXT: v_mad_u64_u32 v[7:8], s[4:5], s7, v5, v[7:8]
; GISEL-NEXT: v_ashrrev_i32_e32 v9, 31, v3
; GISEL-NEXT: v_mad_u64_u32 v[6:7], s[4:5], s7, v8, v[6:7]
; GISEL-NEXT: v_cndmask_b32_e32 v10, v12, v14, vcc
; GISEL-NEXT: v_add_i32_e32 v2, vcc, v2, v9
; GISEL-NEXT: v_addc_u32_e32 v3, vcc, v3, v9, vcc
; GISEL-NEXT: v_xor_b32_e32 v11, v2, v9
; GISEL-NEXT: v_xor_b32_e32 v8, v2, v9
; GISEL-NEXT: v_mul_lo_u32 v2, v13, v0
; GISEL-NEXT: v_mul_lo_u32 v7, v8, v6
; GISEL-NEXT: v_mul_lo_u32 v11, v5, v7
; GISEL-NEXT: v_xor_b32_e32 v12, v3, v9
; GISEL-NEXT: v_mul_hi_u32 v3, v8, v0
; GISEL-NEXT: v_mul_hi_u32 v3, v5, v0
; GISEL-NEXT: v_mul_hi_u32 v0, v13, v0
; GISEL-NEXT: v_add_i32_e32 v2, vcc, v2, v7
; GISEL-NEXT: v_cndmask_b32_e64 v7, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v2, vcc, v2, v11
; GISEL-NEXT: v_cndmask_b32_e64 v11, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v2, vcc, v2, v3
; GISEL-NEXT: v_cndmask_b32_e64 v2, 0, 1, vcc
; GISEL-NEXT: v_mul_lo_u32 v3, v13, v6
; GISEL-NEXT: v_add_i32_e32 v2, vcc, v7, v2
; GISEL-NEXT: v_mul_hi_u32 v7, v8, v6
; GISEL-NEXT: v_mul_lo_u32 v3, v13, v7
; GISEL-NEXT: v_add_i32_e32 v2, vcc, v11, v2
; GISEL-NEXT: v_mul_hi_u32 v11, v5, v7
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v3, v0
; GISEL-NEXT: v_cndmask_b32_e64 v3, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v0, v7
; GISEL-NEXT: v_cndmask_b32_e64 v7, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v3, vcc, v3, v7
; GISEL-NEXT: v_mul_hi_u32 v6, v13, v6
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v0, v11
; GISEL-NEXT: v_cndmask_b32_e64 v11, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v3, vcc, v3, v11
; GISEL-NEXT: v_mul_hi_u32 v7, v13, v7
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v0, v2
; GISEL-NEXT: v_cndmask_b32_e64 v2, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v2, vcc, v3, v2
; GISEL-NEXT: v_add_i32_e32 v2, vcc, v6, v2
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v8, v0
; GISEL-NEXT: v_add_i32_e32 v2, vcc, v7, v2
; GISEL-NEXT: v_add_i32_e32 v3, vcc, v5, v0
; GISEL-NEXT: v_addc_u32_e32 v2, vcc, v13, v2, vcc
; GISEL-NEXT: v_mul_lo_u32 v3, v12, v0
; GISEL-NEXT: v_mul_lo_u32 v6, v11, v2
; GISEL-NEXT: v_mul_hi_u32 v7, v11, v0
; GISEL-NEXT: v_mul_hi_u32 v0, v12, v0
; GISEL-NEXT: v_xor_b32_e32 v8, v10, v4
; GISEL-NEXT: v_add_i32_e32 v3, vcc, v3, v6
; GISEL-NEXT: v_mul_lo_u32 v5, v12, v3
; GISEL-NEXT: v_mul_lo_u32 v7, v8, v2
; GISEL-NEXT: v_sub_i32_e32 v0, vcc, v10, v6
; GISEL-NEXT: v_subb_u32_e32 v1, vcc, v1, v6, vcc
; GISEL-NEXT: v_mul_hi_u32 v6, v8, v3
; GISEL-NEXT: v_add_i32_e32 v5, vcc, v5, v7
; GISEL-NEXT: v_cndmask_b32_e64 v7, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v5, vcc, v5, v6
; GISEL-NEXT: v_cndmask_b32_e64 v5, 0, 1, vcc
; GISEL-NEXT: v_mul_lo_u32 v6, v12, v2
; GISEL-NEXT: v_mul_hi_u32 v3, v12, v3
; GISEL-NEXT: v_add_i32_e32 v5, vcc, v7, v5
; GISEL-NEXT: v_mul_hi_u32 v7, v8, v2
; GISEL-NEXT: v_add_i32_e32 v3, vcc, v6, v3
; GISEL-NEXT: v_cndmask_b32_e64 v6, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v3, vcc, v3, v7
; GISEL-NEXT: v_cndmask_b32_e64 v3, 0, 1, vcc
; GISEL-NEXT: v_mul_lo_u32 v7, v12, v2
; GISEL-NEXT: v_add_i32_e32 v3, vcc, v6, v3
; GISEL-NEXT: v_mul_hi_u32 v6, v11, v2
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v7, v0
; GISEL-NEXT: v_cndmask_b32_e64 v7, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v0, v6
; GISEL-NEXT: v_cndmask_b32_e64 v6, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v6, vcc, v7, v6
; GISEL-NEXT: v_add_i32_e32 v10, vcc, v0, v3
; GISEL-NEXT: v_mul_hi_u32 v7, v12, v2
; GISEL-NEXT: v_mad_u64_u32 v[2:3], s[4:5], v5, v10, 0
; GISEL-NEXT: v_cndmask_b32_e64 v0, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v0, vcc, v6, v0
; GISEL-NEXT: v_add_i32_e32 v13, vcc, v7, v0
; GISEL-NEXT: v_mov_b32_e32 v0, v3
; GISEL-NEXT: v_mad_u64_u32 v[6:7], s[4:5], v5, v13, v[0:1]
; GISEL-NEXT: v_sub_i32_e32 v0, vcc, v1, v4
; GISEL-NEXT: v_subb_u32_e32 v1, vcc, v8, v4, vcc
; GISEL-NEXT: v_mad_u64_u32 v[3:4], s[4:5], 0, v10, v[6:7]
; GISEL-NEXT: v_sub_i32_e32 v2, vcc, v11, v2
; GISEL-NEXT: v_subb_u32_e64 v4, s[4:5], v12, v3, vcc
; GISEL-NEXT: v_sub_i32_e64 v3, s[4:5], v12, v3
; GISEL-NEXT: v_subbrev_u32_e32 v3, vcc, 0, v3, vcc
; GISEL-NEXT: v_cmp_ge_u32_e64 s[4:5], v2, v5
; GISEL-NEXT: v_sub_i32_e32 v2, vcc, v2, v5
; GISEL-NEXT: v_add_i32_e32 v6, vcc, v6, v7
; GISEL-NEXT: v_add_i32_e32 v7, vcc, v3, v5
; GISEL-NEXT: v_mul_hi_u32 v10, v12, v2
; GISEL-NEXT: v_mad_u64_u32 v[2:3], s[4:5], v4, v7, 0
; GISEL-NEXT: v_cndmask_b32_e64 v5, 0, 1, vcc
; GISEL-NEXT: v_add_i32_e32 v5, vcc, v6, v5
; GISEL-NEXT: v_add_i32_e32 v10, vcc, v10, v5
; GISEL-NEXT: v_mad_u64_u32 v[5:6], s[4:5], v4, v10, v[3:4]
; GISEL-NEXT: v_sub_i32_e32 v2, vcc, v8, v2
; GISEL-NEXT: v_subb_u32_e64 v3, s[4:5], v12, v5, vcc
; GISEL-NEXT: v_sub_i32_e64 v5, s[4:5], v12, v5
; GISEL-NEXT: v_subbrev_u32_e32 v5, vcc, 0, v5, vcc
; GISEL-NEXT: v_cmp_ge_u32_e64 s[4:5], v2, v4
; GISEL-NEXT: v_sub_i32_e32 v2, vcc, v2, v4
; GISEL-NEXT: v_cndmask_b32_e64 v6, 0, -1, s[4:5]
; GISEL-NEXT: v_cmp_eq_u32_e64 s[4:5], 0, v4
; GISEL-NEXT: v_subbrev_u32_e32 v3, vcc, 0, v3, vcc
; GISEL-NEXT: v_cndmask_b32_e64 v4, -1, v6, s[4:5]
; GISEL-NEXT: v_add_i32_e32 v6, vcc, 1, v10
; GISEL-NEXT: v_addc_u32_e32 v7, vcc, 0, v13, vcc
; GISEL-NEXT: v_cmp_ge_u32_e32 vcc, v2, v5
; GISEL-NEXT: v_cmp_eq_u32_e64 s[4:5], 0, v3
; GISEL-NEXT: v_subbrev_u32_e32 v5, vcc, 0, v5, vcc
; GISEL-NEXT: v_cndmask_b32_e64 v3, -1, v6, s[4:5]
; GISEL-NEXT: v_add_i32_e32 v6, vcc, 1, v7
; GISEL-NEXT: v_addc_u32_e32 v8, vcc, 0, v10, vcc
; GISEL-NEXT: v_cmp_ge_u32_e32 vcc, v2, v4
; GISEL-NEXT: v_cndmask_b32_e64 v2, 0, -1, vcc
; GISEL-NEXT: v_cmp_eq_u32_e32 vcc, 0, v3
; GISEL-NEXT: v_cmp_eq_u32_e32 vcc, 0, v5
; GISEL-NEXT: v_cndmask_b32_e32 v2, -1, v2, vcc
; GISEL-NEXT: v_add_i32_e32 v3, vcc, 1, v6
; GISEL-NEXT: v_addc_u32_e32 v5, vcc, 0, v7, vcc
; GISEL-NEXT: v_add_i32_e32 v4, vcc, 1, v6
; GISEL-NEXT: v_addc_u32_e32 v5, vcc, 0, v8, vcc
; GISEL-NEXT: v_cmp_ne_u32_e32 vcc, 0, v2
; GISEL-NEXT: v_cndmask_b32_e32 v2, v6, v3, vcc
; GISEL-NEXT: v_cndmask_b32_e32 v3, v7, v5, vcc
; GISEL-NEXT: v_cmp_ne_u32_e32 vcc, 0, v4
; GISEL-NEXT: v_cndmask_b32_e32 v2, v10, v2, vcc
; GISEL-NEXT: v_cndmask_b32_e32 v3, v13, v3, vcc
; GISEL-NEXT: v_cndmask_b32_e32 v2, v6, v4, vcc
; GISEL-NEXT: v_cndmask_b32_e32 v4, v8, v5, vcc
; GISEL-NEXT: v_cmp_ne_u32_e32 vcc, 0, v3
; GISEL-NEXT: v_cndmask_b32_e32 v2, v7, v2, vcc
; GISEL-NEXT: v_cndmask_b32_e32 v3, v10, v4, vcc
; GISEL-NEXT: v_xor_b32_e32 v2, v2, v9
; GISEL-NEXT: v_xor_b32_e32 v3, v3, v9
; GISEL-NEXT: v_sub_i32_e32 v2, vcc, v2, v9
Expand Down
Loading
Loading