forked from OSchip/llvm-project
Power9] Implement new vsx instructions: compare and conversion
This change implements the following vsx instructions: Quad/Double-Precision Compare: xscmpoqp xscmpuqp xscmpexpdp xscmpexpqp xscmpeqdp xscmpgedp xscmpgtdp xscmpnedp xvcmpnedp(.) xvcmpnesp(.) Quad-Precision Floating-Point Conversion xscvqpdp(o) xscvdpqp xscvqpsdz xscvqpswz xscvqpudz xscvqpuwz xscvsdqp xscvudqp xscvdphp xscvhpdp xvcvhpsp xvcvsphp xsrqpi xsrqpix xsrqpxp 28 instructions Phabricator: http://reviews.llvm.org/D16709 llvm-svn: 262068
This commit is contained in:
Kit Barton
parent
e50f744743
commit
93612ec5f2
|
|
@ -124,6 +124,12 @@ def FeatureP8Crypto : SubtargetFeature<"crypto", "HasP8Crypto", "true",
|
|||
def FeatureP8Vector : SubtargetFeature<"power8-vector", "HasP8Vector", "true",
|
||||
"Enable POWER8 vector instructions",
|
||||
[FeatureVSX, FeatureP8Altivec]>;
|
||||
def FeatureP9Altivec : SubtargetFeature<"power9-altivec", "HasP9Altivec", "true",
|
||||
"Enable POWER9 Altivec instructions",
|
||||
[FeatureP8Altivec]>;
|
||||
def FeatureP9Vector : SubtargetFeature<"power9-vector", "HasP9Vector", "true",
|
||||
"Enable POWER9 vector instructions",
|
||||
[FeatureP8Vector, FeatureP9Altivec]>;
|
||||
def FeatureDirectMove :
|
||||
SubtargetFeature<"direct-move", "HasDirectMove", "true",
|
||||
"Enable Power8 direct move instructions",
|
||||
|
|
|
|||
|
|
@ -747,6 +747,13 @@ class XForm_htm3<bits<6> opcode, bits<10> xo, dag OOL, dag IOL, string asmstr,
|
|||
let Inst{31} = RC;
|
||||
}
|
||||
|
||||
// e.g. [PO VRT XO VRB XO /] or [PO VRT XO VRB XO RO]
|
||||
class X_RD5_XO5_RS5<bits<6> opcode, bits<5> xo2, bits<10> xo, dag OOL, dag IOL,
|
||||
string asmstr, InstrItinClass itin, list<dag> pattern>
|
||||
: XForm_base_r3xo<opcode, xo, OOL, IOL, asmstr, itin, pattern> {
|
||||
let A = xo2;
|
||||
}
|
||||
|
||||
// XX*-Form (VSX)
|
||||
class XX1Form<bits<6> opcode, bits<10> xo, dag OOL, dag IOL, string asmstr,
|
||||
InstrItinClass itin, list<dag> pattern>
|
||||
|
|
@ -820,6 +827,22 @@ class XX2Form_2<bits<6> opcode, bits<9> xo, dag OOL, dag IOL, string asmstr,
|
|||
let Inst{31} = XT{5};
|
||||
}
|
||||
|
||||
class XX2_RD6_XO5_RS6<bits<6> opcode, bits<5> xo2, bits<9> xo, dag OOL, dag IOL,
|
||||
string asmstr, InstrItinClass itin, list<dag> pattern>
|
||||
: I<opcode, OOL, IOL, asmstr, itin> {
|
||||
bits<6> XT;
|
||||
bits<6> XB;
|
||||
|
||||
let Pattern = pattern;
|
||||
|
||||
let Inst{6-10} = XT{4-0};
|
||||
let Inst{11-15} = xo2;
|
||||
let Inst{16-20} = XB{4-0};
|
||||
let Inst{21-29} = xo;
|
||||
let Inst{30} = XB{5};
|
||||
let Inst{31} = XT{5};
|
||||
}
|
||||
|
||||
class XX3Form<bits<6> opcode, bits<8> xo, dag OOL, dag IOL, string asmstr,
|
||||
InstrItinClass itin, list<dag> pattern>
|
||||
: I<opcode, OOL, IOL, asmstr, itin> {
|
||||
|
|
|
|||
|
|
@ -1783,3 +1783,138 @@ def : Pat<(i64 (bitconvert f64:$S)),
|
|||
def : Pat<(f64 (bitconvert i64:$S)),
|
||||
(f64 (MTVSRD $S))>;
|
||||
}
|
||||
|
||||
// The following VSX instructions were introduced in Power ISA 3.0
|
||||
def HasP9Vector : Predicate<"PPCSubTarget->hasP9Vector()">;
|
||||
let Predicates = [HasP9Vector] in {
|
||||
|
||||
// [PO VRT XO VRB XO /]
|
||||
class X_VT5_XO5_VB5<bits<6> opcode, bits<5> xo2, bits<10> xo, string opc,
|
||||
list<dag> pattern>
|
||||
: X_RD5_XO5_RS5<opcode, xo2, xo, (outs vrrc:$vT), (ins vrrc:$vB),
|
||||
!strconcat(opc, " $vT, $vB"), IIC_VecFP, pattern>;
|
||||
|
||||
// [PO VRT XO VRB XO RO], Round to Odd version of [PO VRT XO VRB XO /]
|
||||
class X_VT5_XO5_VB5_Ro<bits<6> opcode, bits<5> xo2, bits<10> xo, string opc,
|
||||
list<dag> pattern>
|
||||
: X_VT5_XO5_VB5<opcode, xo2, xo, opc, pattern>, isDOT;
|
||||
|
||||
// [PO VRT XO VRB XO /], but the VRB is only used the left 64 bits (or less),
|
||||
// So we use different operand class for VRB
|
||||
class X_VT5_XO5_VB5_TyVB<bits<6> opcode, bits<5> xo2, bits<10> xo, string opc,
|
||||
RegisterOperand vbtype, list<dag> pattern>
|
||||
: X_RD5_XO5_RS5<opcode, xo2, xo, (outs vrrc:$vT), (ins vbtype:$vB),
|
||||
!strconcat(opc, " $vT, $vB"), IIC_VecFP, pattern>;
|
||||
|
||||
// [PO T XO B XO BX TX]
|
||||
class XX2_XT6_XO5_XB6<bits<6> opcode, bits<5> xo2, bits<9> xo, string opc,
|
||||
RegisterOperand vtype, list<dag> pattern>
|
||||
: XX2_RD6_XO5_RS6<opcode, xo2, xo, (outs vtype:$XT), (ins vtype:$XB),
|
||||
!strconcat(opc, " $XT, $XB"), IIC_VecFP, pattern>;
|
||||
|
||||
// [PO T A B XO AX BX TX], src and dest register use different operand class
|
||||
class XX3_XT5_XA5_XB5<bits<6> opcode, bits<8> xo, string opc,
|
||||
RegisterOperand xty, RegisterOperand aty, RegisterOperand bty,
|
||||
InstrItinClass itin, list<dag> pattern>
|
||||
: XX3Form<opcode, xo, (outs xty:$XT), (ins aty:$XA, bty:$XB),
|
||||
!strconcat(opc, " $XT, $XA, $XB"), itin, pattern>;
|
||||
|
||||
//===--------------------------------------------------------------------===//
|
||||
// Quad/Double-Precision Compare Instructions:
|
||||
|
||||
// [PO BF // VRA VRB XO /]
|
||||
class X_BF3_VA5_VB5<bits<6> opcode, bits<10> xo, string opc,
|
||||
list<dag> pattern>
|
||||
: XForm_17<opcode, xo, (outs crrc:$crD), (ins vrrc:$VA, vrrc:$VB),
|
||||
!strconcat(opc, " $crD, $VA, $VB"), IIC_FPCompare> {
|
||||
let Pattern = pattern;
|
||||
}
|
||||
|
||||
// QP Compare Ordered/Unordered
|
||||
def XSCMPOQP : X_BF3_VA5_VB5<63, 132, "xscmpoqp", []>;
|
||||
def XSCMPUQP : X_BF3_VA5_VB5<63, 644, "xscmpuqp", []>;
|
||||
|
||||
// DP/QP Compare Exponents
|
||||
def XSCMPEXPDP : XX3Form_1<60, 59,
|
||||
(outs crrc:$crD), (ins vsfrc:$XA, vsfrc:$XB),
|
||||
"xscmpexpdp $crD, $XA, $XB", IIC_FPCompare, []>;
|
||||
def XSCMPEXPQP : X_BF3_VA5_VB5<63, 164, "xscmpexpqp", []>;
|
||||
|
||||
// DP Compare ==, >=, >, !=
|
||||
// Use vsrc for XT, because the entire register of XT is set.
|
||||
// XT.dword[1] = 0x0000_0000_0000_0000
|
||||
def XSCMPEQDP : XX3_XT5_XA5_XB5<60, 3, "xscmpeqdp", vsrc, vsfrc, vsfrc,
|
||||
IIC_FPCompare, []>;
|
||||
def XSCMPGEDP : XX3_XT5_XA5_XB5<60, 19, "xscmpgedp", vsrc, vsfrc, vsfrc,
|
||||
IIC_FPCompare, []>;
|
||||
def XSCMPGTDP : XX3_XT5_XA5_XB5<60, 11, "xscmpgtdp", vsrc, vsfrc, vsfrc,
|
||||
IIC_FPCompare, []>;
|
||||
def XSCMPNEDP : XX3_XT5_XA5_XB5<60, 27, "xscmpnedp", vsrc, vsfrc, vsfrc,
|
||||
IIC_FPCompare, []>;
|
||||
// Vector Compare Not Equal
|
||||
def XVCMPNEDP : XX3Form_Rc<60, 123,
|
||||
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
|
||||
"xvcmpnedp $XT, $XA, $XB", IIC_VecFPCompare, []>;
|
||||
let Defs = [CR6] in
|
||||
def XVCMPNEDPo : XX3Form_Rc<60, 123,
|
||||
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
|
||||
"xvcmpnedp. $XT, $XA, $XB", IIC_VecFPCompare, []>,
|
||||
isDOT;
|
||||
def XVCMPNESP : XX3Form_Rc<60, 91,
|
||||
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
|
||||
"xvcmpnesp $XT, $XA, $XB", IIC_VecFPCompare, []>;
|
||||
let Defs = [CR6] in
|
||||
def XVCMPNESPo : XX3Form_Rc<60, 91,
|
||||
(outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
|
||||
"xvcmpnesp. $XT, $XA, $XB", IIC_VecFPCompare, []>,
|
||||
isDOT;
|
||||
|
||||
//===--------------------------------------------------------------------===//
|
||||
// Quad-Precision Floating-Point Conversion Instructions:
|
||||
|
||||
// Convert DP -> QP
|
||||
def XSCVDPQP : X_VT5_XO5_VB5_TyVB<63, 22, 836, "xscvdpqp", vsfrc, []>;
|
||||
|
||||
// Round & Convert QP -> DP (dword[1] is set to zero)
|
||||
def XSCVQPDP : X_VT5_XO5_VB5 <63, 20, 836, "xscvqpdp" , []>;
|
||||
def XSCVQPDPO : X_VT5_XO5_VB5_Ro<63, 20, 836, "xscvqpdpo", []>;
|
||||
|
||||
// Truncate & Convert QP -> (Un)Signed (D)Word (dword[1] is set to zero)
|
||||
def XSCVQPSDZ : X_VT5_XO5_VB5<63, 25, 836, "xscvqpsdz", []>;
|
||||
def XSCVQPSWZ : X_VT5_XO5_VB5<63, 9, 836, "xscvqpswz", []>;
|
||||
def XSCVQPUDZ : X_VT5_XO5_VB5<63, 17, 836, "xscvqpudz", []>;
|
||||
def XSCVQPUWZ : X_VT5_XO5_VB5<63, 1, 836, "xscvqpuwz", []>;
|
||||
|
||||
// Convert (Un)Signed DWord -> QP
|
||||
def XSCVSDQP : X_VT5_XO5_VB5_TyVB<63, 10, 836, "xscvsdqp", vsfrc, []>;
|
||||
def XSCVUDQP : X_VT5_XO5_VB5_TyVB<63, 2, 836, "xscvudqp", vsfrc, []>;
|
||||
|
||||
//===--------------------------------------------------------------------===//
|
||||
// Round to Floating-Point Integer Instructions
|
||||
|
||||
// (Round &) Convert DP <-> HP
|
||||
// Note! xscvdphp's src and dest register both use the left 64 bits, so we use
|
||||
// vsfrc for src and dest register. xscvhpdp's src only use the left 16 bits,
|
||||
// but we still use vsfrc for it.
|
||||
def XSCVDPHP : XX2_XT6_XO5_XB6<60, 17, 347, "xscvdphp", vsfrc, []>;
|
||||
def XSCVHPDP : XX2_XT6_XO5_XB6<60, 16, 347, "xscvhpdp", vsfrc, []>;
|
||||
|
||||
// Vector HP -> SP
|
||||
def XVCVHPSP : XX2_XT6_XO5_XB6<60, 24, 475, "xvcvhpsp", vsrc, []>;
|
||||
def XVCVSPHP : XX2_XT6_XO5_XB6<60, 25, 475, "xvcvsphp", vsrc, []>;
|
||||
|
||||
class Z23_VT5_R1_VB5_RMC2_EX1<bits<6> opcode, bits<8> xo, bit ex, string opc,
|
||||
list<dag> pattern>
|
||||
: Z23Form_1<opcode, xo,
|
||||
(outs vrrc:$vT), (ins u1imm:$r, vrrc:$vB, u2imm:$rmc),
|
||||
!strconcat(opc, " $r, $vT, $vB, $rmc"), IIC_VecFP, pattern> {
|
||||
let RC = ex;
|
||||
}
|
||||
|
||||
// Round to Quad-Precision Integer [with Inexact]
|
||||
def XSRQPI : Z23_VT5_R1_VB5_RMC2_EX1<63, 5, 0, "xsrqpi" , []>;
|
||||
def XSRQPIX : Z23_VT5_R1_VB5_RMC2_EX1<63, 5, 1, "xsrqpix", []>;
|
||||
|
||||
// Round Quad-Precision to Double-Extended Precision (fp80)
|
||||
def XSRQPXP : Z23_VT5_R1_VB5_RMC2_EX1<63, 37, 0, "xsrqpxp", []>;
|
||||
} // end HasP9Vector
|
||||
|
|
|
|||
|
|
@ -70,6 +70,8 @@ void PPCSubtarget::initializeEnvironment() {
|
|||
HasP8Vector = false;
|
||||
HasP8Altivec = false;
|
||||
HasP8Crypto = false;
|
||||
HasP9Vector = false;
|
||||
HasP9Altivec = false;
|
||||
HasFCPSGN = false;
|
||||
HasFSQRT = false;
|
||||
HasFRE = false;
|
||||
|
|
|
|||
|
|
@ -92,6 +92,8 @@ protected:
|
|||
bool HasP8Vector;
|
||||
bool HasP8Altivec;
|
||||
bool HasP8Crypto;
|
||||
bool HasP9Vector;
|
||||
bool HasP9Altivec;
|
||||
bool HasFCPSGN;
|
||||
bool HasFSQRT;
|
||||
bool HasFRE, HasFRES, HasFRSQRTE, HasFRSQRTES;
|
||||
|
|
@ -230,6 +232,8 @@ public:
|
|||
bool hasP8Vector() const { return HasP8Vector; }
|
||||
bool hasP8Altivec() const { return HasP8Altivec; }
|
||||
bool hasP8Crypto() const { return HasP8Crypto; }
|
||||
bool hasP9Vector() const { return HasP9Vector; }
|
||||
bool hasP9Altivec() const { return HasP9Altivec; }
|
||||
bool hasMFOCRF() const { return HasMFOCRF; }
|
||||
bool hasISEL() const { return HasISEL; }
|
||||
bool hasPOPCNTD() const { return HasPOPCNTD; }
|
||||
|
|
|
|||
|
|
@ -0,0 +1,87 @@
|
|||
//===- README_P9.txt - Notes for improving Power9 code gen ----------------===//
|
||||
|
||||
TODO: Instructions Need Implement Instrinstics or Map to LLVM IR
|
||||
|
||||
Altivec:
|
||||
|
||||
VSX:
|
||||
|
||||
- QP Compare Ordered/Unordered: xscmpoqp xscmpuqp
|
||||
. ref: XSCMPUDP
|
||||
def XSCMPUDP : XX3Form_1<60, 35,
|
||||
(outs crrc:$crD), (ins vsfrc:$XA, vsfrc:$XB),
|
||||
"xscmpudp $crD, $XA, $XB", IIC_FPCompare, []>;
|
||||
|
||||
. No SDAG, intrinsic, builtin are required??
|
||||
Or llvm fcmp order/unorder compare??
|
||||
|
||||
- DP/QP Compare Exponents: xscmpexpdp xscmpexpqp
|
||||
. No SDAG, intrinsic, builtin are required?
|
||||
|
||||
- DP Compare ==, >=, >, !=: xscmpeqdp xscmpgedp xscmpgtdp xscmpnedp
|
||||
. I checked existing instruction "XSCMPUDP". They are different in target
|
||||
register. "XSCMPUDP" write to CR field, xscmp*dp write to VSX register
|
||||
|
||||
. Use instrinsic:
|
||||
(set i128:$XT, (int_ppc_vsx_xscmpeqdp f64:$XA, f64:$XB))
|
||||
(set i128:$XT, (int_ppc_vsx_xscmpgedp f64:$XA, f64:$XB))
|
||||
(set i128:$XT, (int_ppc_vsx_xscmpgtdp f64:$XA, f64:$XB))
|
||||
(set i128:$XT, (int_ppc_vsx_xscmpnedp f64:$XA, f64:$XB))
|
||||
|
||||
- Vector Compare Not Equal: xvcmpnedp xvcmpnedp. xvcmpnesp xvcmpnesp.
|
||||
. Similar to xvcmpeqdp:
|
||||
defm XVCMPEQDP : XX3Form_Rcr<60, 99,
|
||||
"xvcmpeqdp", "$XT, $XA, $XB", IIC_VecFPCompare,
|
||||
int_ppc_vsx_xvcmpeqdp, v2i64, v2f64>;
|
||||
|
||||
. So we should use "XX3Form_Rcr" to implement instrinsic
|
||||
|
||||
- Convert DP -> QP: xscvdpqp
|
||||
. Similar to XSCVDPSP:
|
||||
def XSCVDPSP : XX2Form<60, 265,
|
||||
(outs vsfrc:$XT), (ins vsfrc:$XB),
|
||||
"xscvdpsp $XT, $XB", IIC_VecFP, []>;
|
||||
. So, No SDAG, intrinsic, builtin are required??
|
||||
|
||||
- Round & Convert QP -> DP (dword[1] is set to zero): xscvqpdp xscvqpdpo
|
||||
. Similar to XSCVDPSP
|
||||
. No SDAG, intrinsic, builtin are required??
|
||||
|
||||
- Truncate & Convert QP -> (Un)Signed (D)Word (dword[1] is set to zero):
|
||||
xscvqpsdz xscvqpswz xscvqpudz xscvqpuwz
|
||||
. According to PowerISA_V3.0, these are similar to "XSCVDPSXDS", "XSCVDPSXWS",
|
||||
"XSCVDPUXDS", "XSCVDPUXWS"
|
||||
|
||||
. DAG patterns:
|
||||
(set f128:$XT, (PPCfctidz f128:$XB)) // xscvqpsdz
|
||||
(set f128:$XT, (PPCfctiwz f128:$XB)) // xscvqpswz
|
||||
(set f128:$XT, (PPCfctiduz f128:$XB)) // xscvqpudz
|
||||
(set f128:$XT, (PPCfctiwuz f128:$XB)) // xscvqpuwz
|
||||
|
||||
- Convert (Un)Signed DWord -> QP: xscvsdqp xscvudqp
|
||||
. Similar to XSCVSXDSP
|
||||
. (set f128:$XT, (PPCfcfids f64:$XB)) // xscvsdqp
|
||||
(set f128:$XT, (PPCfcfidus f64:$XB)) // xscvudqp
|
||||
|
||||
- (Round &) Convert DP <-> HP: xscvdphp xscvhpdp
|
||||
. Similar to XSCVDPSP
|
||||
. No SDAG, intrinsic, builtin are required??
|
||||
|
||||
- Vector HP -> SP: xvcvhpsp xvcvsphp
|
||||
. Similar to XVCVDPSP:
|
||||
def XVCVDPSP : XX2Form<60, 393,
|
||||
(outs vsrc:$XT), (ins vsrc:$XB),
|
||||
"xvcvdpsp $XT, $XB", IIC_VecFP, []>;
|
||||
. No SDAG, intrinsic, builtin are required??
|
||||
|
||||
- Round to Quad-Precision Integer: xsrqpi xsrqpix
|
||||
. These are combination of "XSRDPI", "XSRDPIC", "XSRDPIM", .., because you
|
||||
need to assign rounding mode in instruction
|
||||
. Provide builtin?
|
||||
(set f128:$vT, (int_ppc_vsx_xsrqpi f128:$vB))
|
||||
(set f128:$vT, (int_ppc_vsx_xsrqpix f128:$vB))
|
||||
|
||||
- Round Quad-Precision to Double-Extended Precision (fp80): xsrqpxp
|
||||
. Provide builtin?
|
||||
(set f128:$vT, (int_ppc_vsx_xsrqpxp f128:$vB))
|
||||
|
||||
|
|
@ -539,3 +539,89 @@
|
|||
|
||||
# CHECK: mtvsrwz 0, 3
|
||||
0x7c 0x03 0x01 0xe6
|
||||
|
||||
# Power9 Instructions:
|
||||
|
||||
# CHECK: xscmpoqp 6, 31, 27
|
||||
0xff 0x1f 0xd9 0x08
|
||||
|
||||
# CHECK: xscmpuqp 6, 31, 27
|
||||
0xff 0x1f 0xdd 0x08
|
||||
|
||||
# CHECK: xscmpexpdp 6, 63, 27
|
||||
0xf3 0x1f 0xd9 0xdc
|
||||
|
||||
# CHECK: xscmpexpqp 6, 31, 27
|
||||
0xff 0x1f 0xd9 0x48
|
||||
|
||||
# CHECK: xscmpeqdp 7, 63, 27
|
||||
0xf0 0xff 0xd8 0x1c
|
||||
|
||||
# CHECK: xscmpgedp 7, 63, 27
|
||||
0xf0 0xff 0xd8 0x9c
|
||||
|
||||
# CHECK: xscmpgtdp 7, 63, 27
|
||||
0xf0 0xff 0xd8 0x5c
|
||||
|
||||
# CHECK: xscmpnedp 7, 63, 27
|
||||
0xf0 0xff 0xd8 0xdc
|
||||
|
||||
# CHECK: xvcmpnedp 7, 63, 27
|
||||
0xf0 0xff 0xdb 0xdc
|
||||
|
||||
# CHECK: xvcmpnedp. 7, 63, 27
|
||||
0xf0 0xff 0xdf 0xdc
|
||||
|
||||
# CHECK: xvcmpnesp 7, 63, 27
|
||||
0xf0 0xff 0xda 0xdc
|
||||
|
||||
# CHECK: xvcmpnesp. 7, 63, 27
|
||||
0xf0 0xff 0xde 0xdc
|
||||
|
||||
# CHECK: xscvdpqp 7, 27
|
||||
0xfc 0xf6 0xde 0x88
|
||||
|
||||
# CHECK: xscvqpdp 7, 27
|
||||
0xfc 0xf4 0xde 0x88
|
||||
|
||||
# CHECK: xscvqpdpo 7, 27
|
||||
0xfc 0xf4 0xde 0x89
|
||||
|
||||
# CHECK: xscvqpsdz 7, 27
|
||||
0xfc 0xf9 0xde 0x88
|
||||
|
||||
# CHECK: xscvqpswz 7, 27
|
||||
0xfc 0xe9 0xde 0x88
|
||||
|
||||
# CHECK: xscvqpudz 7, 27
|
||||
0xfc 0xf1 0xde 0x88
|
||||
|
||||
# CHECK: xscvqpuwz 7, 27
|
||||
0xfc 0xe1 0xde 0x88
|
||||
|
||||
# CHECK: xscvsdqp 7, 27
|
||||
0xfc 0xea 0xde 0x88
|
||||
|
||||
# CHECK: xscvudqp 7, 27
|
||||
0xfc 0xe2 0xde 0x88
|
||||
|
||||
# CHECK: xscvdphp 7, 63
|
||||
0xf0 0xf1 0xfd 0x6e
|
||||
|
||||
# CHECK: xscvhpdp 7, 63
|
||||
0xf0 0xf0 0xfd 0x6e
|
||||
|
||||
# CHECK: xvcvhpsp 7, 63
|
||||
0xf0 0xf8 0xff 0x6e
|
||||
|
||||
# CHECK: xvcvsphp 7, 63
|
||||
0xf0 0xf9 0xff 0x6e
|
||||
|
||||
# CHECK: xsrqpi 1, 7, 27, 2
|
||||
0xfc 0xe1 0xdc 0x0a
|
||||
|
||||
# CHECK: xsrqpix 1, 7, 27, 2
|
||||
0xfc 0xe1 0xdc 0x0b
|
||||
|
||||
# CHECK: xsrqpxp 1, 7, 27, 2
|
||||
0xfc 0xe1 0xdc 0x4a
|
||||
|
|
|
|||
|
|
@ -547,3 +547,113 @@
|
|||
# CHECK-BE: mtvsrwz 0, 3 # encoding: [0x7c,0x03,0x01,0xe6]
|
||||
# CHECK-LE: mtvsrwz 0, 3 # encoding: [0xe6,0x01,0x03,0x7c]
|
||||
mtvsrwz 0, 3
|
||||
|
||||
# Power9 Instructions:
|
||||
|
||||
# Compare Ordered/Unordered
|
||||
# CHECK-BE: xscmpoqp 6, 31, 27 # encoding: [0xff,0x1f,0xd9,0x08]
|
||||
# CHECK-LE: xscmpoqp 6, 31, 27 # encoding: [0x08,0xd9,0x1f,0xff]
|
||||
xscmpoqp 6, 31, 27
|
||||
# CHECK-BE: xscmpuqp 6, 31, 27 # encoding: [0xff,0x1f,0xdd,0x08]
|
||||
# CHECK-LE: xscmpuqp 6, 31, 27 # encoding: [0x08,0xdd,0x1f,0xff]
|
||||
xscmpuqp 6, 31, 27
|
||||
|
||||
# Compare Exponents
|
||||
# CHECK-BE: xscmpexpdp 6, 63, 27 # encoding: [0xf3,0x1f,0xd9,0xdc]
|
||||
# CHECK-LE: xscmpexpdp 6, 63, 27 # encoding: [0xdc,0xd9,0x1f,0xf3]
|
||||
xscmpexpdp 6, 63, 27
|
||||
# CHECK-BE: xscmpexpqp 6, 31, 27 # encoding: [0xff,0x1f,0xd9,0x48]
|
||||
# CHECK-LE: xscmpexpqp 6, 31, 27 # encoding: [0x48,0xd9,0x1f,0xff]
|
||||
xscmpexpqp 6, 31, 27
|
||||
|
||||
# Compare ==, >=, >, !=
|
||||
# CHECK-BE: xscmpeqdp 7, 63, 27 # encoding: [0xf0,0xff,0xd8,0x1c]
|
||||
# CHECK-LE: xscmpeqdp 7, 63, 27 # encoding: [0x1c,0xd8,0xff,0xf0]
|
||||
xscmpeqdp 7, 63, 27
|
||||
# CHECK-BE: xscmpgedp 7, 63, 27 # encoding: [0xf0,0xff,0xd8,0x9c]
|
||||
# CHECK-LE: xscmpgedp 7, 63, 27 # encoding: [0x9c,0xd8,0xff,0xf0]
|
||||
xscmpgedp 7, 63, 27
|
||||
# CHECK-BE: xscmpgtdp 7, 63, 27 # encoding: [0xf0,0xff,0xd8,0x5c]
|
||||
# CHECK-LE: xscmpgtdp 7, 63, 27 # encoding: [0x5c,0xd8,0xff,0xf0]
|
||||
xscmpgtdp 7, 63, 27
|
||||
# CHECK-BE: xscmpnedp 7, 63, 27 # encoding: [0xf0,0xff,0xd8,0xdc]
|
||||
# CHECK-LE: xscmpnedp 7, 63, 27 # encoding: [0xdc,0xd8,0xff,0xf0]
|
||||
xscmpnedp 7, 63, 27
|
||||
|
||||
# Vector Compare Not Equal
|
||||
# CHECK-BE: xvcmpnedp 7, 63, 27 # encoding: [0xf0,0xff,0xdb,0xdc]
|
||||
# CHECK-LE: xvcmpnedp 7, 63, 27 # encoding: [0xdc,0xdb,0xff,0xf0]
|
||||
xvcmpnedp 7, 63, 27
|
||||
# CHECK-BE: xvcmpnedp. 7, 63, 27 # encoding: [0xf0,0xff,0xdf,0xdc]
|
||||
# CHECK-LE: xvcmpnedp. 7, 63, 27 # encoding: [0xdc,0xdf,0xff,0xf0]
|
||||
xvcmpnedp. 7, 63, 27
|
||||
# CHECK-BE: xvcmpnesp 7, 63, 27 # encoding: [0xf0,0xff,0xda,0xdc]
|
||||
# CHECK-LE: xvcmpnesp 7, 63, 27 # encoding: [0xdc,0xda,0xff,0xf0]
|
||||
xvcmpnesp 7, 63, 27
|
||||
# CHECK-BE: xvcmpnesp. 7, 63, 27 # encoding: [0xf0,0xff,0xde,0xdc]
|
||||
# CHECK-LE: xvcmpnesp. 7, 63, 27 # encoding: [0xdc,0xde,0xff,0xf0]
|
||||
xvcmpnesp. 7, 63, 27
|
||||
|
||||
# Convert DP -> QP
|
||||
# CHECK-BE: xscvdpqp 7, 27 # encoding: [0xfc,0xf6,0xde,0x88]
|
||||
# CHECK-LE: xscvdpqp 7, 27 # encoding: [0x88,0xde,0xf6,0xfc]
|
||||
xscvdpqp 7, 27
|
||||
|
||||
# Round & Convert QP -> DP
|
||||
# CHECK-BE: xscvqpdp 7, 27 # encoding: [0xfc,0xf4,0xde,0x88]
|
||||
# CHECK-LE: xscvqpdp 7, 27 # encoding: [0x88,0xde,0xf4,0xfc]
|
||||
xscvqpdp 7, 27
|
||||
# CHECK-BE: xscvqpdpo 7, 27 # encoding: [0xfc,0xf4,0xde,0x89]
|
||||
# CHECK-LE: xscvqpdpo 7, 27 # encoding: [0x89,0xde,0xf4,0xfc]
|
||||
xscvqpdpo 7, 27
|
||||
|
||||
# Truncate & Convert QP -> (Un)Signed (D)Word
|
||||
# CHECK-BE: xscvqpsdz 7, 27 # encoding: [0xfc,0xf9,0xde,0x88]
|
||||
# CHECK-LE: xscvqpsdz 7, 27 # encoding: [0x88,0xde,0xf9,0xfc]
|
||||
xscvqpsdz 7, 27
|
||||
# CHECK-BE: xscvqpswz 7, 27 # encoding: [0xfc,0xe9,0xde,0x88]
|
||||
# CHECK-LE: xscvqpswz 7, 27 # encoding: [0x88,0xde,0xe9,0xfc]
|
||||
xscvqpswz 7, 27
|
||||
# CHECK-BE: xscvqpudz 7, 27 # encoding: [0xfc,0xf1,0xde,0x88]
|
||||
# CHECK-LE: xscvqpudz 7, 27 # encoding: [0x88,0xde,0xf1,0xfc]
|
||||
xscvqpudz 7, 27
|
||||
# CHECK-BE: xscvqpuwz 7, 27 # encoding: [0xfc,0xe1,0xde,0x88]
|
||||
# CHECK-LE: xscvqpuwz 7, 27 # encoding: [0x88,0xde,0xe1,0xfc]
|
||||
xscvqpuwz 7, 27
|
||||
|
||||
# Convert (Un)Signed DWord -> QP
|
||||
# CHECK-BE: xscvsdqp 7, 27 # encoding: [0xfc,0xea,0xde,0x88]
|
||||
# CHECK-LE: xscvsdqp 7, 27 # encoding: [0x88,0xde,0xea,0xfc]
|
||||
xscvsdqp 7, 27
|
||||
# CHECK-BE: xscvudqp 7, 27 # encoding: [0xfc,0xe2,0xde,0x88]
|
||||
# CHECK-LE: xscvudqp 7, 27 # encoding: [0x88,0xde,0xe2,0xfc]
|
||||
xscvudqp 7, 27
|
||||
|
||||
# (Round &) Convert DP <-> HP
|
||||
# CHECK-BE: xscvdphp 7, 63 # encoding: [0xf0,0xf1,0xfd,0x6e]
|
||||
# CHECK-LE: xscvdphp 7, 63 # encoding: [0x6e,0xfd,0xf1,0xf0]
|
||||
xscvdphp 7, 63
|
||||
# CHECK-BE: xscvhpdp 7, 63 # encoding: [0xf0,0xf0,0xfd,0x6e]
|
||||
# CHECK-LE: xscvhpdp 7, 63 # encoding: [0x6e,0xfd,0xf0,0xf0]
|
||||
xscvhpdp 7, 63
|
||||
|
||||
# HP -> SP
|
||||
# CHECK-BE: xvcvhpsp 7, 63 # encoding: [0xf0,0xf8,0xff,0x6e]
|
||||
# CHECK-LE: xvcvhpsp 7, 63 # encoding: [0x6e,0xff,0xf8,0xf0]
|
||||
xvcvhpsp 7, 63
|
||||
# CHECK-BE: xvcvsphp 7, 63 # encoding: [0xf0,0xf9,0xff,0x6e]
|
||||
# CHECK-LE: xvcvsphp 7, 63 # encoding: [0x6e,0xff,0xf9,0xf0]
|
||||
xvcvsphp 7, 63
|
||||
|
||||
# Round to Quad-Precision Integer [with Inexact]
|
||||
# CHECK-BE: xsrqpi 1, 7, 27, 2 # encoding: [0xfc,0xe1,0xdc,0x0a]
|
||||
# CHECK-LE: xsrqpi 1, 7, 27, 2 # encoding: [0x0a,0xdc,0xe1,0xfc]
|
||||
xsrqpi 1, 7, 27, 2
|
||||
# CHECK-BE: xsrqpix 1, 7, 27, 2 # encoding: [0xfc,0xe1,0xdc,0x0b]
|
||||
# CHECK-LE: xsrqpix 1, 7, 27, 2 # encoding: [0x0b,0xdc,0xe1,0xfc]
|
||||
xsrqpix 1, 7, 27, 2
|
||||
|
||||
# Round Quad-Precision to Double-Extended Precision
|
||||
# CHECK-BE: xsrqpxp 1, 7, 27, 2 # encoding: [0xfc,0xe1,0xdc,0x4a]
|
||||
# CHECK-LE: xsrqpxp 1, 7, 27, 2 # encoding: [0x4a,0xdc,0xe1,0xfc]
|
||||
xsrqpxp 1, 7, 27, 2
|
||||
|
|
|
|||
Loading…
Reference in New Issue