[llvm] [AMDGPU][True16][MC] true16 for v_cmpx_lt_f16 (PR #122936)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Jan 14 12:51:04 PST 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Brox Chen (broxigarchen)
<details>
<summary>Changes</summary>
True16 format for v_cmpx_lt_f16. Update VOPCX t16 and fake16 pseudo.
---
Patch is 174.96 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/122936.diff
29 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/VOPCInstructions.td (+103-26)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16_from_vopcx.s (+37-28)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8_from_vopcx.s (+17-8)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop3_from_vopcx.s (+10-4)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vopcx.s (+45-30)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vopcx_dpp16.s (+37-28)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vopcx_dpp8.s (+15-6)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vopcx_t16_err.s (+31-12)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vopcx_t16_promote.s (+31-12)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3cx.s (+10-4)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3cx_dpp16.s (+41-32)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3cx_dpp8.s (+21-12)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vopcx.s (+42-30)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vopcx_dpp16.s (+34-28)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vopcx_dpp8.s (+12-6)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vopcx_t16_err.s (+31-12)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vopcx_t16_promote.s (+31-12)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp16_from_vopcx.txt (+44-18)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp8_from_vopcx.txt (+24-8)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_from_vopcx.txt (+16-6)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vopcx.txt (+74-19)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vopcx_dpp16.txt (+56-18)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vopcx_dpp8.txt (+32-6)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3cx.txt (+26-6)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3cx_dpp16.txt (+104-19)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3cx_dpp8.txt (+29-9)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vopcx.txt (+66-19)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vopcx_dpp16.txt (+48-18)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vopcx_dpp8.txt (+24-6)
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/VOPCInstructions.td b/llvm/lib/Target/AMDGPU/VOPCInstructions.td
index 14e34c9e00ec6f..8542383a090b23 100644
--- a/llvm/lib/Target/AMDGPU/VOPCInstructions.td
+++ b/llvm/lib/Target/AMDGPU/VOPCInstructions.td
@@ -153,8 +153,7 @@ class VOPC_NoSdst_Profile<list<SchedReadWrite> sched, ValueType vt0,
let InsSDWA = (ins Src0ModSDWA:$src0_modifiers, Src0SDWA:$src0,
Src1ModSDWA:$src1_modifiers, Src1SDWA:$src1,
src0_sel:$src0_sel, src1_sel:$src1_sel);
- let AsmVOP3Base = !if(Src0VT.isFP, "$src0_modifiers, $src1_modifiers$clamp",
- "$src0, $src1");
+ let HasDst = 0;
let AsmSDWA9 = "$src0_modifiers, $src1_modifiers $src0_sel $src1_sel";
let EmitDst = 0;
}
@@ -164,23 +163,53 @@ multiclass VOPC_NoSdst_Profile_t16<list<SchedReadWrite> sched, ValueType vt0, Va
def _t16 : VOPC_NoSdst_Profile<sched, vt0, vt1> {
let IsTrue16 = 1;
let IsRealTrue16 = 1;
- let Src1RC32 = getVregSrcForVT<Src1VT, 1/*IsTrue16*/, 1/*IsFake16*/>.ret;
- let Src0DPP = getVregSrcForVT<Src0VT, 1/*IsTrue16*/, 1/*IsFake16*/>.ret;
- let Src1DPP = getVregSrcForVT<Src1VT, 1/*IsTrue16*/, 1/*IsFake16*/>.ret;
- let Src2DPP = getVregSrcForVT<Src2VT, 1/*IsTrue16*/, 1/*IsFake16*/>.ret;
- let Src0ModDPP = getSrcModDPP_t16<Src0VT>.ret;
- let Src1ModDPP = getSrcModDPP_t16<Src1VT>.ret;
- let Src2ModDPP = getSrcModDPP_t16<Src2VT>.ret;
+ let HasOpSel = 1;
+ let HasModifiers = 1; // All instructions at least have OpSel
+ let Src0RC32 = getVOPSrc0ForVT<Src0VT, 1/*IsTrue16*/, 0/*IsFake16*/>.ret;
+ let Src1RC32 = getVregSrcForVT<Src1VT, 1/*IsTrue16*/, 0/*IsFake16*/>.ret;
+ let Src0DPP = getVregSrcForVT<Src0VT, 1/*IsTrue16*/, 0/*IsFake16*/>.ret;
+ let Src1DPP = getVregSrcForVT<Src1VT, 1/*IsTrue16*/, 0/*IsFake16*/>.ret;
+ let Src2DPP = getVregSrcForVT<Src2VT, 1/*IsTrue16*/, 0/*IsFake16*/>.ret;
+ let Src0ModDPP = getSrcModDPP_t16<Src0VT, 0/*IsFake16*/>.ret;
+ let Src1ModDPP = getSrcModDPP_t16<Src1VT, 0/*IsFake16*/>.ret;
+ let Src2ModDPP = getSrcModDPP_t16<Src2VT, 0/*IsFake16*/>.ret;
+ let Src0VOP3DPP = VGPRSrc_16;
+ let Src1VOP3DPP = getVOP3DPPSrcForVT<Src1VT, 0/*IsFake16*/>.ret;
+ let Src2VOP3DPP = getVOP3DPPSrcForVT<Src2VT, 0/*IsFake16*/>.ret;
+
+ let Src0RC64 = getVOP3SrcForVT<Src0VT, 1/*IsTrue16*/>.ret;
+ let Src1RC64 = getVOP3SrcForVT<Src1VT, 1/*IsTrue16*/>.ret;
+ let Src2RC64 = getVOP3SrcForVT<Src2VT, 1/*IsTrue16*/>.ret;
+ let Src0Mod = getSrc0Mod<Src0VT, DstVT, 1/*IsTrue16*/, 0/*IsFake16*/>.ret;
+ let Src1Mod = getSrcMod<Src1VT, 1/*IsTrue16*/, 0/*IsFake16*/>.ret;
+ let Src2Mod = getSrcMod<Src2VT, 1/*IsTrue16*/, 0/*IsFake16*/>.ret;
+ let Src0ModVOP3DPP = getSrc0ModVOP3DPP<Src0VT, DstVT, 0/*IsFake16*/>.ret;
+ let Src1ModVOP3DPP = getSrcModVOP3DPP<Src1VT, 0/*IsFake16*/>.ret;
+ let Src2ModVOP3DPP = getSrcModVOP3DPP<Src2VT, 0/*IsFake16*/>.ret;
}
def _fake16 : VOPC_NoSdst_Profile<sched, vt0, vt1> {
let IsTrue16 = 1;
+ let Src0RC32 = getVOPSrc0ForVT<Src0VT, 1/*IsTrue16*/, 1/*IsFake16*/>.ret;
let Src1RC32 = getVregSrcForVT<Src1VT, 1/*IsTrue16*/, 1/*IsFake16*/>.ret;
let Src0DPP = getVregSrcForVT<Src0VT, 1/*IsTrue16*/, 1/*IsFake16*/>.ret;
let Src1DPP = getVregSrcForVT<Src1VT, 1/*IsTrue16*/, 1/*IsFake16*/>.ret;
let Src2DPP = getVregSrcForVT<Src2VT, 1/*IsTrue16*/, 1/*IsFake16*/>.ret;
- let Src0ModDPP = getSrcModDPP_t16<Src0VT>.ret;
- let Src1ModDPP = getSrcModDPP_t16<Src1VT>.ret;
- let Src2ModDPP = getSrcModDPP_t16<Src2VT>.ret;
+ let Src0ModDPP = getSrcModDPP_t16<Src0VT, 1/*IsFake16*/>.ret;
+ let Src1ModDPP = getSrcModDPP_t16<Src1VT, 1/*IsFake16*/>.ret;
+ let Src2ModDPP = getSrcModDPP_t16<Src2VT, 1/*IsFake16*/>.ret;
+ let Src0VOP3DPP = VGPRSrc_32;
+ let Src1VOP3DPP = getVOP3DPPSrcForVT<Src1VT, 1/*IsFake16*/>.ret;
+ let Src2VOP3DPP = getVOP3DPPSrcForVT<Src2VT, 1/*IsFake16*/>.ret;
+
+ let Src0RC64 = getVOP3SrcForVT<Src0VT, 0/*IsTrue16*/>.ret;
+ let Src1RC64 = getVOP3SrcForVT<Src1VT, 0/*IsTrue16*/>.ret;
+ let Src2RC64 = getVOP3SrcForVT<Src2VT, 0/*IsTrue16*/>.ret;
+ let Src0Mod = getSrc0Mod<Src0VT, DstVT, 1/*IsTrue16*/, 1/*IsFake16*/>.ret;
+ let Src1Mod = getSrcMod<Src1VT, 0/*IsTrue16*/, 1/*IsFake16*/>.ret;
+ let Src2Mod = getSrcMod<Src2VT, 0/*IsTrue16*/, 1/*IsFake16*/>.ret;
+ let Src0ModVOP3DPP = getSrc0ModVOP3DPP<Src0VT, DstVT, 1/*IsFake16*/>.ret;
+ let Src1ModVOP3DPP = getSrcModVOP3DPP<Src1VT, 1/*IsFake16*/>.ret;
+ let Src2ModVOP3DPP = getSrcModVOP3DPP<Src2VT, 1/*IsFake16*/>.ret;
}
}
@@ -1419,6 +1448,13 @@ class VOPC64_DPP16_Dst_t16<bits<10> op, VOP_DPP_Pseudo ps,
let Inst{14} = 0;
}
+class VOPC64_DPP16_NoDst_t16<bits<10> op, VOP_DPP_Pseudo ps,
+ string opName = ps.OpName>
+ : VOPC64_DPP<ps, opName>, VOP3_DPP_Enc_t16<op, ps.Pfl, 1> {
+ let Inst{7-0} = ? ;
+ let Inst{14} = 0;
+}
+
class VOPC64_DPP8<VOP_Pseudo ps, string opName = ps.OpName>
: VOP3_DPP8_Base<opName, ps.Pfl> {
Instruction Opcode = !cast<Instruction>(NAME);
@@ -1452,6 +1488,13 @@ class VOPC64_DPP8_Dst_t16<bits<10> op, VOP_Pseudo ps, string opName = ps.OpName>
let Constraints = "";
}
+class VOPC64_DPP8_NoDst_t16<bits<10> op, VOP_Pseudo ps, string opName = ps.OpName>
+ : VOPC64_DPP8<ps, opName>, VOP3_DPP8_Enc_t16<op, ps.Pfl> {
+ let Inst{7-0} = ? ;
+ let Inst{14} = 0;
+ let Constraints = "";
+}
+
//===----------------------------------------------------------------------===//
// Target-specific instruction encodings.
//===----------------------------------------------------------------------===//
@@ -1619,7 +1662,7 @@ multiclass VOPCX_Real<GFXGen Gen, bits<9> op> {
# " " # ps32.AsmOperands;
}
def _e64#Gen.Suffix :
- VOP3_Real<ps64, Gen.Subtarget>,
+ VOP3_Real_Gen<ps64, Gen>,
VOP3a_gfx11_gfx12<{0, op}, ps64.Pfl> {
let Inst{7-0} = ?; // sdst
let AsmString = !subst("_nosdst", "", ps64.Mnemonic)
@@ -1677,11 +1720,22 @@ multiclass VOPCX_Real_with_name<GFXGen Gen, bits<9> op, string OpName,
VOPCe<op{7-0}> {
let AsmString = asm_name # "{_e32} " # ps32.AsmOperands;
}
- def _e64#Gen.Suffix
- : VOP3_Real_Gen<ps64, Gen, asm_name>,
- VOP3a_gfx11_gfx12<{0, op}, ps64.Pfl> {
- let Inst{7-0} = ? ; // sdst
- let AsmString = asm_name # "{_e64} " # ps64.AsmOperands;
+
+ if ps64.Pfl.IsRealTrue16 then {
+ def _e64#Gen.Suffix
+ : VOP3_Real_Gen<ps64, Gen, asm_name>,
+ VOP3e_t16_gfx11_gfx12<{0, op}, ps64.Pfl> {
+ let Inst{7-0} = ? ; // sdst
+ let Inst{14} = 0;
+ let AsmString = asm_name # "{_e64} " # ps64.AsmOperands;
+ }
+ } else {
+ def _e64#Gen.Suffix
+ : VOP3_Real_Gen<ps64, Gen, asm_name>,
+ VOP3a_gfx11_gfx12<{0, op}, ps64.Pfl> {
+ let Inst{7-0} = ? ; // sdst
+ let AsmString = asm_name # "{_e64} " # ps64.AsmOperands;
+ }
}
defm : VOPCXInstAliases<OpName, !substr(Gen.Suffix, 1), NAME, asm_name>;
@@ -1695,14 +1749,25 @@ multiclass VOPCX_Real_with_name<GFXGen Gen, bits<9> op, string OpName,
if ps64.Pfl.HasExtVOP3DPP then {
defvar psDPP = !cast<VOP_DPP_Pseudo>(OpName#"_nosdst_e64"#"_dpp");
defvar AsmDPP = ps64.Pfl.AsmVOP3DPP16;
- def _e64_dpp#Gen.Suffix
- : VOPC64_DPP16_NoDst<{0, op}, psDPP, asm_name>,
- SIMCInstr<psDPP.PseudoInstr, Gen.Subtarget> {
- let AsmString = asm_name # "{_e64_dpp} " # AsmDPP;
- }
defvar AsmDPP8 = ps64.Pfl.AsmVOP3DPP8;
- def _e64_dpp8#Gen.Suffix : VOPC64_DPP8_NoDst<{0, op}, ps64, asm_name> {
- let AsmString = asm_name # "{_e64_dpp} " # AsmDPP8;
+ if ps64.Pfl.IsRealTrue16 then {
+ def _e64_dpp#Gen.Suffix
+ : VOPC64_DPP16_NoDst_t16<{0, op}, psDPP, asm_name>,
+ SIMCInstr<psDPP.PseudoInstr, Gen.Subtarget> {
+ let AsmString = asm_name # "{_e64_dpp} " # AsmDPP;
+ }
+ def _e64_dpp8#Gen.Suffix : VOPC64_DPP8_NoDst_t16<{0, op}, ps64, asm_name> {
+ let AsmString = asm_name # "{_e64_dpp} " # AsmDPP8;
+ }
+ } else {
+ def _e64_dpp#Gen.Suffix
+ : VOPC64_DPP16_NoDst<{0, op}, psDPP, asm_name>,
+ SIMCInstr<psDPP.PseudoInstr, Gen.Subtarget> {
+ let AsmString = asm_name # "{_e64_dpp} " # AsmDPP;
+ }
+ def _e64_dpp8#Gen.Suffix : VOPC64_DPP8_NoDst<{0, op}, ps64, asm_name> {
+ let AsmString = asm_name # "{_e64_dpp} " # AsmDPP8;
+ }
}
} // End if ps64.Pfl.HasExtVOP3DPP
} // End DecoderNamespace
@@ -1756,11 +1821,23 @@ multiclass VOPCX_Real_t16_gfx11<bits<9> op, string asm_name,
string OpName = NAME, string pseudo_mnemonic = ""> :
VOPCX_Real_t16<GFX11Gen, op, asm_name, OpName, pseudo_mnemonic>;
+multiclass VOPCX_Real_t16_and_fake16_gfx11<bits<9> op, string asm_name,
+ string OpName = NAME, string pseudo_mnemonic = ""> {
+ defm _t16: VOPCX_Real_t16_gfx11<op, asm_name, OpName#"_t16", pseudo_mnemonic>;
+ defm _fake16: VOPCX_Real_t16_gfx11<op, asm_name, OpName#"_fake16", pseudo_mnemonic>;
+}
+
multiclass VOPCX_Real_t16_gfx11_gfx12<bits<9> op, string asm_name,
string OpName = NAME, string pseudo_mnemonic = ""> :
VOPCX_Real_t16<GFX11Gen, op, asm_name, OpName, pseudo_mnemonic>,
VOPCX_Real_t16<GFX12Gen, op, asm_name, OpName, pseudo_mnemonic>;
+multiclass VOPCX_Real_t16_and_fake16_gfx11_gfx12<bits<9> op, string asm_name,
+ string OpName = NAME, string pseudo_mnemonic = ""> {
+ defm _t16: VOPCX_Real_t16_gfx11_gfx12<op, asm_name, OpName#"_t16", pseudo_mnemonic>;
+ defm _fake16: VOPCX_Real_t16_gfx11_gfx12<op, asm_name, OpName#"_fake16", pseudo_mnemonic>;
+}
+
defm V_CMP_F_F16_fake16 : VOPC_Real_t16_gfx11<0x000, "v_cmp_f_f16">;
defm V_CMP_LT_F16 : VOPC_Real_t16_and_fake16_gfx11_gfx12<0x001, "v_cmp_lt_f16">;
defm V_CMP_EQ_F16_fake16 : VOPC_Real_t16_gfx11_gfx12<0x002, "v_cmp_eq_f16">;
@@ -1848,7 +1925,7 @@ defm V_CMP_CLASS_F32 : VOPC_Real_gfx11_gfx12<0x07e>;
defm V_CMP_CLASS_F64 : VOPC_Real_gfx11_gfx12<0x07f>;
defm V_CMPX_F_F16_fake16 : VOPCX_Real_t16_gfx11<0x080, "v_cmpx_f_f16">;
-defm V_CMPX_LT_F16_fake16 : VOPCX_Real_t16_gfx11_gfx12<0x081, "v_cmpx_lt_f16">;
+defm V_CMPX_LT_F16 : VOPCX_Real_t16_and_fake16_gfx11_gfx12<0x081, "v_cmpx_lt_f16">;
defm V_CMPX_EQ_F16_fake16 : VOPCX_Real_t16_gfx11_gfx12<0x082, "v_cmpx_eq_f16">;
defm V_CMPX_LE_F16_fake16 : VOPCX_Real_t16_gfx11_gfx12<0x083, "v_cmpx_le_f16">;
defm V_CMPX_GT_F16_fake16 : VOPCX_Real_t16_gfx11_gfx12<0x084, "v_cmpx_gt_f16">;
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16_from_vopcx.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16_from_vopcx.s
index 462ad7ba6516d5..60ec94446235ed 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16_from_vopcx.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16_from_vopcx.s
@@ -1347,47 +1347,56 @@ v_cmpx_lg_f32_e64_dpp -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctr
v_cmpx_lg_f32_e64_dpp -|v255|, -|v255| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX11: v_cmpx_lg_f32_e64_dpp -|v255|, -|v255| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0x7e,0x83,0x95,0xd4,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x05,0x30]
-v_cmpx_lt_f16_e64_dpp v1, v2 quad_perm:[3,2,1,0]
-// GFX11: v_cmpx_lt_f16_e64_dpp v1, v2 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
+v_cmpx_lt_f16_e64_dpp v1.l, v2.l quad_perm:[3,2,1,0]
+// GFX11: v_cmpx_lt_f16_e64_dpp v1.l, v2.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
-v_cmpx_lt_f16_e64_dpp v1, v2 quad_perm:[0,1,2,3]
-// GFX11: v_cmpx_lt_f16_e64_dpp v1, v2 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0xe4,0x00,0xff]
+v_cmpx_lt_f16_e64_dpp v1.l, v2.l quad_perm:[0,1,2,3]
+// GFX11: v_cmpx_lt_f16_e64_dpp v1.l, v2.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0xe4,0x00,0xff]
-v_cmpx_lt_f16_e64_dpp v1, v2 row_mirror
-// GFX11: v_cmpx_lt_f16_e64_dpp v1, v2 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x40,0x01,0xff]
+v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_mirror
+// GFX11: v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x40,0x01,0xff]
-v_cmpx_lt_f16_e64_dpp v1, v2 row_half_mirror
-// GFX11: v_cmpx_lt_f16_e64_dpp v1, v2 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x41,0x01,0xff]
+v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_half_mirror
+// GFX11: v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x41,0x01,0xff]
-v_cmpx_lt_f16_e64_dpp v1, v2 row_shl:1
-// GFX11: v_cmpx_lt_f16_e64_dpp v1, v2 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x01,0x01,0xff]
+v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_shl:1
+// GFX11: v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x01,0x01,0xff]
-v_cmpx_lt_f16_e64_dpp v1, v2 row_shl:15
-// GFX11: v_cmpx_lt_f16_e64_dpp v1, v2 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x0f,0x01,0xff]
+v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_shl:15
+// GFX11: v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x0f,0x01,0xff]
-v_cmpx_lt_f16_e64_dpp v1, v2 row_shr:1
-// GFX11: v_cmpx_lt_f16_e64_dpp v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x11,0x01,0xff]
+v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_shr:1
+// GFX11: v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x11,0x01,0xff]
-v_cmpx_lt_f16_e64_dpp v1, v2 row_shr:15
-// GFX11: v_cmpx_lt_f16_e64_dpp v1, v2 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x1f,0x01,0xff]
+v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_shr:15
+// GFX11: v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x1f,0x01,0xff]
-v_cmpx_lt_f16_e64_dpp v1, v2 row_ror:1
-// GFX11: v_cmpx_lt_f16_e64_dpp v1, v2 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x21,0x01,0xff]
+v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_ror:1
+// GFX11: v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x21,0x01,0xff]
-v_cmpx_lt_f16_e64_dpp v1, v2 row_ror:15
-// GFX11: v_cmpx_lt_f16_e64_dpp v1, v2 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x2f,0x01,0xff]
+v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_ror:15
+// GFX11: v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x2f,0x01,0xff]
-v_cmpx_lt_f16_e64_dpp v1, v2 row_share:0 row_mask:0xf bank_mask:0xf
-// GFX11: v_cmpx_lt_f16_e64_dpp v1, v2 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x50,0x01,0xff]
+v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_share:0 row_mask:0xf bank_mask:0xf
+// GFX11: v_cmpx_lt_f16_e64_dpp v1.l, v2.l row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x81,0xd4,0xfa,0x04,0x02,0x00,0x01,0x50,0x01,0xff]
-v_cmpx_lt_f16_e64_dpp |v1|, -v2 row_share:15 row_mask:0x0 bank_mask:0x1
-// GFX11: v_cmpx_lt_f16_e64_dpp |v1|, -v2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x7e,0x01,0x81,0xd4,0xfa,0x04,0x02,0x40,0x01,0x5f,0x01,0x01]
+v_cmpx_lt_f16_e64_dpp |v1.l|, -v2.l row_share:15 row_mask:0x0 bank_mask:0x1
+// GFX11: v_cmpx_lt_f16_e64_dpp |v1.l|, -v2.l row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x7e,0x01,0x81,0xd4,0xfa,0x04,0x02,0x40,0x01,0x5f,0x01,0x01]
-v_cmpx_lt_f16_e64_dpp -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
-// GFX11: v_cmpx_lt_f16_e64_dpp -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x7e,0x02,0x81,0xd4,0xfa,0x04,0x02,0x20,0x01,0x60,0x09,0x13]
+v_cmpx_lt_f16_e64_dpp -v1.l, |v2.l| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
+// GFX11: v_cmpx_lt_f16_e64_dpp -v1.l, |v2.l| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x7e,0x02,0x81,0xd4,0xfa,0x04,0x02,0x20,0x01,0x60,0x09,0x13]
-v_cmpx_lt_f16_e64_dpp -|v255|, -|v255| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
-// GFX11: v_cmpx_lt_f16_e64_dpp -|v255|, -|v255| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0x7e,0x83,0x81,0xd4,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x05,0x30]
+v_cmpx_lt_f16_e64_dpp -|v255.l|, -|v255.l| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
+// GFX11: v_cmpx_lt_f16_e64_dpp -|v255.l|, -|v255.l| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0x7e,0x83,0x81,0xd4,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x05,0x30]
+
+v_cmpx_lt_f16_e64_dpp |v1.h|, -v2.h row_share:15 row_mask:0x0 bank_mask:0x1
+// GFX11: v_cmpx_lt_f16_e64_dpp |v1.h|, -v2.h op_sel:[1,1] row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x7e,0x19,0x81,0xd4,0xfa,0x04,0x02,0x40,0x01,0x5f,0x01,0x01]
+
+v_cmpx_lt_f16_e64_dpp -v1.h, |v2.l| row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
+// GFX11: v_cmpx_lt_f16_e64_dpp -v1.h, |v2.l| op_sel:[1,0] row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x7e,0x0a,0x81,0xd4,0xfa,0x04,0x02,0x20,0x01,0x60,0x09,0x13]
+
+v_cmpx_lt_f16_e64_dpp -|v255.l|, -|v255.h| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
+// GFX11: v_cmpx_lt_f16_e64_dpp -|v255.l|, -|v255.h| op_sel:[0,1] clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0x7e,0x93,0x81,0xd4,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x05,0x30]
v_cmpx_lt_f32_e64_dpp v1, v2 quad_perm:[3,2,1,0]
// GFX11: v_cmpx_lt_f32_e64_dpp v1, v2 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x7e,0x00,0x91,0xd4,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8_from_vopcx.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8_from_vopcx.s
index 46f1db837b0dd8..fb2b28874bd04f 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8_from_vopcx.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8_from_vopcx.s
@@ -326,17 +326,26 @@ v_cmpx_lg_f32_e64_dpp -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] fi:1
v_cmpx_lg_f32_e64_dpp -|v255|, -|v255| clamp dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX11: v_cmpx_lg_f32_e64_dpp -|v255|, -|v255| clamp dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0x7e,0x83,0x95,0xd4,0xe9,0xfe,0x03,0x60,0xff,0x00,0x00,0x00]
-v_cmpx_lt_f16_e64_dpp v1, v2 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_cmpx_lt_f16_e64_dpp v1, v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x7e,0x00,0x81,0xd4,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05]
+v_cmpx_lt_f16_e64_dpp v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_cmpx_lt_f16_e64_dpp v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x7e,0x00,0x81,0xd4,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05]
-v_cmpx_lt_f16_e64_dpp |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_cmpx_lt_f16_e64_dpp |v1|, -v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x7e,0x01,0x81,0xd4,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05]
+v_cmpx_lt_f16_e64_dpp |v1.l|, -v2.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_cmpx_lt_f16_e64_dpp |v1.l|, -v2.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x7e,0x01,0x81,0xd4,0xe9,0x04,0x02,0x40,0x01,0x77,0x39,0x05]
-v_cmpx_lt_f16_e64_dpp -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] fi:1
-// GFX11: v_cmpx_lt_f16_e64_dpp -v1, |v2| dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x7e,0x02,0x81,0xd4,0xea,0x04,0x02,0x20,0x01,0x77,0x39,0x05]
+v_cmpx_lt_f16_e64_dpp -v1.l, |v2.l| dpp8:[7,6,5,4,3,2,1,0] fi:1
+// GFX11: v_cmpx_lt_f16_e64_dpp -v1.l, |v2.l| dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x7e,0x02,0x81,0xd4,0xea,0x04,0x02,0x20,0x01,0x77,0x39,0x05]
-v_cmpx_lt_f16_e64_dpp -|v255|, -|v255| clamp dpp8:[0,0,0,0,0,0,0,0] fi:0
-// GFX11: v_cmpx_lt_f16_e64_dpp -|v25...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/122936
More information about the llvm-commits
mailing list