[llvm] [AMDGPU][True16][MC] true16 for v_cos_f16 (PR #120639)
Brox Chen via llvm-commits
llvm-commits at lists.llvm.org
Fri Jan 3 08:46:40 PST 2025
https://github.com/broxigarchen updated https://github.com/llvm/llvm-project/pull/120639
>From d696c9c3818604a914352e3fcbbf6b6c9a7ed4dc Mon Sep 17 00:00:00 2001
From: guochen2 <guochen2 at amd.com>
Date: Thu, 19 Dec 2024 16:26:07 -0500
Subject: [PATCH] True16 for v_cos_f16
---
llvm/lib/Target/AMDGPU/VOP1Instructions.td | 2 +-
llvm/test/CodeGen/AMDGPU/llvm.cos.f16.ll | 32 ++++
llvm/test/MC/AMDGPU/gfx11_asm_vop1.s | 75 +++++----
llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s | 65 ++++----
llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp8.s | 21 ++-
llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_err.s | 42 +++++
.../MC/AMDGPU/gfx11_asm_vop1_t16_promote.s | 154 +++++++++++++-----
.../AMDGPU/gfx11_asm_vop3_dpp16_from_vop1.s | 65 ++++----
.../MC/AMDGPU/gfx11_asm_vop3_dpp8_from_vop1.s | 25 ++-
.../test/MC/AMDGPU/gfx11_asm_vop3_from_vop1.s | 69 ++++----
llvm/test/MC/AMDGPU/gfx12_asm_vop1.s | 72 ++++----
llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp16.s | 62 +++----
llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp8.s | 18 +-
llvm/test/MC/AMDGPU/gfx12_asm_vop1_t16_err.s | 42 +++++
.../MC/AMDGPU/gfx12_asm_vop1_t16_promote.s | 154 +++++++++++++-----
.../test/MC/AMDGPU/gfx12_asm_vop3_from_vop1.s | 69 ++++----
.../AMDGPU/gfx12_asm_vop3_from_vop1_dpp16.s | 65 ++++----
.../MC/AMDGPU/gfx12_asm_vop3_from_vop1_dpp8.s | 25 ++-
.../Disassembler/AMDGPU/gfx11_dasm_vop1.txt | 63 +++++--
.../AMDGPU/gfx11_dasm_vop1_dpp16.txt | 54 ++++--
.../AMDGPU/gfx11_dasm_vop1_dpp8.txt | 17 +-
.../gfx11_dasm_vop3_dpp16_from_vop1.txt | 54 ++++--
.../AMDGPU/gfx11_dasm_vop3_dpp8_from_vop1.txt | 24 ++-
.../AMDGPU/gfx11_dasm_vop3_from_vop1.txt | 57 +++++--
.../AMDGPU/gfx12_dasm_vop1_dpp16.txt | 50 ++++--
.../AMDGPU/gfx12_dasm_vop1_dpp8.txt | 13 +-
.../AMDGPU/gfx12_dasm_vop3_from_vop1.txt | 57 +++++--
.../gfx12_dasm_vop3_from_vop1_dpp16.txt | 54 ++++--
.../AMDGPU/gfx12_dasm_vop3_from_vop1_dpp8.txt | 24 ++-
29 files changed, 1062 insertions(+), 462 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/VOP1Instructions.td b/llvm/lib/Target/AMDGPU/VOP1Instructions.td
index 1dd39be9e8d9c7..9620c9320f5f67 100644
--- a/llvm/lib/Target/AMDGPU/VOP1Instructions.td
+++ b/llvm/lib/Target/AMDGPU/VOP1Instructions.td
@@ -1046,7 +1046,7 @@ defm V_TRUNC_F16_fake16 : VOP1_Real_FULL_t16_gfx11_gfx12<0x05d, "v_trunc_f1
defm V_RNDNE_F16_fake16 : VOP1_Real_FULL_t16_gfx11_gfx12<0x05e, "v_rndne_f16">;
defm V_FRACT_F16_fake16 : VOP1_Real_FULL_t16_gfx11_gfx12<0x05f, "v_fract_f16">;
defm V_SIN_F16_fake16 : VOP1_Real_FULL_t16_gfx11_gfx12<0x060, "v_sin_f16">;
-defm V_COS_F16_fake16 : VOP1_Real_FULL_t16_gfx11_gfx12<0x061, "v_cos_f16">;
+defm V_COS_F16 : VOP1_Real_FULL_t16_and_fake16_gfx11_gfx12<0x061, "v_cos_f16">;
defm V_SAT_PK_U8_I16_fake16 : VOP1_Real_FULL_t16_gfx11_gfx12<0x062, "v_sat_pk_u8_i16">;
defm V_CVT_NORM_I16_F16 : VOP1_Real_FULL_t16_and_fake16_gfx11_gfx12<0x063, "v_cvt_norm_i16_f16">;
defm V_CVT_NORM_U16_F16 : VOP1_Real_FULL_t16_and_fake16_gfx11_gfx12<0x064, "v_cvt_norm_u16_f16">;
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.cos.f16.ll b/llvm/test/CodeGen/AMDGPU/llvm.cos.f16.ll
index 3ff759a5cdb94f..867025adca9440 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.cos.f16.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.cos.f16.ll
@@ -4,6 +4,7 @@
; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=GFX9 %s
; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=GFX10 %s
; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=GFX11 %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=gfx1200 -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefix=GFX12 %s
define amdgpu_kernel void @cos_f16(ptr addrspace(1) %r, ptr addrspace(1) %a) {
; GFX6-LABEL: cos_f16:
@@ -80,6 +81,19 @@ define amdgpu_kernel void @cos_f16(ptr addrspace(1) %r, ptr addrspace(1) %a) {
; GFX11-NEXT: v_cos_f16_e32 v1, v1
; GFX11-NEXT: global_store_b16 v0, v1, s[0:1]
; GFX11-NEXT: s_endpgm
+;
+; GFX12-LABEL: cos_f16:
+; GFX12: ; %bb.0:
+; GFX12-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
+; GFX12-NEXT: v_mov_b32_e32 v0, 0
+; GFX12-NEXT: s_wait_kmcnt 0x0
+; GFX12-NEXT: global_load_u16 v1, v0, s[2:3]
+; GFX12-NEXT: s_wait_loadcnt 0x0
+; GFX12-NEXT: v_mul_f16_e32 v1, 0.15915494, v1
+; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GFX12-NEXT: v_cos_f16_e32 v1, v1
+; GFX12-NEXT: global_store_b16 v0, v1, s[0:1]
+; GFX12-NEXT: s_endpgm
%a.val = load half, ptr addrspace(1) %a
%r.val = call half @llvm.cos.f16(half %a.val)
store half %r.val, ptr addrspace(1) %r
@@ -188,6 +202,24 @@ define amdgpu_kernel void @cos_v2f16(ptr addrspace(1) %r, ptr addrspace(1) %a) {
; GFX11-NEXT: v_pack_b32_f16 v1, v1, v2
; GFX11-NEXT: global_store_b32 v0, v1, s[0:1]
; GFX11-NEXT: s_endpgm
+;
+; GFX12-LABEL: cos_v2f16:
+; GFX12: ; %bb.0:
+; GFX12-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
+; GFX12-NEXT: v_mov_b32_e32 v0, 0
+; GFX12-NEXT: s_wait_kmcnt 0x0
+; GFX12-NEXT: global_load_b32 v1, v0, s[2:3]
+; GFX12-NEXT: s_wait_loadcnt 0x0
+; GFX12-NEXT: v_lshrrev_b32_e32 v2, 16, v1
+; GFX12-NEXT: v_mul_f16_e32 v1, 0.15915494, v1
+; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX12-NEXT: v_mul_f16_e32 v2, 0.15915494, v2
+; GFX12-NEXT: v_cos_f16_e32 v1, v1
+; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(TRANS32_DEP_1)
+; GFX12-NEXT: v_cos_f16_e32 v2, v2
+; GFX12-NEXT: v_pack_b32_f16 v1, v1, v2
+; GFX12-NEXT: global_store_b32 v0, v1, s[0:1]
+; GFX12-NEXT: s_endpgm
%a.val = load <2 x half>, ptr addrspace(1) %a
%r.val = call <2 x half> @llvm.cos.v2f16(<2 x half> %a.val)
store <2 x half> %r.val, ptr addrspace(1) %r
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop1.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop1.s
index 4e4dc6647daebd..fcc30eca6ae5a7 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop1.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop1.s
@@ -269,50 +269,65 @@ v_clz_i32_u32 v5, src_scc
v_clz_i32_u32 v255, 0xaf123456
// GFX11: v_clz_i32_u32_e32 v255, 0xaf123456 ; encoding: [0xff,0x72,0xfe,0x7f,0x56,0x34,0x12,0xaf]
-v_cos_f16 v5, v1
-// GFX11: v_cos_f16_e32 v5, v1 ; encoding: [0x01,0xc3,0x0a,0x7e]
+v_cos_f16 v5.l, v1.l
+// GFX11: v_cos_f16_e32 v5.l, v1.l ; encoding: [0x01,0xc3,0x0a,0x7e]
-v_cos_f16 v5, v127
-// GFX11: v_cos_f16_e32 v5, v127 ; encoding: [0x7f,0xc3,0x0a,0x7e]
+v_cos_f16 v5.l, v127.l
+// GFX11: v_cos_f16_e32 v5.l, v127.l ; encoding: [0x7f,0xc3,0x0a,0x7e]
-v_cos_f16 v5, s1
-// GFX11: v_cos_f16_e32 v5, s1 ; encoding: [0x01,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, s1
+// GFX11: v_cos_f16_e32 v5.l, s1 ; encoding: [0x01,0xc2,0x0a,0x7e]
-v_cos_f16 v5, s105
-// GFX11: v_cos_f16_e32 v5, s105 ; encoding: [0x69,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, s105
+// GFX11: v_cos_f16_e32 v5.l, s105 ; encoding: [0x69,0xc2,0x0a,0x7e]
-v_cos_f16 v5, vcc_lo
-// GFX11: v_cos_f16_e32 v5, vcc_lo ; encoding: [0x6a,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, vcc_lo
+// GFX11: v_cos_f16_e32 v5.l, vcc_lo ; encoding: [0x6a,0xc2,0x0a,0x7e]
-v_cos_f16 v5, vcc_hi
-// GFX11: v_cos_f16_e32 v5, vcc_hi ; encoding: [0x6b,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, vcc_hi
+// GFX11: v_cos_f16_e32 v5.l, vcc_hi ; encoding: [0x6b,0xc2,0x0a,0x7e]
-v_cos_f16 v5, ttmp15
-// GFX11: v_cos_f16_e32 v5, ttmp15 ; encoding: [0x7b,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, ttmp15
+// GFX11: v_cos_f16_e32 v5.l, ttmp15 ; encoding: [0x7b,0xc2,0x0a,0x7e]
-v_cos_f16 v5, m0
-// GFX11: v_cos_f16_e32 v5, m0 ; encoding: [0x7d,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, m0
+// GFX11: v_cos_f16_e32 v5.l, m0 ; encoding: [0x7d,0xc2,0x0a,0x7e]
-v_cos_f16 v5, exec_lo
-// GFX11: v_cos_f16_e32 v5, exec_lo ; encoding: [0x7e,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, exec_lo
+// GFX11: v_cos_f16_e32 v5.l, exec_lo ; encoding: [0x7e,0xc2,0x0a,0x7e]
-v_cos_f16 v5, exec_hi
-// GFX11: v_cos_f16_e32 v5, exec_hi ; encoding: [0x7f,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, exec_hi
+// GFX11: v_cos_f16_e32 v5.l, exec_hi ; encoding: [0x7f,0xc2,0x0a,0x7e]
-v_cos_f16 v5, null
-// GFX11: v_cos_f16_e32 v5, null ; encoding: [0x7c,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, null
+// GFX11: v_cos_f16_e32 v5.l, null ; encoding: [0x7c,0xc2,0x0a,0x7e]
-v_cos_f16 v5, -1
-// GFX11: v_cos_f16_e32 v5, -1 ; encoding: [0xc1,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, -1
+// GFX11: v_cos_f16_e32 v5.l, -1 ; encoding: [0xc1,0xc2,0x0a,0x7e]
-v_cos_f16 v5, 0.5
-// GFX11: v_cos_f16_e32 v5, 0.5 ; encoding: [0xf0,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, 0.5
+// GFX11: v_cos_f16_e32 v5.l, 0.5 ; encoding: [0xf0,0xc2,0x0a,0x7e]
-v_cos_f16 v5, src_scc
-// GFX11: v_cos_f16_e32 v5, src_scc ; encoding: [0xfd,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, src_scc
+// GFX11: v_cos_f16_e32 v5.l, src_scc ; encoding: [0xfd,0xc2,0x0a,0x7e]
-v_cos_f16 v127, 0xfe0b
-// GFX11: v_cos_f16_e32 v127, 0xfe0b ; encoding: [0xff,0xc2,0xfe,0x7e,0x0b,0xfe,0x00,0x00]
+v_cos_f16 v127.l, 0xfe0b
+// GFX11: v_cos_f16_e32 v127.l, 0xfe0b ; encoding: [0xff,0xc2,0xfe,0x7e,0x0b,0xfe,0x00,0x00]
+
+v_cos_f16 v5.l, v1.h
+// GFX11: v_cos_f16_e32 v5.l, v1.h ; encoding: [0x81,0xc3,0x0a,0x7e]
+
+v_cos_f16 v5.l, v127.h
+// GFX11: v_cos_f16_e32 v5.l, v127.h ; encoding: [0xff,0xc3,0x0a,0x7e]
+
+v_cos_f16 v127.l, 0.5
+// GFX11: v_cos_f16_e32 v127.l, 0.5 ; encoding: [0xf0,0xc2,0xfe,0x7e]
+
+v_cos_f16 v5.h, src_scc
+// GFX11: v_cos_f16_e32 v5.h, src_scc ; encoding: [0xfd,0xc2,0x0a,0x7f]
+
+v_cos_f16 v127.h, 0xfe0b
+// GFX11: v_cos_f16_e32 v127.h, 0xfe0b ; encoding: [0xff,0xc2,0xfe,0x7f,0x0b,0xfe,0x00,0x00]
v_cos_f32 v5, v1
// GFX11: v_cos_f32_e32 v5, v1 ; encoding: [0x01,0x6d,0x0a,0x7e]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s
index 98e4b29b25666e..c878cc05e3a3b9 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s
@@ -212,47 +212,56 @@ v_clz_i32_u32 v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
v_clz_i32_u32 v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX11: v_clz_i32_u32_dpp v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0x72,0xfe,0x7f,0xff,0x6f,0x05,0x30]
-v_cos_f16 v5, v1 quad_perm:[3,2,1,0]
-// GFX11: v_cos_f16_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1b,0x00,0xff]
+v_cos_f16 v5.l, v1.l quad_perm:[3,2,1,0]
+// GFX11: v_cos_f16_dpp v5.l, v1.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1b,0x00,0xff]
-v_cos_f16 v5, v1 quad_perm:[0,1,2,3]
-// GFX11: v_cos_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x00,0xff]
+v_cos_f16 v5.l, v1.l quad_perm:[0,1,2,3]
+// GFX11: v_cos_f16_dpp v5.l, v1.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x00,0xff]
-v_cos_f16 v5, v1 row_mirror
-// GFX11: v_cos_f16_dpp v5, v1 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x40,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_mirror
+// GFX11: v_cos_f16_dpp v5.l, v1.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x40,0x01,0xff]
-v_cos_f16 v5, v1 row_half_mirror
-// GFX11: v_cos_f16_dpp v5, v1 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x41,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_half_mirror
+// GFX11: v_cos_f16_dpp v5.l, v1.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x41,0x01,0xff]
-v_cos_f16 v5, v1 row_shl:1
-// GFX11: v_cos_f16_dpp v5, v1 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x01,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_shl:1
+// GFX11: v_cos_f16_dpp v5.l, v1.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x01,0x01,0xff]
-v_cos_f16 v5, v1 row_shl:15
-// GFX11: v_cos_f16_dpp v5, v1 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x0f,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_shl:15
+// GFX11: v_cos_f16_dpp v5.l, v1.l row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x0f,0x01,0xff]
-v_cos_f16 v5, v1 row_shr:1
-// GFX11: v_cos_f16_dpp v5, v1 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x11,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_shr:1
+// GFX11: v_cos_f16_dpp v5.l, v1.l row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x11,0x01,0xff]
-v_cos_f16 v5, v1 row_shr:15
-// GFX11: v_cos_f16_dpp v5, v1 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1f,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_shr:15
+// GFX11: v_cos_f16_dpp v5.l, v1.l row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1f,0x01,0xff]
-v_cos_f16 v5, v1 row_ror:1
-// GFX11: v_cos_f16_dpp v5, v1 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x21,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_ror:1
+// GFX11: v_cos_f16_dpp v5.l, v1.l row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x21,0x01,0xff]
-v_cos_f16 v5, v1 row_ror:15
-// GFX11: v_cos_f16_dpp v5, v1 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x2f,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_ror:15
+// GFX11: v_cos_f16_dpp v5.l, v1.l row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x2f,0x01,0xff]
-v_cos_f16 v5, v1 row_share:0 row_mask:0xf bank_mask:0xf
-// GFX11: v_cos_f16_dpp v5, v1 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x50,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf
+// GFX11: v_cos_f16_dpp v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x50,0x01,0xff]
-v_cos_f16 v5, v1 row_share:15 row_mask:0x0 bank_mask:0x1
-// GFX11: v_cos_f16_dpp v5, v1 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x5f,0x01,0x01]
+v_cos_f16 v5.l, v1.l row_share:15 row_mask:0x0 bank_mask:0x1
+// GFX11: v_cos_f16_dpp v5.l, v1.l row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x5f,0x01,0x01]
-v_cos_f16 v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
-// GFX11: v_cos_f16_dpp v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x60,0x09,0x13]
+v_cos_f16 v5.l, v1.l row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1
+// GFX11: v_cos_f16_dpp v5.l, v1.l row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x60,0x09,0x13]
-v_cos_f16 v127, -|v127| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
-// GFX11: v_cos_f16_dpp v127, -|v127| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xc2,0xfe,0x7e,0x7f,0x6f,0x35,0x30]
+v_cos_f16 v127.l, -|v127.l| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1
+// GFX11: v_cos_f16_dpp v127.l, -|v127.l| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xc2,0xfe,0x7e,0x7f,0x6f,0x35,0x30]
+
+v_cos_f16 v127.l, v127.l row_share:15 row_mask:0x0 bank_mask:0x1
+// GFX11: v_cos_f16_dpp v127.l, v127.l row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xc2,0xfe,0x7e,0x7f,0x5f,0x01,0x01]
+
+v_cos_f16 v5.h, v1.h row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
+// GFX11: v_cos_f16_dpp v5.h, v1.h row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0xc2,0x0a,0x7f,0x81,0x60,0x09,0x13]
+
+v_cos_f16 v127.h, -|v127.h| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
+// GFX11: v_cos_f16_dpp v127.h, -|v127.h| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xc2,0xfe,0x7f,0xff,0x6f,0x35,0x30]
v_cos_f32 v5, v1 quad_perm:[3,2,1,0]
// GFX11: v_cos_f32_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x6c,0x0a,0x7e,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp8.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp8.s
index ab4606af2bb35c..06232292c4e329 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp8.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp8.s
@@ -50,14 +50,23 @@ v_clz_i32_u32 v5, v1 dpp8:[7,6,5,4,3,2,1,0] fi:1
v_clz_i32_u32 v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX11: v_clz_i32_u32_dpp v255, v255 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0x72,0xfe,0x7f,0xff,0x00,0x00,0x00]
-v_cos_f16 v5, v1 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_cos_f16_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xc2,0x0a,0x7e,0x01,0x77,0x39,0x05]
+v_cos_f16 v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_cos_f16_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xc2,0x0a,0x7e,0x01,0x77,0x39,0x05]
-v_cos_f16 v5, v1 dpp8:[7,6,5,4,3,2,1,0] fi:1
-// GFX11: v_cos_f16_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0xc2,0x0a,0x7e,0x01,0x77,0x39,0x05]
+v_cos_f16 v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] fi:1
+// GFX11: v_cos_f16_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0xc2,0x0a,0x7e,0x01,0x77,0x39,0x05]
-v_cos_f16 v127, v127 dpp8:[0,0,0,0,0,0,0,0] fi:0
-// GFX11: v_cos_f16_dpp v127, v127 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xc2,0xfe,0x7e,0x7f,0x00,0x00,0x00]
+v_cos_f16 v127.l, v127.l dpp8:[0,0,0,0,0,0,0,0]
+// GFX11: v_cos_f16_dpp v127.l, v127.l dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xc2,0xfe,0x7e,0x7f,0x00,0x00,0x00]
+
+v_cos_f16 v127.l, v127.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_cos_f16_dpp v127.l, v127.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xc2,0xfe,0x7e,0x7f,0x77,0x39,0x05]
+
+v_cos_f16 v5.h, v1.h dpp8:[7,6,5,4,3,2,1,0] fi:1
+// GFX11: v_cos_f16_dpp v5.h, v1.h dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0xc2,0x0a,0x7f,0x81,0x77,0x39,0x05]
+
+v_cos_f16 v127.h, v127.h dpp8:[0,0,0,0,0,0,0,0] fi:0
+// GFX11: v_cos_f16_dpp v127.h, v127.h dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xc2,0xfe,0x7f,0xff,0x00,0x00,0x00]
v_cos_f32 v5, v1 dpp8:[7,6,5,4,3,2,1,0]
// GFX11: v_cos_f32_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0x6c,0x0a,0x7e,0x01,0x77,0x39,0x05]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_err.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_err.s
index 4ae91340386b65..6ff3c26d89725e 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_err.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_err.s
@@ -47,6 +47,12 @@ v_ceil_f16_e32 v5.l, v199.l quad_perm:[3,2,1,0]
v_cos_f16_e32 v128, 0xfe0b
// GFX11: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
+v_cos_f16_e32 v128.h, 0xfe0b
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_cos_f16_e32 v128.l, 0xfe0b
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
v_cos_f16_e32 v255, v1
// GFX11: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
@@ -56,6 +62,24 @@ v_cos_f16_e32 v255, v1 dpp8:[7,6,5,4,3,2,1,0]
v_cos_f16_e32 v255, v1 quad_perm:[3,2,1,0]
// GFX11: :[[@LINE-1]]:24: error: invalid operand for instruction
+v_cos_f16_e32 v255.h, v1.h
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_cos_f16_e32 v255.h, v1.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_cos_f16_e32 v255.h, v1.h quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_cos_f16_e32 v255.l, v1.l
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_cos_f16_e32 v255.l, v1.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_cos_f16_e32 v255.l, v1.l quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
v_cos_f16_e32 v5, v199
// GFX11: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
@@ -65,6 +89,24 @@ v_cos_f16_e32 v5, v199 dpp8:[7,6,5,4,3,2,1,0]
v_cos_f16_e32 v5, v199 quad_perm:[3,2,1,0]
// GFX11: :[[@LINE-1]]:24: error: invalid operand for instruction
+v_cos_f16_e32 v5.h, v199.h
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_cos_f16_e32 v5.h, v199.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_cos_f16_e32 v5.h, v199.h quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_cos_f16_e32 v5.l, v199.l
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_cos_f16_e32 v5.l, v199.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_cos_f16_e32 v5.l, v199.l quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
v_cvt_f16_f32_e32 v128, 0xaf123456
// GFX11: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s
index 1d441720280ca2..2bafba8ee00445 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_promote.s
@@ -68,71 +68,137 @@ v_ceil_f16 v5, v199 dpp8:[7,6,5,4,3,2,1,0]
v_ceil_f16 v5, v199 quad_perm:[3,2,1,0]
// GFX11: v_ceil_f16_e64_dpp v5, v199 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xdc,0xd5,0xfa,0x00,0x00,0x00,0xc7,0x1b,0x00,0xff]
-v_cos_f16 v128, 0xfe0b
-// GFX11: v_cos_f16_e64 v128, 0xfe0b ; encoding: [0x80,0x00,0xe1,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
+v_cos_f16 v128.h, 0xfe0b
+// GFX11: v_cos_f16_e64 v128.h, 0xfe0b op_sel:[0,1] ; encoding: [0x80,0x40,0xe1,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
-v_cos_f16 v255, -1
-// GFX11: v_cos_f16_e64 v255, -1 ; encoding: [0xff,0x00,0xe1,0xd5,0xc1,0x00,0x00,0x00]
+v_cos_f16 v128.l, 0xfe0b
+// GFX11: v_cos_f16_e64 v128.l, 0xfe0b ; encoding: [0x80,0x00,0xe1,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
-v_cos_f16 v255, 0.5
-// GFX11: v_cos_f16_e64 v255, 0.5 ; encoding: [0xff,0x00,0xe1,0xd5,0xf0,0x00,0x00,0x00]
+v_cos_f16 v255.h, -1
+// GFX11: v_cos_f16_e64 v255.h, -1 op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0xc1,0x00,0x00,0x00]
-v_cos_f16 v255, exec_hi
-// GFX11: v_cos_f16_e64 v255, exec_hi ; encoding: [0xff,0x00,0xe1,0xd5,0x7f,0x00,0x00,0x00]
+v_cos_f16 v255.h, 0.5
+// GFX11: v_cos_f16_e64 v255.h, 0.5 op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0xf0,0x00,0x00,0x00]
-v_cos_f16 v255, exec_lo
-// GFX11: v_cos_f16_e64 v255, exec_lo ; encoding: [0xff,0x00,0xe1,0xd5,0x7e,0x00,0x00,0x00]
+v_cos_f16 v255.h, exec_hi
+// GFX11: v_cos_f16_e64 v255.h, exec_hi op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x7f,0x00,0x00,0x00]
-v_cos_f16 v255, m0
-// GFX11: v_cos_f16_e64 v255, m0 ; encoding: [0xff,0x00,0xe1,0xd5,0x7d,0x00,0x00,0x00]
+v_cos_f16 v255.h, exec_lo
+// GFX11: v_cos_f16_e64 v255.h, exec_lo op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x7e,0x00,0x00,0x00]
-v_cos_f16 v255, null
-// GFX11: v_cos_f16_e64 v255, null ; encoding: [0xff,0x00,0xe1,0xd5,0x7c,0x00,0x00,0x00]
+v_cos_f16 v255.h, m0
+// GFX11: v_cos_f16_e64 v255.h, m0 op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x7d,0x00,0x00,0x00]
-v_cos_f16 v255, s1
-// GFX11: v_cos_f16_e64 v255, s1 ; encoding: [0xff,0x00,0xe1,0xd5,0x01,0x00,0x00,0x00]
+v_cos_f16 v255.h, null
+// GFX11: v_cos_f16_e64 v255.h, null op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x7c,0x00,0x00,0x00]
-v_cos_f16 v255, s105
-// GFX11: v_cos_f16_e64 v255, s105 ; encoding: [0xff,0x00,0xe1,0xd5,0x69,0x00,0x00,0x00]
+v_cos_f16 v255.h, s1
+// GFX11: v_cos_f16_e64 v255.h, s1 op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x01,0x00,0x00,0x00]
-v_cos_f16 v255, src_scc
-// GFX11: v_cos_f16_e64 v255, src_scc ; encoding: [0xff,0x00,0xe1,0xd5,0xfd,0x00,0x00,0x00]
+v_cos_f16 v255.h, s105
+// GFX11: v_cos_f16_e64 v255.h, s105 op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x69,0x00,0x00,0x00]
-v_cos_f16 v255, ttmp15
-// GFX11: v_cos_f16_e64 v255, ttmp15 ; encoding: [0xff,0x00,0xe1,0xd5,0x7b,0x00,0x00,0x00]
+v_cos_f16 v255.h, src_scc
+// GFX11: v_cos_f16_e64 v255.h, src_scc op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0xfd,0x00,0x00,0x00]
-v_cos_f16 v255, v1
-// GFX11: v_cos_f16_e64 v255, v1 ; encoding: [0xff,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00]
+v_cos_f16 v255.h, ttmp15
+// GFX11: v_cos_f16_e64 v255.h, ttmp15 op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x7b,0x00,0x00,0x00]
-v_cos_f16 v255, v1 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_cos_f16_e64_dpp v255, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
+v_cos_f16 v255.h, v1.h
+// GFX11: v_cos_f16_e64 v255.h, v1.h op_sel:[1,1] ; encoding: [0xff,0x48,0xe1,0xd5,0x01,0x01,0x00,0x00]
-v_cos_f16 v255, v1 quad_perm:[3,2,1,0]
-// GFX11: v_cos_f16_e64_dpp v255, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
+v_cos_f16 v255.h, v1.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_cos_f16_e64_dpp v255.h, v1.h op_sel:[1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x48,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
-v_cos_f16 v255, v127
-// GFX11: v_cos_f16_e64 v255, v127 ; encoding: [0xff,0x00,0xe1,0xd5,0x7f,0x01,0x00,0x00]
+v_cos_f16 v255.h, v1.h quad_perm:[3,2,1,0]
+// GFX11: v_cos_f16_e64_dpp v255.h, v1.h op_sel:[1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x48,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
-v_cos_f16 v255, v127 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_cos_f16_e64_dpp v255, v127 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x7f,0x77,0x39,0x05]
+v_cos_f16 v255.h, v127.h
+// GFX11: v_cos_f16_e64 v255.h, v127.h op_sel:[1,1] ; encoding: [0xff,0x48,0xe1,0xd5,0x7f,0x01,0x00,0x00]
-v_cos_f16 v255, v127 quad_perm:[3,2,1,0]
-// GFX11: v_cos_f16_e64_dpp v255, v127 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x7f,0x1b,0x00,0xff]
+v_cos_f16 v255.h, v127.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_cos_f16_e64_dpp v255.h, v127.h op_sel:[1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x48,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x7f,0x77,0x39,0x05]
-v_cos_f16 v255, vcc_hi
-// GFX11: v_cos_f16_e64 v255, vcc_hi ; encoding: [0xff,0x00,0xe1,0xd5,0x6b,0x00,0x00,0x00]
+v_cos_f16 v255.h, v127.h quad_perm:[3,2,1,0]
+// GFX11: v_cos_f16_e64_dpp v255.h, v127.h op_sel:[1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x48,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x7f,0x1b,0x00,0xff]
-v_cos_f16 v255, vcc_lo
-// GFX11: v_cos_f16_e64 v255, vcc_lo ; encoding: [0xff,0x00,0xe1,0xd5,0x6a,0x00,0x00,0x00]
+v_cos_f16 v255.h, vcc_hi
+// GFX11: v_cos_f16_e64 v255.h, vcc_hi op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x6b,0x00,0x00,0x00]
-v_cos_f16 v5, v199
-// GFX11: v_cos_f16_e64 v5, v199 ; encoding: [0x05,0x00,0xe1,0xd5,0xc7,0x01,0x00,0x00]
+v_cos_f16 v255.h, vcc_lo
+// GFX11: v_cos_f16_e64 v255.h, vcc_lo op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x6a,0x00,0x00,0x00]
-v_cos_f16 v5, v199 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_cos_f16_e64_dpp v5, v199 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0xc7,0x77,0x39,0x05]
+v_cos_f16 v255.l, -1
+// GFX11: v_cos_f16_e64 v255.l, -1 ; encoding: [0xff,0x00,0xe1,0xd5,0xc1,0x00,0x00,0x00]
-v_cos_f16 v5, v199 quad_perm:[3,2,1,0]
-// GFX11: v_cos_f16_e64_dpp v5, v199 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0xc7,0x1b,0x00,0xff]
+v_cos_f16 v255.l, 0.5
+// GFX11: v_cos_f16_e64 v255.l, 0.5 ; encoding: [0xff,0x00,0xe1,0xd5,0xf0,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, exec_hi
+// GFX11: v_cos_f16_e64 v255.l, exec_hi ; encoding: [0xff,0x00,0xe1,0xd5,0x7f,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, exec_lo
+// GFX11: v_cos_f16_e64 v255.l, exec_lo ; encoding: [0xff,0x00,0xe1,0xd5,0x7e,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, m0
+// GFX11: v_cos_f16_e64 v255.l, m0 ; encoding: [0xff,0x00,0xe1,0xd5,0x7d,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, null
+// GFX11: v_cos_f16_e64 v255.l, null ; encoding: [0xff,0x00,0xe1,0xd5,0x7c,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, s1
+// GFX11: v_cos_f16_e64 v255.l, s1 ; encoding: [0xff,0x00,0xe1,0xd5,0x01,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, s105
+// GFX11: v_cos_f16_e64 v255.l, s105 ; encoding: [0xff,0x00,0xe1,0xd5,0x69,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, src_scc
+// GFX11: v_cos_f16_e64 v255.l, src_scc ; encoding: [0xff,0x00,0xe1,0xd5,0xfd,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, ttmp15
+// GFX11: v_cos_f16_e64 v255.l, ttmp15 ; encoding: [0xff,0x00,0xe1,0xd5,0x7b,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, v1.l
+// GFX11: v_cos_f16_e64 v255.l, v1.l ; encoding: [0xff,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00]
+
+v_cos_f16 v255.l, v1.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_cos_f16_e64_dpp v255.l, v1.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
+
+v_cos_f16 v255.l, v1.l quad_perm:[3,2,1,0]
+// GFX11: v_cos_f16_e64_dpp v255.l, v1.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
+
+v_cos_f16 v255.l, v127.l
+// GFX11: v_cos_f16_e64 v255.l, v127.l ; encoding: [0xff,0x00,0xe1,0xd5,0x7f,0x01,0x00,0x00]
+
+v_cos_f16 v255.l, v127.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_cos_f16_e64_dpp v255.l, v127.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x7f,0x77,0x39,0x05]
+
+v_cos_f16 v255.l, v127.l quad_perm:[3,2,1,0]
+// GFX11: v_cos_f16_e64_dpp v255.l, v127.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x7f,0x1b,0x00,0xff]
+
+v_cos_f16 v255.l, vcc_hi
+// GFX11: v_cos_f16_e64 v255.l, vcc_hi ; encoding: [0xff,0x00,0xe1,0xd5,0x6b,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, vcc_lo
+// GFX11: v_cos_f16_e64 v255.l, vcc_lo ; encoding: [0xff,0x00,0xe1,0xd5,0x6a,0x00,0x00,0x00]
+
+v_cos_f16 v5.h, v199.h
+// GFX11: v_cos_f16_e64 v5.h, v199.h op_sel:[1,1] ; encoding: [0x05,0x48,0xe1,0xd5,0xc7,0x01,0x00,0x00]
+
+v_cos_f16 v5.h, v199.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_cos_f16_e64_dpp v5.h, v199.h op_sel:[1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x48,0xe1,0xd5,0xe9,0x00,0x00,0x00,0xc7,0x77,0x39,0x05]
+
+v_cos_f16 v5.h, v199.h quad_perm:[3,2,1,0]
+// GFX11: v_cos_f16_e64_dpp v5.h, v199.h op_sel:[1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x48,0xe1,0xd5,0xfa,0x00,0x00,0x00,0xc7,0x1b,0x00,0xff]
+
+v_cos_f16 v5.l, v199.l
+// GFX11: v_cos_f16_e64 v5.l, v199.l ; encoding: [0x05,0x00,0xe1,0xd5,0xc7,0x01,0x00,0x00]
+
+v_cos_f16 v5.l, v199.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_cos_f16_e64_dpp v5.l, v199.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0xc7,0x77,0x39,0x05]
+
+v_cos_f16 v5.l, v199.l quad_perm:[3,2,1,0]
+// GFX11: v_cos_f16_e64_dpp v5.l, v199.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0xc7,0x1b,0x00,0xff]
v_cvt_f16_f32 v128.h, 0xaf123456
// GFX11: v_cvt_f16_f32_e64 v128.h, 0xaf123456 op_sel:[0,1] ; encoding: [0x80,0x40,0x8a,0xd5,0xff,0x00,0x00,0x00,0x56,0x34,0x12,0xaf]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16_from_vop1.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16_from_vop1.s
index f38ff6a2fdd7d3..3354cea2f7aa1b 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16_from_vop1.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16_from_vop1.s
@@ -220,47 +220,56 @@ v_clz_i32_u32_e64_dpp v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1
v_clz_i32_u32_e64_dpp v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX11: v_clz_i32_u32_e64_dpp v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0xb9,0xd5,0xfa,0x00,0x00,0x00,0xff,0x6f,0x05,0x30]
-v_cos_f16_e64_dpp v5, v1 quad_perm:[3,2,1,0]
-// GFX11: v_cos_f16_e64_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l quad_perm:[3,2,1,0]
+// GFX11: v_cos_f16_e64_dpp v5.l, v1.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
-v_cos_f16_e64_dpp v5, v1 quad_perm:[0,1,2,3]
-// GFX11: v_cos_f16_e64_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0xe4,0x00,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l quad_perm:[0,1,2,3]
+// GFX11: v_cos_f16_e64_dpp v5.l, v1.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0xe4,0x00,0xff]
-v_cos_f16_e64_dpp v5, v1 row_mirror
-// GFX11: v_cos_f16_e64_dpp v5, v1 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x40,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_mirror
+// GFX11: v_cos_f16_e64_dpp v5.l, v1.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x40,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 row_half_mirror
-// GFX11: v_cos_f16_e64_dpp v5, v1 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x41,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_half_mirror
+// GFX11: v_cos_f16_e64_dpp v5.l, v1.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x41,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 row_shl:1
-// GFX11: v_cos_f16_e64_dpp v5, v1 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x01,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_shl:1
+// GFX11: v_cos_f16_e64_dpp v5.l, v1.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x01,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 row_shl:15
-// GFX11: v_cos_f16_e64_dpp v5, v1 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x0f,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_shl:15
+// GFX11: v_cos_f16_e64_dpp v5.l, v1.l row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x0f,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 row_shr:1
-// GFX11: v_cos_f16_e64_dpp v5, v1 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x11,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_shr:1
+// GFX11: v_cos_f16_e64_dpp v5.l, v1.l row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x11,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 row_shr:15
-// GFX11: v_cos_f16_e64_dpp v5, v1 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1f,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_shr:15
+// GFX11: v_cos_f16_e64_dpp v5.l, v1.l row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1f,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 row_ror:1
-// GFX11: v_cos_f16_e64_dpp v5, v1 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x21,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_ror:1
+// GFX11: v_cos_f16_e64_dpp v5.l, v1.l row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x21,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 row_ror:15
-// GFX11: v_cos_f16_e64_dpp v5, v1 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x2f,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_ror:15
+// GFX11: v_cos_f16_e64_dpp v5.l, v1.l row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x2f,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 row_share:0 row_mask:0xf bank_mask:0xf
-// GFX11: v_cos_f16_e64_dpp v5, v1 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x50,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf
+// GFX11: v_cos_f16_e64_dpp v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x50,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 mul:2 row_share:15 row_mask:0x0 bank_mask:0x1
-// GFX11: v_cos_f16_e64_dpp v5, v1 mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01]
+v_cos_f16_e64_dpp v5.l, v1.l mul:2 row_share:15 row_mask:0x0 bank_mask:0x1
+// GFX11: v_cos_f16_e64_dpp v5.l, v1.l mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01]
-v_cos_f16_e64_dpp v5, v1 mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
-// GFX11: v_cos_f16_e64_dpp v5, v1 mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x09,0x13]
+v_cos_f16_e64_dpp v5.l, v1.l mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
+// GFX11: v_cos_f16_e64_dpp v5.l, v1.l mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x09,0x13]
-v_cos_f16_e64_dpp v255, -|v255| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
-// GFX11: v_cos_f16_e64_dpp v255, -|v255| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x05,0x30]
+v_cos_f16_e64_dpp v255.l, -|v255.l| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
+// GFX11: v_cos_f16_e64_dpp v255.l, -|v255.l| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x05,0x30]
+
+v_cos_f16_e64_dpp v5.h, v1.h mul:2 row_share:15 row_mask:0x0 bank_mask:0x1
+// GFX11: [0x05,0x48,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01]
+
+v_cos_f16_e64_dpp v5.l, v1.h mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
+// GFX11: [0x05,0x08,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x09,0x13]
+
+v_cos_f16_e64_dpp v255.h, -|v255.l| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
+// GFX11: [0xff,0xc1,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x05,0x30]
v_cos_f32_e64_dpp v5, v1 quad_perm:[3,2,1,0]
// GFX11: v_cos_f32_e64_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xb6,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8_from_vop1.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8_from_vop1.s
index 95407886ccba15..8c9c7541a941d7 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8_from_vop1.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8_from_vop1.s
@@ -61,17 +61,26 @@ v_clz_i32_u32_e64_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] fi:1
v_clz_i32_u32_e64_dpp v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX11: v_clz_i32_u32_e64_dpp v255, v255 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x00,0xb9,0xd5,0xe9,0x00,0x00,0x00,0xff,0x00,0x00,0x00]
-v_cos_f16_e64_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_cos_f16_e64_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
+v_cos_f16_e64_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_cos_f16_e64_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
-v_cos_f16_e64_dpp v5, v1 mul:2 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_cos_f16_e64_dpp v5, v1 mul:2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05]
+v_cos_f16_e64_dpp v5.l, v1.l mul:2 dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_cos_f16_e64_dpp v5.l, v1.l mul:2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05]
-v_cos_f16_e64_dpp v5, v1 mul:4 dpp8:[7,6,5,4,3,2,1,0] fi:1
-// GFX11: v_cos_f16_e64_dpp v5, v1 mul:4 dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x05,0x00,0xe1,0xd5,0xea,0x00,0x00,0x10,0x01,0x77,0x39,0x05]
+v_cos_f16_e64_dpp v5.l, v1.l mul:4 dpp8:[7,6,5,4,3,2,1,0] fi:1
+// GFX11: v_cos_f16_e64_dpp v5.l, v1.l mul:4 dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x05,0x00,0xe1,0xd5,0xea,0x00,0x00,0x10,0x01,0x77,0x39,0x05]
-v_cos_f16_e64_dpp v255, -|v255| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:0
-// GFX11: v_cos_f16_e64_dpp v255, -|v255| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x81,0xe1,0xd5,0xe9,0x00,0x00,0x38,0xff,0x00,0x00,0x00]
+v_cos_f16_e64_dpp v255.l, -|v255.l| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:0
+// GFX11: v_cos_f16_e64_dpp v255.l, -|v255.l| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x81,0xe1,0xd5,0xe9,0x00,0x00,0x38,0xff,0x00,0x00,0x00]
+
+v_cos_f16_e64_dpp v5.h, v1.h mul:2 dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: [0x05,0x48,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05]
+
+v_cos_f16_e64_dpp v5.l, v1.h mul:4 dpp8:[7,6,5,4,3,2,1,0] fi:1
+// GFX11: [0x05,0x08,0xe1,0xd5,0xea,0x00,0x00,0x10,0x01,0x77,0x39,0x05]
+
+v_cos_f16_e64_dpp v255.h, -|v255.l| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:0
+// GFX11: [0xff,0xc1,0xe1,0xd5,0xe9,0x00,0x00,0x38,0xff,0x00,0x00,0x00]
v_cos_f32_e64_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0]
// GFX11: v_cos_f32_e64_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xb6,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_from_vop1.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_from_vop1.s
index 3850f0254a7f1a..15e36836ab5975 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_from_vop1.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_from_vop1.s
@@ -262,50 +262,59 @@ v_clz_i32_u32_e64 v5, src_scc
v_clz_i32_u32_e64 v255, 0xaf123456
// GFX11: v_clz_i32_u32_e64 v255, 0xaf123456 ; encoding: [0xff,0x00,0xb9,0xd5,0xff,0x00,0x00,0x00,0x56,0x34,0x12,0xaf]
-v_cos_f16_e64 v5, v1
-// GFX11: v_cos_f16_e64 v5, v1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00]
+v_cos_f16_e64 v5.l, v1.l
+// GFX11: v_cos_f16_e64 v5.l, v1.l ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00]
-v_cos_f16_e64 v5, v255
-// GFX11: v_cos_f16_e64 v5, v255 ; encoding: [0x05,0x00,0xe1,0xd5,0xff,0x01,0x00,0x00]
+v_cos_f16_e64 v5.l, v255.l
+// GFX11: v_cos_f16_e64 v5.l, v255.l ; encoding: [0x05,0x00,0xe1,0xd5,0xff,0x01,0x00,0x00]
-v_cos_f16_e64 v5, s1
-// GFX11: v_cos_f16_e64 v5, s1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, s1
+// GFX11: v_cos_f16_e64 v5.l, s1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x00,0x00,0x00]
-v_cos_f16_e64 v5, s105
-// GFX11: v_cos_f16_e64 v5, s105 ; encoding: [0x05,0x00,0xe1,0xd5,0x69,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, s105
+// GFX11: v_cos_f16_e64 v5.l, s105 ; encoding: [0x05,0x00,0xe1,0xd5,0x69,0x00,0x00,0x00]
-v_cos_f16_e64 v5, vcc_lo
-// GFX11: v_cos_f16_e64 v5, vcc_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x6a,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, vcc_lo
+// GFX11: v_cos_f16_e64 v5.l, vcc_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x6a,0x00,0x00,0x00]
-v_cos_f16_e64 v5, vcc_hi
-// GFX11: v_cos_f16_e64 v5, vcc_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x6b,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, vcc_hi
+// GFX11: v_cos_f16_e64 v5.l, vcc_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x6b,0x00,0x00,0x00]
-v_cos_f16_e64 v5, ttmp15
-// GFX11: v_cos_f16_e64 v5, ttmp15 ; encoding: [0x05,0x00,0xe1,0xd5,0x7b,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, ttmp15
+// GFX11: v_cos_f16_e64 v5.l, ttmp15 ; encoding: [0x05,0x00,0xe1,0xd5,0x7b,0x00,0x00,0x00]
-v_cos_f16_e64 v5, m0
-// GFX11: v_cos_f16_e64 v5, m0 ; encoding: [0x05,0x00,0xe1,0xd5,0x7d,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, m0
+// GFX11: v_cos_f16_e64 v5.l, m0 ; encoding: [0x05,0x00,0xe1,0xd5,0x7d,0x00,0x00,0x00]
-v_cos_f16_e64 v5, exec_lo
-// GFX11: v_cos_f16_e64 v5, exec_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x7e,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, exec_lo
+// GFX11: v_cos_f16_e64 v5.l, exec_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x7e,0x00,0x00,0x00]
-v_cos_f16_e64 v5, exec_hi
-// GFX11: v_cos_f16_e64 v5, exec_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x7f,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, exec_hi
+// GFX11: v_cos_f16_e64 v5.l, exec_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x7f,0x00,0x00,0x00]
-v_cos_f16_e64 v5, null
-// GFX11: v_cos_f16_e64 v5, null ; encoding: [0x05,0x00,0xe1,0xd5,0x7c,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, null
+// GFX11: v_cos_f16_e64 v5.l, null ; encoding: [0x05,0x00,0xe1,0xd5,0x7c,0x00,0x00,0x00]
-v_cos_f16_e64 v5, -1
-// GFX11: v_cos_f16_e64 v5, -1 ; encoding: [0x05,0x00,0xe1,0xd5,0xc1,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, -1
+// GFX11: v_cos_f16_e64 v5.l, -1 ; encoding: [0x05,0x00,0xe1,0xd5,0xc1,0x00,0x00,0x00]
-v_cos_f16_e64 v5, 0.5 mul:2
-// GFX11: v_cos_f16_e64 v5, 0.5 mul:2 ; encoding: [0x05,0x00,0xe1,0xd5,0xf0,0x00,0x00,0x08]
+v_cos_f16_e64 v5.l, 0.5 mul:2
+// GFX11: v_cos_f16_e64 v5.l, 0.5 mul:2 ; encoding: [0x05,0x00,0xe1,0xd5,0xf0,0x00,0x00,0x08]
-v_cos_f16_e64 v5, src_scc mul:4
-// GFX11: v_cos_f16_e64 v5, src_scc mul:4 ; encoding: [0x05,0x00,0xe1,0xd5,0xfd,0x00,0x00,0x10]
+v_cos_f16_e64 v5.l, src_scc mul:4
+// GFX11: v_cos_f16_e64 v5.l, src_scc mul:4 ; encoding: [0x05,0x00,0xe1,0xd5,0xfd,0x00,0x00,0x10]
-v_cos_f16_e64 v255, -|0xfe0b| clamp div:2
-// GFX11: v_cos_f16_e64 v255, -|0xfe0b| clamp div:2 ; encoding: [0xff,0x81,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00]
+v_cos_f16_e64 v255.l, -|0xfe0b| clamp div:2
+// GFX11: v_cos_f16_e64 v255.l, -|0xfe0b| clamp div:2 ; encoding: [0xff,0x81,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00]
+
+v_cos_f16_e64 v5.h, v1.h
+// GFX11: [0x05,0x48,0xe1,0xd5,0x01,0x01,0x00,0x00]
+
+v_cos_f16_e64 v5.l, v255.h
+// GFX11: [0x05,0x08,0xe1,0xd5,0xff,0x01,0x00,0x00]
+
+v_cos_f16_e64 v255.h, -|0xfe0b| clamp div:2
+// GFX11: [0xff,0xc1,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00]
v_cos_f32_e64 v5, v1
// GFX11: v_cos_f32_e64 v5, v1 ; encoding: [0x05,0x00,0xb6,0xd5,0x01,0x01,0x00,0x00]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop1.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop1.s
index edd3b916f4e5f3..80836a262d9f03 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop1.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop1.s
@@ -265,50 +265,62 @@ v_clz_i32_u32 v5, src_scc
v_clz_i32_u32 v255, 0xaf123456
// GFX12: v_clz_i32_u32_e32 v255, 0xaf123456 ; encoding: [0xff,0x72,0xfe,0x7f,0x56,0x34,0x12,0xaf]
-v_cos_f16 v5, v1
-// GFX12: v_cos_f16_e32 v5, v1 ; encoding: [0x01,0xc3,0x0a,0x7e]
+v_cos_f16 v5.l, v1.l
+// GFX12: v_cos_f16_e32 v5.l, v1.l ; encoding: [0x01,0xc3,0x0a,0x7e]
-v_cos_f16 v5, v127
-// GFX12: v_cos_f16_e32 v5, v127 ; encoding: [0x7f,0xc3,0x0a,0x7e]
+v_cos_f16 v5.l, v127.l
+// GFX12: v_cos_f16_e32 v5.l, v127.l ; encoding: [0x7f,0xc3,0x0a,0x7e]
-v_cos_f16 v5, s1
-// GFX12: v_cos_f16_e32 v5, s1 ; encoding: [0x01,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, s1
+// GFX12: v_cos_f16_e32 v5.l, s1 ; encoding: [0x01,0xc2,0x0a,0x7e]
-v_cos_f16 v5, s105
-// GFX12: v_cos_f16_e32 v5, s105 ; encoding: [0x69,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, s105
+// GFX12: v_cos_f16_e32 v5.l, s105 ; encoding: [0x69,0xc2,0x0a,0x7e]
-v_cos_f16 v5, vcc_lo
-// GFX12: v_cos_f16_e32 v5, vcc_lo ; encoding: [0x6a,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, vcc_lo
+// GFX12: v_cos_f16_e32 v5.l, vcc_lo ; encoding: [0x6a,0xc2,0x0a,0x7e]
-v_cos_f16 v5, vcc_hi
-// GFX12: v_cos_f16_e32 v5, vcc_hi ; encoding: [0x6b,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, vcc_hi
+// GFX12: v_cos_f16_e32 v5.l, vcc_hi ; encoding: [0x6b,0xc2,0x0a,0x7e]
-v_cos_f16 v5, ttmp15
-// GFX12: v_cos_f16_e32 v5, ttmp15 ; encoding: [0x7b,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, ttmp15
+// GFX12: v_cos_f16_e32 v5.l, ttmp15 ; encoding: [0x7b,0xc2,0x0a,0x7e]
-v_cos_f16 v5, m0
-// GFX12: v_cos_f16_e32 v5, m0 ; encoding: [0x7d,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, m0
+// GFX12: v_cos_f16_e32 v5.l, m0 ; encoding: [0x7d,0xc2,0x0a,0x7e]
-v_cos_f16 v5, exec_lo
-// GFX12: v_cos_f16_e32 v5, exec_lo ; encoding: [0x7e,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, exec_lo
+// GFX12: v_cos_f16_e32 v5.l, exec_lo ; encoding: [0x7e,0xc2,0x0a,0x7e]
-v_cos_f16 v5, exec_hi
-// GFX12: v_cos_f16_e32 v5, exec_hi ; encoding: [0x7f,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, exec_hi
+// GFX12: v_cos_f16_e32 v5.l, exec_hi ; encoding: [0x7f,0xc2,0x0a,0x7e]
-v_cos_f16 v5, null
-// GFX12: v_cos_f16_e32 v5, null ; encoding: [0x7c,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, null
+// GFX12: v_cos_f16_e32 v5.l, null ; encoding: [0x7c,0xc2,0x0a,0x7e]
-v_cos_f16 v5, -1
-// GFX12: v_cos_f16_e32 v5, -1 ; encoding: [0xc1,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, -1
+// GFX12: v_cos_f16_e32 v5.l, -1 ; encoding: [0xc1,0xc2,0x0a,0x7e]
-v_cos_f16 v5, 0.5
-// GFX12: v_cos_f16_e32 v5, 0.5 ; encoding: [0xf0,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, 0.5
+// GFX12: v_cos_f16_e32 v5.l, 0.5 ; encoding: [0xf0,0xc2,0x0a,0x7e]
-v_cos_f16 v5, src_scc
-// GFX12: v_cos_f16_e32 v5, src_scc ; encoding: [0xfd,0xc2,0x0a,0x7e]
+v_cos_f16 v5.l, src_scc
+// GFX12: v_cos_f16_e32 v5.l, src_scc ; encoding: [0xfd,0xc2,0x0a,0x7e]
-v_cos_f16 v127, 0xfe0b
-// GFX12: v_cos_f16_e32 v127, 0xfe0b ; encoding: [0xff,0xc2,0xfe,0x7e,0x0b,0xfe,0x00,0x00]
+v_cos_f16 v127.l, 0xfe0b
+// GFX12: v_cos_f16_e32 v127.l, 0xfe0b ; encoding: [0xff,0xc2,0xfe,0x7e,0x0b,0xfe,0x00,0x00]
+
+v_cos_f16 v5.l, v1.h
+// GFX12: v_cos_f16_e32 v5.l, v1.h ; encoding: [0x81,0xc3,0x0a,0x7e]
+
+v_cos_f16 v5.l, v127.h
+// GFX12: v_cos_f16_e32 v5.l, v127.h ; encoding: [0xff,0xc3,0x0a,0x7e]
+
+v_cos_f16 v5.h, src_scc
+// GFX12: v_cos_f16_e32 v5.h, src_scc ; encoding: [0xfd,0xc2,0x0a,0x7f]
+
+v_cos_f16 v127.h, 0xfe0b
+// GFX12: v_cos_f16_e32 v127.h, 0xfe0b ; encoding: [0xff,0xc2,0xfe,0x7f,0x0b,0xfe,0x00,0x00]
v_cos_f32 v5, v1
// GFX12: v_cos_f32_e32 v5, v1 ; encoding: [0x01,0x6d,0x0a,0x7e]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp16.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp16.s
index 56b42f19db38ab..164866cc7d840a 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp16.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp16.s
@@ -214,47 +214,53 @@ v_clz_i32_u32 v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
v_clz_i32_u32 v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX12: v_clz_i32_u32_dpp v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0x72,0xfe,0x7f,0xff,0x6f,0x05,0x30]
-v_cos_f16 v5, v1 quad_perm:[3,2,1,0]
-// GFX12: v_cos_f16_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1b,0x00,0xff]
+v_cos_f16 v5.l, v1.l quad_perm:[3,2,1,0]
+// GFX12: v_cos_f16_dpp v5.l, v1.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1b,0x00,0xff]
-v_cos_f16 v5, v1 quad_perm:[0,1,2,3]
-// GFX12: v_cos_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x00,0xff]
+v_cos_f16 v5.l, v1.l quad_perm:[0,1,2,3]
+// GFX12: v_cos_f16_dpp v5.l, v1.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x00,0xff]
-v_cos_f16 v5, v1 row_mirror
-// GFX12: v_cos_f16_dpp v5, v1 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x40,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_mirror
+// GFX12: v_cos_f16_dpp v5.l, v1.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x40,0x01,0xff]
-v_cos_f16 v5, v1 row_half_mirror
-// GFX12: v_cos_f16_dpp v5, v1 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x41,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_half_mirror
+// GFX12: v_cos_f16_dpp v5.l, v1.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x41,0x01,0xff]
-v_cos_f16 v5, v1 row_shl:1
-// GFX12: v_cos_f16_dpp v5, v1 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x01,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_shl:1
+// GFX12: v_cos_f16_dpp v5.l, v1.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x01,0x01,0xff]
-v_cos_f16 v5, v1 row_shl:15
-// GFX12: v_cos_f16_dpp v5, v1 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x0f,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_shl:15
+// GFX12: v_cos_f16_dpp v5.l, v1.l row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x0f,0x01,0xff]
-v_cos_f16 v5, v1 row_shr:1
-// GFX12: v_cos_f16_dpp v5, v1 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x11,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_shr:1
+// GFX12: v_cos_f16_dpp v5.l, v1.l row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x11,0x01,0xff]
-v_cos_f16 v5, v1 row_shr:15
-// GFX12: v_cos_f16_dpp v5, v1 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1f,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_shr:15
+// GFX12: v_cos_f16_dpp v5.l, v1.l row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1f,0x01,0xff]
-v_cos_f16 v5, v1 row_ror:1
-// GFX12: v_cos_f16_dpp v5, v1 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x21,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_ror:1
+// GFX12: v_cos_f16_dpp v5.l, v1.l row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x21,0x01,0xff]
-v_cos_f16 v5, v1 row_ror:15
-// GFX12: v_cos_f16_dpp v5, v1 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x2f,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_ror:15
+// GFX12: v_cos_f16_dpp v5.l, v1.l row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x2f,0x01,0xff]
-v_cos_f16 v5, v1 row_share:0 row_mask:0xf bank_mask:0xf
-// GFX12: v_cos_f16_dpp v5, v1 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x50,0x01,0xff]
+v_cos_f16 v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf
+// GFX12: v_cos_f16_dpp v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x50,0x01,0xff]
-v_cos_f16 v5, v1 row_share:15 row_mask:0x0 bank_mask:0x1
-// GFX12: v_cos_f16_dpp v5, v1 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x5f,0x01,0x01]
+v_cos_f16 v5.l, v1.l row_share:15 row_mask:0x0 bank_mask:0x1
+// GFX12: v_cos_f16_dpp v5.l, v1.l row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x5f,0x01,0x01]
-v_cos_f16 v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
-// GFX12: v_cos_f16_dpp v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x60,0x09,0x13]
+v_cos_f16 v5.l, v1.l row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
+// GFX12: v_cos_f16_dpp v5.l, v1.l row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x60,0x09,0x13]
-v_cos_f16 v127, -|v127| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
-// GFX12: v_cos_f16_dpp v127, -|v127| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xc2,0xfe,0x7e,0x7f,0x6f,0x35,0x30]
+v_cos_f16 v127.l, -|v127.l| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
+// GFX12: v_cos_f16_dpp v127.l, -|v127.l| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xc2,0xfe,0x7e,0x7f,0x6f,0x35,0x30]
+
+v_cos_f16 v5.h, v1.h row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
+// GFX12: v_cos_f16_dpp v5.h, v1.h row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0xc2,0x0a,0x7f,0x81,0x60,0x09,0x13]
+
+v_cos_f16 v127.h, -|v127.h| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
+// GFX12: v_cos_f16_dpp v127.h, -|v127.h| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xc2,0xfe,0x7f,0xff,0x6f,0x35,0x30]
v_cos_f32 v5, v1 quad_perm:[3,2,1,0]
// GFX12: v_cos_f32_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x6c,0x0a,0x7e,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp8.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp8.s
index 09f3069114d4a7..cfaad855db30e9 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp8.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop1_dpp8.s
@@ -49,14 +49,20 @@ v_clz_i32_u32 v5, v1 dpp8:[7,6,5,4,3,2,1,0] fi:1
v_clz_i32_u32 v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX12: v_clz_i32_u32_dpp v255, v255 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0x72,0xfe,0x7f,0xff,0x00,0x00,0x00]
-v_cos_f16 v5, v1 dpp8:[7,6,5,4,3,2,1,0]
-// GFX12: v_cos_f16_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xc2,0x0a,0x7e,0x01,0x77,0x39,0x05]
+v_cos_f16 v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: v_cos_f16_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xc2,0x0a,0x7e,0x01,0x77,0x39,0x05]
-v_cos_f16 v5, v1 dpp8:[7,6,5,4,3,2,1,0] fi:1
-// GFX12: v_cos_f16_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0xc2,0x0a,0x7e,0x01,0x77,0x39,0x05]
+v_cos_f16 v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] fi:1
+// GFX12: v_cos_f16_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0xc2,0x0a,0x7e,0x01,0x77,0x39,0x05]
-v_cos_f16 v127, v127 dpp8:[0,0,0,0,0,0,0,0] fi:0
-// GFX12: v_cos_f16_dpp v127, v127 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xc2,0xfe,0x7e,0x7f,0x00,0x00,0x00]
+v_cos_f16 v127.l, v127.l dpp8:[0,0,0,0,0,0,0,0] fi:0
+// GFX12: v_cos_f16_dpp v127.l, v127.l dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xc2,0xfe,0x7e,0x7f,0x00,0x00,0x00]
+
+v_cos_f16 v5.h, v1.h dpp8:[7,6,5,4,3,2,1,0] fi:1
+// GFX12: v_cos_f16_dpp v5.h, v1.h dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0xc2,0x0a,0x7f,0x81,0x77,0x39,0x05]
+
+v_cos_f16 v127.h, v127.h dpp8:[0,0,0,0,0,0,0,0] fi:0
+// GFX12: v_cos_f16_dpp v127.h, v127.h dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xc2,0xfe,0x7f,0xff,0x00,0x00,0x00]
v_cos_f32 v5, v1 dpp8:[7,6,5,4,3,2,1,0]
// GFX12: v_cos_f32_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0x6c,0x0a,0x7e,0x01,0x77,0x39,0x05]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop1_t16_err.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop1_t16_err.s
index 0ccad9c6730791..abe39210c87bb8 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop1_t16_err.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop1_t16_err.s
@@ -25,6 +25,12 @@ v_ceil_f16_e32 v5, v199 quad_perm:[3,2,1,0]
v_cos_f16_e32 v128, 0xfe0b
// GFX12: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
+v_cos_f16_e32 v128.h, 0xfe0b
+// GFX12: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_cos_f16_e32 v128.l, 0xfe0b
+// GFX12: :[[@LINE-1]]:15: error: invalid operand for instruction
+
v_cos_f16_e32 v255, v1
// GFX12: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
@@ -34,6 +40,24 @@ v_cos_f16_e32 v255, v1 dpp8:[7,6,5,4,3,2,1,0]
v_cos_f16_e32 v255, v1 quad_perm:[3,2,1,0]
// GFX12: :[[@LINE-1]]:24: error: invalid operand for instruction
+v_cos_f16_e32 v255.h, v1.h
+// GFX12: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_cos_f16_e32 v255.h, v1.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_cos_f16_e32 v255.h, v1.h quad_perm:[3,2,1,0]
+// GFX12: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_cos_f16_e32 v255.l, v1.l
+// GFX12: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_cos_f16_e32 v255.l, v1.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_cos_f16_e32 v255.l, v1.l quad_perm:[3,2,1,0]
+// GFX12: :[[@LINE-1]]:15: error: invalid operand for instruction
+
v_cos_f16_e32 v5, v199
// GFX12: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
@@ -43,6 +67,24 @@ v_cos_f16_e32 v5, v199 dpp8:[7,6,5,4,3,2,1,0]
v_cos_f16_e32 v5, v199 quad_perm:[3,2,1,0]
// GFX12: :[[@LINE-1]]:24: error: invalid operand for instruction
+v_cos_f16_e32 v5.h, v199.h
+// GFX12: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_cos_f16_e32 v5.h, v199.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_cos_f16_e32 v5.h, v199.h quad_perm:[3,2,1,0]
+// GFX12: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_cos_f16_e32 v5.l, v199.l
+// GFX12: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_cos_f16_e32 v5.l, v199.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_cos_f16_e32 v5.l, v199.l quad_perm:[3,2,1,0]
+// GFX12: :[[@LINE-1]]:21: error: invalid operand for instruction
+
v_cvt_f16_f32_e32 v128.h, 0xaf123456
// GFX12: :[[@LINE-1]]:19: error: invalid operand for instruction
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop1_t16_promote.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop1_t16_promote.s
index f220ec2b7d1e58..4f900cbfbfc978 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop1_t16_promote.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop1_t16_promote.s
@@ -67,71 +67,137 @@ v_ceil_f16 v5, v199 dpp8:[7,6,5,4,3,2,1,0]
v_ceil_f16 v5, v199 quad_perm:[3,2,1,0]
// GFX12: v_ceil_f16_e64_dpp v5, v199 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xdc,0xd5,0xfa,0x00,0x00,0x00,0xc7,0x1b,0x00,0xff]
-v_cos_f16 v128, 0xfe0b
-// GFX12: v_cos_f16_e64 v128, 0xfe0b ; encoding: [0x80,0x00,0xe1,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
+v_cos_f16 v128.h, 0xfe0b
+// GFX12: v_cos_f16_e64 v128.h, 0xfe0b op_sel:[0,1] ; encoding: [0x80,0x40,0xe1,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
-v_cos_f16 v255, -1
-// GFX12: v_cos_f16_e64 v255, -1 ; encoding: [0xff,0x00,0xe1,0xd5,0xc1,0x00,0x00,0x00]
+v_cos_f16 v128.l, 0xfe0b
+// GFX12: v_cos_f16_e64 v128.l, 0xfe0b ; encoding: [0x80,0x00,0xe1,0xd5,0xff,0x00,0x00,0x00,0x0b,0xfe,0x00,0x00]
-v_cos_f16 v255, 0.5
-// GFX12: v_cos_f16_e64 v255, 0.5 ; encoding: [0xff,0x00,0xe1,0xd5,0xf0,0x00,0x00,0x00]
+v_cos_f16 v255.h, -1
+// GFX12: v_cos_f16_e64 v255.h, -1 op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0xc1,0x00,0x00,0x00]
-v_cos_f16 v255, exec_hi
-// GFX12: v_cos_f16_e64 v255, exec_hi ; encoding: [0xff,0x00,0xe1,0xd5,0x7f,0x00,0x00,0x00]
+v_cos_f16 v255.h, 0.5
+// GFX12: v_cos_f16_e64 v255.h, 0.5 op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0xf0,0x00,0x00,0x00]
-v_cos_f16 v255, exec_lo
-// GFX12: v_cos_f16_e64 v255, exec_lo ; encoding: [0xff,0x00,0xe1,0xd5,0x7e,0x00,0x00,0x00]
+v_cos_f16 v255.h, exec_hi
+// GFX12: v_cos_f16_e64 v255.h, exec_hi op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x7f,0x00,0x00,0x00]
-v_cos_f16 v255, m0
-// GFX12: v_cos_f16_e64 v255, m0 ; encoding: [0xff,0x00,0xe1,0xd5,0x7d,0x00,0x00,0x00]
+v_cos_f16 v255.h, exec_lo
+// GFX12: v_cos_f16_e64 v255.h, exec_lo op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x7e,0x00,0x00,0x00]
-v_cos_f16 v255, null
-// GFX12: v_cos_f16_e64 v255, null ; encoding: [0xff,0x00,0xe1,0xd5,0x7c,0x00,0x00,0x00]
+v_cos_f16 v255.h, m0
+// GFX12: v_cos_f16_e64 v255.h, m0 op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x7d,0x00,0x00,0x00]
-v_cos_f16 v255, s1
-// GFX12: v_cos_f16_e64 v255, s1 ; encoding: [0xff,0x00,0xe1,0xd5,0x01,0x00,0x00,0x00]
+v_cos_f16 v255.h, null
+// GFX12: v_cos_f16_e64 v255.h, null op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x7c,0x00,0x00,0x00]
-v_cos_f16 v255, s105
-// GFX12: v_cos_f16_e64 v255, s105 ; encoding: [0xff,0x00,0xe1,0xd5,0x69,0x00,0x00,0x00]
+v_cos_f16 v255.h, s1
+// GFX12: v_cos_f16_e64 v255.h, s1 op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x01,0x00,0x00,0x00]
-v_cos_f16 v255, src_scc
-// GFX12: v_cos_f16_e64 v255, src_scc ; encoding: [0xff,0x00,0xe1,0xd5,0xfd,0x00,0x00,0x00]
+v_cos_f16 v255.h, s105
+// GFX12: v_cos_f16_e64 v255.h, s105 op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x69,0x00,0x00,0x00]
-v_cos_f16 v255, ttmp15
-// GFX12: v_cos_f16_e64 v255, ttmp15 ; encoding: [0xff,0x00,0xe1,0xd5,0x7b,0x00,0x00,0x00]
+v_cos_f16 v255.h, src_scc
+// GFX12: v_cos_f16_e64 v255.h, src_scc op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0xfd,0x00,0x00,0x00]
-v_cos_f16 v255, v1
-// GFX12: v_cos_f16_e64 v255, v1 ; encoding: [0xff,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00]
+v_cos_f16 v255.h, ttmp15
+// GFX12: v_cos_f16_e64 v255.h, ttmp15 op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x7b,0x00,0x00,0x00]
-v_cos_f16 v255, v1 dpp8:[7,6,5,4,3,2,1,0]
-// GFX12: v_cos_f16_e64_dpp v255, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
+v_cos_f16 v255.h, v1.h
+// GFX12: v_cos_f16_e64 v255.h, v1.h op_sel:[1,1] ; encoding: [0xff,0x48,0xe1,0xd5,0x01,0x01,0x00,0x00]
-v_cos_f16 v255, v1 quad_perm:[3,2,1,0]
-// GFX12: v_cos_f16_e64_dpp v255, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
+v_cos_f16 v255.h, v1.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: v_cos_f16_e64_dpp v255.h, v1.h op_sel:[1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x48,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
-v_cos_f16 v255, v127
-// GFX12: v_cos_f16_e64 v255, v127 ; encoding: [0xff,0x00,0xe1,0xd5,0x7f,0x01,0x00,0x00]
+v_cos_f16 v255.h, v1.h quad_perm:[3,2,1,0]
+// GFX12: v_cos_f16_e64_dpp v255.h, v1.h op_sel:[1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x48,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
-v_cos_f16 v255, v127 dpp8:[7,6,5,4,3,2,1,0]
-// GFX12: v_cos_f16_e64_dpp v255, v127 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x7f,0x77,0x39,0x05]
+v_cos_f16 v255.h, v127.h
+// GFX12: v_cos_f16_e64 v255.h, v127.h op_sel:[1,1] ; encoding: [0xff,0x48,0xe1,0xd5,0x7f,0x01,0x00,0x00]
-v_cos_f16 v255, v127 quad_perm:[3,2,1,0]
-// GFX12: v_cos_f16_e64_dpp v255, v127 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x7f,0x1b,0x00,0xff]
+v_cos_f16 v255.h, v127.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: v_cos_f16_e64_dpp v255.h, v127.h op_sel:[1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x48,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x7f,0x77,0x39,0x05]
-v_cos_f16 v255, vcc_hi
-// GFX12: v_cos_f16_e64 v255, vcc_hi ; encoding: [0xff,0x00,0xe1,0xd5,0x6b,0x00,0x00,0x00]
+v_cos_f16 v255.h, v127.h quad_perm:[3,2,1,0]
+// GFX12: v_cos_f16_e64_dpp v255.h, v127.h op_sel:[1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x48,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x7f,0x1b,0x00,0xff]
-v_cos_f16 v255, vcc_lo
-// GFX12: v_cos_f16_e64 v255, vcc_lo ; encoding: [0xff,0x00,0xe1,0xd5,0x6a,0x00,0x00,0x00]
+v_cos_f16 v255.h, vcc_hi
+// GFX12: v_cos_f16_e64 v255.h, vcc_hi op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x6b,0x00,0x00,0x00]
-v_cos_f16 v5, v199
-// GFX12: v_cos_f16_e64 v5, v199 ; encoding: [0x05,0x00,0xe1,0xd5,0xc7,0x01,0x00,0x00]
+v_cos_f16 v255.h, vcc_lo
+// GFX12: v_cos_f16_e64 v255.h, vcc_lo op_sel:[0,1] ; encoding: [0xff,0x40,0xe1,0xd5,0x6a,0x00,0x00,0x00]
-v_cos_f16 v5, v199 dpp8:[7,6,5,4,3,2,1,0]
-// GFX12: v_cos_f16_e64_dpp v5, v199 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0xc7,0x77,0x39,0x05]
+v_cos_f16 v255.l, -1
+// GFX12: v_cos_f16_e64 v255.l, -1 ; encoding: [0xff,0x00,0xe1,0xd5,0xc1,0x00,0x00,0x00]
-v_cos_f16 v5, v199 quad_perm:[3,2,1,0]
-// GFX12: v_cos_f16_e64_dpp v5, v199 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0xc7,0x1b,0x00,0xff]
+v_cos_f16 v255.l, 0.5
+// GFX12: v_cos_f16_e64 v255.l, 0.5 ; encoding: [0xff,0x00,0xe1,0xd5,0xf0,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, exec_hi
+// GFX12: v_cos_f16_e64 v255.l, exec_hi ; encoding: [0xff,0x00,0xe1,0xd5,0x7f,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, exec_lo
+// GFX12: v_cos_f16_e64 v255.l, exec_lo ; encoding: [0xff,0x00,0xe1,0xd5,0x7e,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, m0
+// GFX12: v_cos_f16_e64 v255.l, m0 ; encoding: [0xff,0x00,0xe1,0xd5,0x7d,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, null
+// GFX12: v_cos_f16_e64 v255.l, null ; encoding: [0xff,0x00,0xe1,0xd5,0x7c,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, s1
+// GFX12: v_cos_f16_e64 v255.l, s1 ; encoding: [0xff,0x00,0xe1,0xd5,0x01,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, s105
+// GFX12: v_cos_f16_e64 v255.l, s105 ; encoding: [0xff,0x00,0xe1,0xd5,0x69,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, src_scc
+// GFX12: v_cos_f16_e64 v255.l, src_scc ; encoding: [0xff,0x00,0xe1,0xd5,0xfd,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, ttmp15
+// GFX12: v_cos_f16_e64 v255.l, ttmp15 ; encoding: [0xff,0x00,0xe1,0xd5,0x7b,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, v1.l
+// GFX12: v_cos_f16_e64 v255.l, v1.l ; encoding: [0xff,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00]
+
+v_cos_f16 v255.l, v1.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: v_cos_f16_e64_dpp v255.l, v1.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
+
+v_cos_f16 v255.l, v1.l quad_perm:[3,2,1,0]
+// GFX12: v_cos_f16_e64_dpp v255.l, v1.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
+
+v_cos_f16 v255.l, v127.l
+// GFX12: v_cos_f16_e64 v255.l, v127.l ; encoding: [0xff,0x00,0xe1,0xd5,0x7f,0x01,0x00,0x00]
+
+v_cos_f16 v255.l, v127.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: v_cos_f16_e64_dpp v255.l, v127.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x7f,0x77,0x39,0x05]
+
+v_cos_f16 v255.l, v127.l quad_perm:[3,2,1,0]
+// GFX12: v_cos_f16_e64_dpp v255.l, v127.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x7f,0x1b,0x00,0xff]
+
+v_cos_f16 v255.l, vcc_hi
+// GFX12: v_cos_f16_e64 v255.l, vcc_hi ; encoding: [0xff,0x00,0xe1,0xd5,0x6b,0x00,0x00,0x00]
+
+v_cos_f16 v255.l, vcc_lo
+// GFX12: v_cos_f16_e64 v255.l, vcc_lo ; encoding: [0xff,0x00,0xe1,0xd5,0x6a,0x00,0x00,0x00]
+
+v_cos_f16 v5.h, v199.h
+// GFX12: v_cos_f16_e64 v5.h, v199.h op_sel:[1,1] ; encoding: [0x05,0x48,0xe1,0xd5,0xc7,0x01,0x00,0x00]
+
+v_cos_f16 v5.h, v199.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: v_cos_f16_e64_dpp v5.h, v199.h op_sel:[1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x48,0xe1,0xd5,0xe9,0x00,0x00,0x00,0xc7,0x77,0x39,0x05]
+
+v_cos_f16 v5.h, v199.h quad_perm:[3,2,1,0]
+// GFX12: v_cos_f16_e64_dpp v5.h, v199.h op_sel:[1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x48,0xe1,0xd5,0xfa,0x00,0x00,0x00,0xc7,0x1b,0x00,0xff]
+
+v_cos_f16 v5.l, v199.l
+// GFX12: v_cos_f16_e64 v5.l, v199.l ; encoding: [0x05,0x00,0xe1,0xd5,0xc7,0x01,0x00,0x00]
+
+v_cos_f16 v5.l, v199.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: v_cos_f16_e64_dpp v5.l, v199.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0xc7,0x77,0x39,0x05]
+
+v_cos_f16 v5.l, v199.l quad_perm:[3,2,1,0]
+// GFX12: v_cos_f16_e64_dpp v5.l, v199.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0xc7,0x1b,0x00,0xff]
v_cvt_f16_f32 v128.h, 0xaf123456
// GFX12: v_cvt_f16_f32_e64 v128.h, 0xaf123456 op_sel:[0,1] ; encoding: [0x80,0x40,0x8a,0xd5,0xff,0x00,0x00,0x00,0x56,0x34,0x12,0xaf]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1.s
index 015619d31504b5..b3530319f89973 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1.s
@@ -262,50 +262,59 @@ v_clz_i32_u32_e64 v5, src_scc
v_clz_i32_u32_e64 v255, 0xaf123456
// GFX12: v_clz_i32_u32_e64 v255, 0xaf123456 ; encoding: [0xff,0x00,0xb9,0xd5,0xff,0x00,0x00,0x00,0x56,0x34,0x12,0xaf]
-v_cos_f16_e64 v5, v1
-// GFX12: v_cos_f16_e64 v5, v1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00]
+v_cos_f16_e64 v5.l, v1.l
+// GFX12: v_cos_f16_e64 v5.l, v1.l ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00]
-v_cos_f16_e64 v5, v255
-// GFX12: v_cos_f16_e64 v5, v255 ; encoding: [0x05,0x00,0xe1,0xd5,0xff,0x01,0x00,0x00]
+v_cos_f16_e64 v5.l, v255.l
+// GFX12: v_cos_f16_e64 v5.l, v255.l ; encoding: [0x05,0x00,0xe1,0xd5,0xff,0x01,0x00,0x00]
-v_cos_f16_e64 v5, s1
-// GFX12: v_cos_f16_e64 v5, s1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, s1
+// GFX12: v_cos_f16_e64 v5.l, s1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x00,0x00,0x00]
-v_cos_f16_e64 v5, s105
-// GFX12: v_cos_f16_e64 v5, s105 ; encoding: [0x05,0x00,0xe1,0xd5,0x69,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, s105
+// GFX12: v_cos_f16_e64 v5.l, s105 ; encoding: [0x05,0x00,0xe1,0xd5,0x69,0x00,0x00,0x00]
-v_cos_f16_e64 v5, vcc_lo
-// GFX12: v_cos_f16_e64 v5, vcc_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x6a,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, vcc_lo
+// GFX12: v_cos_f16_e64 v5.l, vcc_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x6a,0x00,0x00,0x00]
-v_cos_f16_e64 v5, vcc_hi
-// GFX12: v_cos_f16_e64 v5, vcc_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x6b,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, vcc_hi
+// GFX12: v_cos_f16_e64 v5.l, vcc_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x6b,0x00,0x00,0x00]
-v_cos_f16_e64 v5, ttmp15
-// GFX12: v_cos_f16_e64 v5, ttmp15 ; encoding: [0x05,0x00,0xe1,0xd5,0x7b,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, ttmp15
+// GFX12: v_cos_f16_e64 v5.l, ttmp15 ; encoding: [0x05,0x00,0xe1,0xd5,0x7b,0x00,0x00,0x00]
-v_cos_f16_e64 v5, m0
-// GFX12: v_cos_f16_e64 v5, m0 ; encoding: [0x05,0x00,0xe1,0xd5,0x7d,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, m0
+// GFX12: v_cos_f16_e64 v5.l, m0 ; encoding: [0x05,0x00,0xe1,0xd5,0x7d,0x00,0x00,0x00]
-v_cos_f16_e64 v5, exec_lo
-// GFX12: v_cos_f16_e64 v5, exec_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x7e,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, exec_lo
+// GFX12: v_cos_f16_e64 v5.l, exec_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x7e,0x00,0x00,0x00]
-v_cos_f16_e64 v5, exec_hi
-// GFX12: v_cos_f16_e64 v5, exec_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x7f,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, exec_hi
+// GFX12: v_cos_f16_e64 v5.l, exec_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x7f,0x00,0x00,0x00]
-v_cos_f16_e64 v5, null
-// GFX12: v_cos_f16_e64 v5, null ; encoding: [0x05,0x00,0xe1,0xd5,0x7c,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, null
+// GFX12: v_cos_f16_e64 v5.l, null ; encoding: [0x05,0x00,0xe1,0xd5,0x7c,0x00,0x00,0x00]
-v_cos_f16_e64 v5, -1
-// GFX12: v_cos_f16_e64 v5, -1 ; encoding: [0x05,0x00,0xe1,0xd5,0xc1,0x00,0x00,0x00]
+v_cos_f16_e64 v5.l, -1
+// GFX12: v_cos_f16_e64 v5.l, -1 ; encoding: [0x05,0x00,0xe1,0xd5,0xc1,0x00,0x00,0x00]
-v_cos_f16_e64 v5, 0.5 mul:2
-// GFX12: v_cos_f16_e64 v5, 0.5 mul:2 ; encoding: [0x05,0x00,0xe1,0xd5,0xf0,0x00,0x00,0x08]
+v_cos_f16_e64 v5.l, 0.5 mul:2
+// GFX12: v_cos_f16_e64 v5.l, 0.5 mul:2 ; encoding: [0x05,0x00,0xe1,0xd5,0xf0,0x00,0x00,0x08]
-v_cos_f16_e64 v5, src_scc mul:4
-// GFX12: v_cos_f16_e64 v5, src_scc mul:4 ; encoding: [0x05,0x00,0xe1,0xd5,0xfd,0x00,0x00,0x10]
+v_cos_f16_e64 v5.l, src_scc mul:4
+// GFX12: v_cos_f16_e64 v5.l, src_scc mul:4 ; encoding: [0x05,0x00,0xe1,0xd5,0xfd,0x00,0x00,0x10]
-v_cos_f16_e64 v255, -|0xfe0b| clamp div:2
-// GFX12: v_cos_f16_e64 v255, -|0xfe0b| clamp div:2 ; encoding: [0xff,0x81,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00]
+v_cos_f16_e64 v255.l, -|0xfe0b| clamp div:2
+// GFX12: v_cos_f16_e64 v255.l, -|0xfe0b| clamp div:2 ; encoding: [0xff,0x81,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00]
+
+v_cos_f16_e64 v5.h, v1.h
+// GFX12: v_cos_f16_e64 v5.h, v1.h op_sel:[1,1] ; encoding: [0x05,0x48,0xe1,0xd5,0x01,0x01,0x00,0x00]
+
+v_cos_f16_e64 v5.l, v255.h
+// GFX12: v_cos_f16_e64 v5.l, v255.h op_sel:[1,0] ; encoding: [0x05,0x08,0xe1,0xd5,0xff,0x01,0x00,0x00]
+
+v_cos_f16_e64 v255.h, -|0xfe0b| clamp div:2
+// GFX12: v_cos_f16_e64 v255.h, -|0xfe0b| op_sel:[0,1] clamp div:2 ; encoding: [0xff,0xc1,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00]
v_cos_f32_e64 v5, v1
// GFX12: v_cos_f32_e64 v5, v1 ; encoding: [0x05,0x00,0xb6,0xd5,0x01,0x01,0x00,0x00]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1_dpp16.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1_dpp16.s
index 160bc3fc6afc7c..c2101d087aab4d 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1_dpp16.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1_dpp16.s
@@ -211,47 +211,56 @@ v_clz_i32_u32_e64_dpp v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1
v_clz_i32_u32_e64_dpp v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX12: v_clz_i32_u32_e64_dpp v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0xb9,0xd5,0xfa,0x00,0x00,0x00,0xff,0x6f,0x05,0x30]
-v_cos_f16_e64_dpp v5, v1 quad_perm:[3,2,1,0]
-// GFX12: v_cos_f16_e64_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l quad_perm:[3,2,1,0]
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
-v_cos_f16_e64_dpp v5, v1 quad_perm:[0,1,2,3]
-// GFX12: v_cos_f16_e64_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0xe4,0x00,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l quad_perm:[0,1,2,3]
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0xe4,0x00,0xff]
-v_cos_f16_e64_dpp v5, v1 row_mirror
-// GFX12: v_cos_f16_e64_dpp v5, v1 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x40,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_mirror
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x40,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 row_half_mirror
-// GFX12: v_cos_f16_e64_dpp v5, v1 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x41,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_half_mirror
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x41,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 row_shl:1
-// GFX12: v_cos_f16_e64_dpp v5, v1 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x01,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_shl:1
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x01,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 row_shl:15
-// GFX12: v_cos_f16_e64_dpp v5, v1 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x0f,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_shl:15
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.l row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x0f,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 row_shr:1
-// GFX12: v_cos_f16_e64_dpp v5, v1 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x11,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_shr:1
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.l row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x11,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 row_shr:15
-// GFX12: v_cos_f16_e64_dpp v5, v1 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1f,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_shr:15
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.l row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1f,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 row_ror:1
-// GFX12: v_cos_f16_e64_dpp v5, v1 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x21,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_ror:1
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.l row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x21,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 row_ror:15
-// GFX12: v_cos_f16_e64_dpp v5, v1 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x2f,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_ror:15
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.l row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x2f,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 row_share:0 row_mask:0xf bank_mask:0xf
-// GFX12: v_cos_f16_e64_dpp v5, v1 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x50,0x01,0xff]
+v_cos_f16_e64_dpp v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x50,0x01,0xff]
-v_cos_f16_e64_dpp v5, v1 mul:2 row_share:15 row_mask:0x0 bank_mask:0x1
-// GFX12: v_cos_f16_e64_dpp v5, v1 mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01]
+v_cos_f16_e64_dpp v5.l, v1.l mul:2 row_share:15 row_mask:0x0 bank_mask:0x1
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.l mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01]
-v_cos_f16_e64_dpp v5, v1 mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
-// GFX12: v_cos_f16_e64_dpp v5, v1 mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x09,0x13]
+v_cos_f16_e64_dpp v5.l, v1.l mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.l mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x09,0x13]
-v_cos_f16_e64_dpp v255, -|v255| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
-// GFX12: v_cos_f16_e64_dpp v255, -|v255| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x05,0x30]
+v_cos_f16_e64_dpp v255.l, -|v255.l| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
+// GFX12: v_cos_f16_e64_dpp v255.l, -|v255.l| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x05,0x30]
+
+v_cos_f16_e64_dpp v5.h, v1.h mul:2 row_share:15 row_mask:0x0 bank_mask:0x1
+// GFX12: v_cos_f16_e64_dpp v5.h, v1.h op_sel:[1,1] mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x48,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01]
+
+v_cos_f16_e64_dpp v5.l, v1.h mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.h op_sel:[1,0] mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x05,0x08,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x09,0x13]
+
+v_cos_f16_e64_dpp v255.h, -|v255.l| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
+// GFX12: v_cos_f16_e64_dpp v255.h, -|v255.l| op_sel:[0,1] clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0xc1,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x05,0x30]
v_cos_f32_e64_dpp v5, v1 quad_perm:[3,2,1,0]
// GFX12: v_cos_f32_e64_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xb6,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1_dpp8.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1_dpp8.s
index c9ea7cdf1512ed..c11fe758bf949a 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1_dpp8.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop1_dpp8.s
@@ -52,17 +52,26 @@ v_clz_i32_u32_e64_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] fi:1
v_clz_i32_u32_e64_dpp v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX12: v_clz_i32_u32_e64_dpp v255, v255 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x00,0xb9,0xd5,0xe9,0x00,0x00,0x00,0xff,0x00,0x00,0x00]
-v_cos_f16_e64_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0]
-// GFX12: v_cos_f16_e64_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
+v_cos_f16_e64_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
-v_cos_f16_e64_dpp v5, v1 mul:2 dpp8:[7,6,5,4,3,2,1,0]
-// GFX12: v_cos_f16_e64_dpp v5, v1 mul:2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05]
+v_cos_f16_e64_dpp v5.l, v1.l mul:2 dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.l mul:2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05]
-v_cos_f16_e64_dpp v5, v1 mul:4 dpp8:[7,6,5,4,3,2,1,0] fi:1
-// GFX12: v_cos_f16_e64_dpp v5, v1 mul:4 dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x05,0x00,0xe1,0xd5,0xea,0x00,0x00,0x10,0x01,0x77,0x39,0x05]
+v_cos_f16_e64_dpp v5.l, v1.l mul:4 dpp8:[7,6,5,4,3,2,1,0] fi:1
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.l mul:4 dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x05,0x00,0xe1,0xd5,0xea,0x00,0x00,0x10,0x01,0x77,0x39,0x05]
-v_cos_f16_e64_dpp v255, -|v255| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:0
-// GFX12: v_cos_f16_e64_dpp v255, -|v255| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x81,0xe1,0xd5,0xe9,0x00,0x00,0x38,0xff,0x00,0x00,0x00]
+v_cos_f16_e64_dpp v255.l, -|v255.l| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:0
+// GFX12: v_cos_f16_e64_dpp v255.l, -|v255.l| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x81,0xe1,0xd5,0xe9,0x00,0x00,0x38,0xff,0x00,0x00,0x00]
+
+v_cos_f16_e64_dpp v5.h, v1.h mul:2 dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: v_cos_f16_e64_dpp v5.h, v1.h op_sel:[1,1] mul:2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x48,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05]
+
+v_cos_f16_e64_dpp v5.l, v1.h mul:4 dpp8:[7,6,5,4,3,2,1,0] fi:1
+// GFX12: v_cos_f16_e64_dpp v5.l, v1.h op_sel:[1,0] mul:4 dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0x05,0x08,0xe1,0xd5,0xea,0x00,0x00,0x10,0x01,0x77,0x39,0x05]
+
+v_cos_f16_e64_dpp v255.h, -|v255.l| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:0
+// GFX12: v_cos_f16_e64_dpp v255.h, -|v255.l| op_sel:[0,1] clamp div:2 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0xc1,0xe1,0xd5,0xe9,0x00,0x00,0x38,0xff,0x00,0x00,0x00]
v_cos_f32_e64_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0]
// GFX12: v_cos_f32_e64_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xb6,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1.txt
index 61e529abf44550..47cb1fccb6ebcb 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1.txt
@@ -287,49 +287,82 @@
# GFX11: v_clz_i32_u32_e32 v255, 0xaf123456 ; encoding: [0xff,0x72,0xfe,0x7f,0x56,0x34,0x12,0xaf]
0x01,0xc3,0x0a,0x7e
-# GFX11: v_cos_f16_e32 v5, v1 ; encoding: [0x01,0xc3,0x0a,0x7e]
+# GFX11-REAL16: v_cos_f16_e32 v5.l, v1.l ; encoding: [0x01,0xc3,0x0a,0x7e]
+# GFX11-FAKE16: v_cos_f16_e32 v5, v1 ; encoding: [0x01,0xc3,0x0a,0x7e]
0x7f,0xc3,0x0a,0x7e
-# GFX11: v_cos_f16_e32 v5, v127 ; encoding: [0x7f,0xc3,0x0a,0x7e]
+# GFX11-REAL16: v_cos_f16_e32 v5.l, v127.l ; encoding: [0x7f,0xc3,0x0a,0x7e]
+# GFX11-FAKE16: v_cos_f16_e32 v5, v127 ; encoding: [0x7f,0xc3,0x0a,0x7e]
0x01,0xc2,0x0a,0x7e
-# GFX11: v_cos_f16_e32 v5, s1 ; encoding: [0x01,0xc2,0x0a,0x7e]
+# GFX11-REAL16: v_cos_f16_e32 v5.l, s1 ; encoding: [0x01,0xc2,0x0a,0x7e]
+# GFX11-FAKE16: v_cos_f16_e32 v5, s1 ; encoding: [0x01,0xc2,0x0a,0x7e]
0x69,0xc2,0x0a,0x7e
-# GFX11: v_cos_f16_e32 v5, s105 ; encoding: [0x69,0xc2,0x0a,0x7e]
+# GFX11-REAL16: v_cos_f16_e32 v5.l, s105 ; encoding: [0x69,0xc2,0x0a,0x7e]
+# GFX11-FAKE16: v_cos_f16_e32 v5, s105 ; encoding: [0x69,0xc2,0x0a,0x7e]
0x6a,0xc2,0x0a,0x7e
-# GFX11: v_cos_f16_e32 v5, vcc_lo ; encoding: [0x6a,0xc2,0x0a,0x7e]
+# GFX11-REAL16: v_cos_f16_e32 v5.l, vcc_lo ; encoding: [0x6a,0xc2,0x0a,0x7e]
+# GFX11-FAKE16: v_cos_f16_e32 v5, vcc_lo ; encoding: [0x6a,0xc2,0x0a,0x7e]
0x6b,0xc2,0x0a,0x7e
-# GFX11: v_cos_f16_e32 v5, vcc_hi ; encoding: [0x6b,0xc2,0x0a,0x7e]
+# GFX11-REAL16: v_cos_f16_e32 v5.l, vcc_hi ; encoding: [0x6b,0xc2,0x0a,0x7e]
+# GFX11-FAKE16: v_cos_f16_e32 v5, vcc_hi ; encoding: [0x6b,0xc2,0x0a,0x7e]
0x7b,0xc2,0x0a,0x7e
-# GFX11: v_cos_f16_e32 v5, ttmp15 ; encoding: [0x7b,0xc2,0x0a,0x7e]
+# GFX11-REAL16: v_cos_f16_e32 v5.l, ttmp15 ; encoding: [0x7b,0xc2,0x0a,0x7e]
+# GFX11-FAKE16: v_cos_f16_e32 v5, ttmp15 ; encoding: [0x7b,0xc2,0x0a,0x7e]
0x7d,0xc2,0x0a,0x7e
-# GFX11: v_cos_f16_e32 v5, m0 ; encoding: [0x7d,0xc2,0x0a,0x7e]
+# GFX11-REAL16: v_cos_f16_e32 v5.l, m0 ; encoding: [0x7d,0xc2,0x0a,0x7e]
+# GFX11-FAKE16: v_cos_f16_e32 v5, m0 ; encoding: [0x7d,0xc2,0x0a,0x7e]
0x7e,0xc2,0x0a,0x7e
-# GFX11: v_cos_f16_e32 v5, exec_lo ; encoding: [0x7e,0xc2,0x0a,0x7e]
+# GFX11-REAL16: v_cos_f16_e32 v5.l, exec_lo ; encoding: [0x7e,0xc2,0x0a,0x7e]
+# GFX11-FAKE16: v_cos_f16_e32 v5, exec_lo ; encoding: [0x7e,0xc2,0x0a,0x7e]
0x7f,0xc2,0x0a,0x7e
-# GFX11: v_cos_f16_e32 v5, exec_hi ; encoding: [0x7f,0xc2,0x0a,0x7e]
+# GFX11-REAL16: v_cos_f16_e32 v5.l, exec_hi ; encoding: [0x7f,0xc2,0x0a,0x7e]
+# GFX11-FAKE16: v_cos_f16_e32 v5, exec_hi ; encoding: [0x7f,0xc2,0x0a,0x7e]
0x7c,0xc2,0x0a,0x7e
-# GFX11: v_cos_f16_e32 v5, null ; encoding: [0x7c,0xc2,0x0a,0x7e]
+# GFX11-REAL16: v_cos_f16_e32 v5.l, null ; encoding: [0x7c,0xc2,0x0a,0x7e]
+# GFX11-FAKE16: v_cos_f16_e32 v5, null ; encoding: [0x7c,0xc2,0x0a,0x7e]
0xc1,0xc2,0x0a,0x7e
-# GFX11: v_cos_f16_e32 v5, -1 ; encoding: [0xc1,0xc2,0x0a,0x7e]
+# GFX11-REAL16: v_cos_f16_e32 v5.l, -1 ; encoding: [0xc1,0xc2,0x0a,0x7e]
+# GFX11-FAKE16: v_cos_f16_e32 v5, -1 ; encoding: [0xc1,0xc2,0x0a,0x7e]
0xf0,0xc2,0x0a,0x7e
-# GFX11: v_cos_f16_e32 v5, 0.5 ; encoding: [0xf0,0xc2,0x0a,0x7e]
+# GFX11-REAL16: v_cos_f16_e32 v5.l, 0.5 ; encoding: [0xf0,0xc2,0x0a,0x7e]
+# GFX11-FAKE16: v_cos_f16_e32 v5, 0.5 ; encoding: [0xf0,0xc2,0x0a,0x7e]
0xfd,0xc2,0x0a,0x7e
-# GFX11: v_cos_f16_e32 v5, src_scc ; encoding: [0xfd,0xc2,0x0a,0x7e]
+# GFX11-REAL16: v_cos_f16_e32 v5.l, src_scc ; encoding: [0xfd,0xc2,0x0a,0x7e]
+# GFX11-FAKE16: v_cos_f16_e32 v5, src_scc ; encoding: [0xfd,0xc2,0x0a,0x7e]
0xff,0xc2,0xfe,0x7e,0x0b,0xfe,0x00,0x00
-# GFX11: v_cos_f16_e32 v127, 0xfe0b ; encoding: [0xff,0xc2,0xfe,0x7e,0x0b,0xfe,0x00,0x00]
+# GFX11-REAL16: v_cos_f16_e32 v127.l, 0xfe0b ; encoding: [0xff,0xc2,0xfe,0x7e,0x0b,0xfe,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e32 v127, 0xfe0b ; encoding: [0xff,0xc2,0xfe,0x7e,0x0b,0xfe,0x00,0x00]
+
+0x81,0xc3,0x0a,0x7e
+# GFX11-REAL16: v_cos_f16_e32 v5.l, v1.h ; encoding: [0x81,0xc3,0x0a,0x7e]
+# GFX11-FAKE16: v_cos_f16_e32 v5, v129/*Invalid register, operand has 'VS_32_Lo128' register class*/ ; encoding: [0x81,0xc3,0x0a,0x7e]
+
+0xff,0xc3,0x0a,0x7e
+# GFX11-REAL16: v_cos_f16_e32 v5.l, v127.h ; encoding: [0xff,0xc3,0x0a,0x7e]
+# GFX11-FAKE16: v_cos_f16_e32 v5, v255/*Invalid register, operand has 'VS_32_Lo128' register class*/ ; encoding: [0xff,0xc3,0x0a,0x7e]
+
+0xf0,0xc2,0xfe,0x7e
+# GFX11-REAL16: v_cos_f16_e32 v127.l, 0.5 ; encoding: [0xf0,0xc2,0xfe,0x7e]
+# GFX11-FAKE16: v_cos_f16_e32 v127, 0.5 ; encoding: [0xf0,0xc2,0xfe,0x7e]
+
+0xfd,0xc2,0x0a,0x7f
+# GFX11-REAL16: v_cos_f16_e32 v5.h, src_scc ; encoding: [0xfd,0xc2,0x0a,0x7f]
+
+0xff,0xc2,0xfe,0x7f,0x0b,0xfe,0x00,0x00
+# GFX11-REAL16: v_cos_f16_e32 v127.h, 0xfe0b ; encoding: [0xff,0xc2,0xfe,0x7f,0x0b,0xfe,0x00,0x00]
0x01,0x6d,0x0a,0x7e
# GFX11: v_cos_f32_e32 v5, v1 ; encoding: [0x01,0x6d,0x0a,0x7e]
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1_dpp16.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1_dpp16.txt
index 1075a3eecd5407..7a725f8d13584e 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1_dpp16.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1_dpp16.txt
@@ -229,46 +229,72 @@
# GFX11: v_clz_i32_u32_dpp v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xfa,0x72,0xfe,0x7f,0xff,0x6f,0x0d,0x30]
0xfa,0xc2,0x0a,0x7e,0x01,0x1b,0x00,0xff
-# GFX11: v_cos_f16_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1b,0x00,0xff]
+# GFX11-REAL16: v_cos_f16_dpp v5.l, v1.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1b,0x00,0xff]
+# GFX11-FAKE16: v_cos_f16_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1b,0x00,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x00,0xff
-# GFX11: v_cos_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x00,0xff]
+# GFX11-REAL16: v_cos_f16_dpp v5.l, v1.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x00,0xff]
+# GFX11-FAKE16: v_cos_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x00,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x40,0x01,0xff
-# GFX11: v_cos_f16_dpp v5, v1 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x40,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_dpp v5.l, v1.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x40,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_dpp v5, v1 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x40,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x41,0x01,0xff
-# GFX11: v_cos_f16_dpp v5, v1 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x41,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_dpp v5.l, v1.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x41,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_dpp v5, v1 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x41,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x01,0x01,0xff
-# GFX11: v_cos_f16_dpp v5, v1 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x01,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_dpp v5.l, v1.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x01,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_dpp v5, v1 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x01,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x0f,0x01,0xff
-# GFX11: v_cos_f16_dpp v5, v1 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x0f,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_dpp v5.l, v1.l row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x0f,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_dpp v5, v1 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x0f,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x11,0x01,0xff
-# GFX11: v_cos_f16_dpp v5, v1 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x11,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_dpp v5.l, v1.l row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x11,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_dpp v5, v1 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x11,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x1f,0x01,0xff
-# GFX11: v_cos_f16_dpp v5, v1 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1f,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_dpp v5.l, v1.l row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1f,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_dpp v5, v1 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1f,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x21,0x01,0xff
-# GFX11: v_cos_f16_dpp v5, v1 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x21,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_dpp v5.l, v1.l row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x21,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_dpp v5, v1 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x21,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x2f,0x01,0xff
-# GFX11: v_cos_f16_dpp v5, v1 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x2f,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_dpp v5.l, v1.l row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x2f,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_dpp v5, v1 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x2f,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x50,0x01,0xff
-# GFX11: v_cos_f16_dpp v5, v1 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x50,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_dpp v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x50,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_dpp v5, v1 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x50,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x5f,0x01,0x01
-# GFX11: v_cos_f16_dpp v5, v1 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x5f,0x01,0x01]
+# GFX11-REAL16: v_cos_f16_dpp v5.l, v1.l row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x5f,0x01,0x01]
+# GFX11-FAKE16: v_cos_f16_dpp v5, v1 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x5f,0x01,0x01]
0xfa,0xc2,0x0a,0x7e,0x01,0x60,0x01,0x13
-# GFX11: v_cos_f16_dpp v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x60,0x01,0x13]
+# GFX11-REAL16: v_cos_f16_dpp v5.l, v1.l row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x60,0x01,0x13]
+# GFX11-FAKE16: v_cos_f16_dpp v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x60,0x01,0x13]
0xfa,0xc2,0xfe,0x7e,0x7f,0x6f,0x3d,0x30
-# GFX11: v_cos_f16_dpp v127, -|v127| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xfa,0xc2,0xfe,0x7e,0x7f,0x6f,0x3d,0x30]
+# GFX11-REAL16: v_cos_f16_dpp v127.l, -|v127.l| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xfa,0xc2,0xfe,0x7e,0x7f,0x6f,0x3d,0x30]
+# GFX11-FAKE16: v_cos_f16_dpp v127, -|v127| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xfa,0xc2,0xfe,0x7e,0x7f,0x6f,0x3d,0x30]
+
+0xfa,0xc2,0xfe,0x7e,0x7f,0x5f,0x01,0x01
+# GFX11-REAL16: v_cos_f16_dpp v127.l, v127.l row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xc2,0xfe,0x7e,0x7f,0x5f,0x01,0x01]
+# GFX11-FAKE16: v_cos_f16_dpp v127, v127 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xc2,0xfe,0x7e,0x7f,0x5f,0x01,0x01]
+
+0xfa,0xc2,0x0a,0x7f,0x81,0x60,0x01,0x13
+# GFX11-REAL16: v_cos_f16_dpp v5.h, v1.h row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0xfa,0xc2,0x0a,0x7f,0x81,0x60,0x01,0x13]
+# GFX11-FAKE16: v_mul_i32_i24_e32 v128, 1, v176 ; encoding: [0x81,0x60,0x01,0x13]
+
+0xfa,0xc2,0xfe,0x7f,0xff,0x6f,0x3d,0x30
+# GFX11-REAL16: v_cos_f16_dpp v127.h, -|v127.h| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xfa,0xc2,0xfe,0x7f,0xff,0x6f,0x3d,0x30]
+# GFX11-FAKE16: v_lshlrev_b32_e32 v30, v255, v183 ; encoding: [0xff,0x6f,0x3d,0x30]
0xfa,0x6c,0x0a,0x7e,0x01,0x1b,0x00,0xff
# GFX11: v_cos_f32_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x6c,0x0a,0x7e,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1_dpp8.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1_dpp8.txt
index 051dd348e9a380..7e446f433d923b 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1_dpp8.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1_dpp8.txt
@@ -43,10 +43,23 @@
# GFX11: v_clz_i32_u32_dpp v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xea,0x72,0xfe,0x7f,0xff,0x00,0x00,0x00]
0xe9,0xc2,0x0a,0x7e,0x01,0x77,0x39,0x05
-# GFX11: v_cos_f16_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xc2,0x0a,0x7e,0x01,0x77,0x39,0x05]
+# GFX11-REAL16: v_cos_f16_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xc2,0x0a,0x7e,0x01,0x77,0x39,0x05]
+# GFX11-FAKE16: v_cos_f16_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xc2,0x0a,0x7e,0x01,0x77,0x39,0x05]
0xea,0xc2,0xfe,0x7e,0x7f,0x00,0x00,0x00
-# GFX11: v_cos_f16_dpp v127, v127 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xea,0xc2,0xfe,0x7e,0x7f,0x00,0x00,0x00]
+# GFX11-REAL16: v_cos_f16_dpp v127.l, v127.l dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xea,0xc2,0xfe,0x7e,0x7f,0x00,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_dpp v127, v127 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xea,0xc2,0xfe,0x7e,0x7f,0x00,0x00,0x00]
+
+0xe9,0xc2,0xfe,0x7e,0x7f,0x77,0x39,0x05
+# GFX11-REAL16: v_cos_f16_dpp v127.l, v127.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xc2,0xfe,0x7e,0x7f,0x77,0x39,0x05]
+# GFX11-FAKE16: v_cos_f16_dpp v127, v127 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xc2,0xfe,0x7e,0x7f,0x77,0x39,0x05]
+
+0xe9,0xc2,0x0a,0x7f,0x81,0x77,0x39,0x05
+# GFX11-REAL16: v_cos_f16_dpp v5.h, v1.h dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xc2,0x0a,0x7f,0x81,0x77,0x39,0x05]
+# GFX11-FAKE16: v_dot2acc_f32_f16 v156, v129, v187 ; encoding: [0x81,0x77,0x39,0x05]
+
+0xea,0xc2,0xfe,0x7f,0xff,0x00,0x00,0x00
+# GFX11-REAL16: v_cos_f16_dpp v127.h, v127.h dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xea,0xc2,0xfe,0x7f,0xff,0x00,0x00,0x00]
0xe9,0x6c,0x0a,0x7e,0x01,0x77,0x39,0x05
# GFX11: v_cos_f32_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0x6c,0x0a,0x7e,0x01,0x77,0x39,0x05]
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp16_from_vop1.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp16_from_vop1.txt
index 2666b758344c61..80eff5aea4d3a7 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp16_from_vop1.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp16_from_vop1.txt
@@ -239,46 +239,72 @@
# GFX11: v_clz_i32_u32_e64_dpp v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x00,0xb9,0xd5,0xfa,0x00,0x00,0x00,0xff,0x6f,0x0d,0x30]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff
-# GFX11: v_cos_f16_e64_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0xe4,0x00,0xff
-# GFX11: v_cos_f16_e64_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0xe4,0x00,0xff]
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0xe4,0x00,0xff]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0xe4,0x00,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x40,0x01,0xff
-# GFX11: v_cos_f16_e64_dpp v5, v1 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x40,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x40,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x40,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x41,0x01,0xff
-# GFX11: v_cos_f16_e64_dpp v5, v1 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x41,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x41,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x41,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x01,0x01,0xff
-# GFX11: v_cos_f16_e64_dpp v5, v1 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x01,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x01,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x01,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x0f,0x01,0xff
-# GFX11: v_cos_f16_e64_dpp v5, v1 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x0f,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x0f,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x0f,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x11,0x01,0xff
-# GFX11: v_cos_f16_e64_dpp v5, v1 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x11,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x11,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x11,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1f,0x01,0xff
-# GFX11: v_cos_f16_e64_dpp v5, v1 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1f,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1f,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1f,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x21,0x01,0xff
-# GFX11: v_cos_f16_e64_dpp v5, v1 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x21,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x21,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x21,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x2f,0x01,0xff
-# GFX11: v_cos_f16_e64_dpp v5, v1 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x2f,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x2f,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x2f,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x50,0x01,0xff
-# GFX11: v_cos_f16_e64_dpp v5, v1 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x50,0x01,0xff]
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x50,0x01,0xff]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x50,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01
-# GFX11: v_cos_f16_e64_dpp v5, v1 mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01]
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.l mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x01,0x13
-# GFX11: v_cos_f16_e64_dpp v5, v1 mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x01,0x13]
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.l mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x01,0x13]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x01,0x13]
0xff,0x81,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x0d,0x30
-# GFX11: v_cos_f16_e64_dpp v255, -|v255| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x0d,0x30]
+# GFX11-REAL16: v_cos_f16_e64_dpp v255.l, -|v255.l| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x0d,0x30]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v255, -|v255| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x0d,0x30]
+
+0x05,0x48,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.h, v1.h op_sel:[1,1] mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x48,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01]
+
+0x05,0x08,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x01,0x13
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.h op_sel:[1,0] mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x08,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x01,0x13]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x01,0x13]
+
+0xff,0xc1,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x0d,0x30
+# GFX11-REAL16: v_cos_f16_e64_dpp v255.h, -|v255.l| op_sel:[0,1] clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc1,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x0d,0x30]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v255, -|v255| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x0d,0x30]
0x05,0x00,0xb6,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff
# GFX11: v_cos_f32_e64_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xb6,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp8_from_vop1.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp8_from_vop1.txt
index c19947c4bd6ff1..c3827791624d54 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp8_from_vop1.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp8_from_vop1.txt
@@ -61,16 +61,32 @@
# GFX11: v_clz_i32_u32_e64_dpp v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x00,0xb9,0xd5,0xea,0x00,0x00,0x00,0xff,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05
-# GFX11: v_cos_f16_e64_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05
-# GFX11: v_cos_f16_e64_dpp v5, v1 mul:2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05]
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.l mul:2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 mul:2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05]
0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x10,0x01,0x77,0x39,0x05
-# GFX11: v_cos_f16_e64_dpp v5, v1 mul:4 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x10,0x01,0x77,0x39,0x05]
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.l mul:4 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x10,0x01,0x77,0x39,0x05]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 mul:4 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x10,0x01,0x77,0x39,0x05]
0xff,0x81,0xe1,0xd5,0xea,0x00,0x00,0x38,0xff,0x00,0x00,0x00
-# GFX11: v_cos_f16_e64_dpp v255, -|v255| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xea,0x00,0x00,0x38,0xff,0x00,0x00,0x00]
+# GFX11-REAL16: v_cos_f16_e64_dpp v255.l, -|v255.l| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xea,0x00,0x00,0x38,0xff,0x00,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v255, -|v255| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xea,0x00,0x00,0x38,0xff,0x00,0x00,0x00]
+
+0x05,0x48,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.h, v1.h op_sel:[1,1] mul:2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x48,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 mul:2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05]
+
+0x05,0x08,0xe1,0xd5,0xe9,0x00,0x00,0x10,0x01,0x77,0x39,0x05
+# GFX11-REAL16: v_cos_f16_e64_dpp v5.l, v1.h op_sel:[1,0] mul:4 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x08,0xe1,0xd5,0xe9,0x00,0x00,0x10,0x01,0x77,0x39,0x05]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v5, v1 mul:4 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x10,0x01,0x77,0x39,0x05]
+
+0xff,0xc1,0xe1,0xd5,0xea,0x00,0x00,0x38,0xff,0x00,0x00,0x00
+# GFX11-REAL16: v_cos_f16_e64_dpp v255.h, -|v255.l| op_sel:[0,1] clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc1,0xe1,0xd5,0xea,0x00,0x00,0x38,0xff,0x00,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64_dpp v255, -|v255| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xea,0x00,0x00,0x38,0xff,0x00,0x00,0x00]
0x05,0x00,0xb6,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05
# GFX11: v_cos_f32_e64_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xb6,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_from_vop1.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_from_vop1.txt
index 3df206ccf522e7..2781c55f659e59 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_from_vop1.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_from_vop1.txt
@@ -281,49 +281,76 @@
# GFX11: v_clz_i32_u32_e64 v255, 0xaf123456 ; encoding: [0xff,0x00,0xb9,0xd5,0xff,0x00,0x00,0x00,0x56,0x34,0x12,0xaf]
0x05,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00
-# GFX11: v_cos_f16_e64 v5, v1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00]
+# GFX11-REAL16: v_cos_f16_e64 v5.l, v1.l ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64 v5, v1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00]
0x05,0x00,0xe1,0xd5,0xff,0x01,0x00,0x00
-# GFX11: v_cos_f16_e64 v5, v255 ; encoding: [0x05,0x00,0xe1,0xd5,0xff,0x01,0x00,0x00]
+# GFX11-REAL16: v_cos_f16_e64 v5.l, v255.l ; encoding: [0x05,0x00,0xe1,0xd5,0xff,0x01,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64 v5, v255 ; encoding: [0x05,0x00,0xe1,0xd5,0xff,0x01,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x01,0x00,0x00,0x00
-# GFX11: v_cos_f16_e64 v5, s1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x00,0x00,0x00]
+# GFX11-REAL16: v_cos_f16_e64 v5.l, s1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x00,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64 v5, s1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x69,0x00,0x00,0x00
-# GFX11: v_cos_f16_e64 v5, s105 ; encoding: [0x05,0x00,0xe1,0xd5,0x69,0x00,0x00,0x00]
+# GFX11-REAL16: v_cos_f16_e64 v5.l, s105 ; encoding: [0x05,0x00,0xe1,0xd5,0x69,0x00,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64 v5, s105 ; encoding: [0x05,0x00,0xe1,0xd5,0x69,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x6a,0x00,0x00,0x00
-# GFX11: v_cos_f16_e64 v5, vcc_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x6a,0x00,0x00,0x00]
+# GFX11-REAL16: v_cos_f16_e64 v5.l, vcc_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x6a,0x00,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64 v5, vcc_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x6a,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x6b,0x00,0x00,0x00
-# GFX11: v_cos_f16_e64 v5, vcc_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x6b,0x00,0x00,0x00]
+# GFX11-REAL16: v_cos_f16_e64 v5.l, vcc_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x6b,0x00,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64 v5, vcc_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x6b,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x7b,0x00,0x00,0x00
-# GFX11: v_cos_f16_e64 v5, ttmp15 ; encoding: [0x05,0x00,0xe1,0xd5,0x7b,0x00,0x00,0x00]
+# GFX11-REAL16: v_cos_f16_e64 v5.l, ttmp15 ; encoding: [0x05,0x00,0xe1,0xd5,0x7b,0x00,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64 v5, ttmp15 ; encoding: [0x05,0x00,0xe1,0xd5,0x7b,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x7d,0x00,0x00,0x00
-# GFX11: v_cos_f16_e64 v5, m0 ; encoding: [0x05,0x00,0xe1,0xd5,0x7d,0x00,0x00,0x00]
+# GFX11-REAL16: v_cos_f16_e64 v5.l, m0 ; encoding: [0x05,0x00,0xe1,0xd5,0x7d,0x00,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64 v5, m0 ; encoding: [0x05,0x00,0xe1,0xd5,0x7d,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x7e,0x00,0x00,0x00
-# GFX11: v_cos_f16_e64 v5, exec_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x7e,0x00,0x00,0x00]
+# GFX11-REAL16: v_cos_f16_e64 v5.l, exec_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x7e,0x00,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64 v5, exec_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x7e,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x7f,0x00,0x00,0x00
-# GFX11: v_cos_f16_e64 v5, exec_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x7f,0x00,0x00,0x00]
+# GFX11-REAL16: v_cos_f16_e64 v5.l, exec_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x7f,0x00,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64 v5, exec_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x7f,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x7c,0x00,0x00,0x00
-# GFX11: v_cos_f16_e64 v5, null ; encoding: [0x05,0x00,0xe1,0xd5,0x7c,0x00,0x00,0x00]
+# GFX11-REAL16: v_cos_f16_e64 v5.l, null ; encoding: [0x05,0x00,0xe1,0xd5,0x7c,0x00,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64 v5, null ; encoding: [0x05,0x00,0xe1,0xd5,0x7c,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0xc1,0x00,0x00,0x00
-# GFX11: v_cos_f16_e64 v5, -1 ; encoding: [0x05,0x00,0xe1,0xd5,0xc1,0x00,0x00,0x00]
+# GFX11-REAL16: v_cos_f16_e64 v5.l, -1 ; encoding: [0x05,0x00,0xe1,0xd5,0xc1,0x00,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64 v5, -1 ; encoding: [0x05,0x00,0xe1,0xd5,0xc1,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0xf0,0x00,0x00,0x08
-# GFX11: v_cos_f16_e64 v5, 0.5 mul:2 ; encoding: [0x05,0x00,0xe1,0xd5,0xf0,0x00,0x00,0x08]
+# GFX11-REAL16: v_cos_f16_e64 v5.l, 0.5 mul:2 ; encoding: [0x05,0x00,0xe1,0xd5,0xf0,0x00,0x00,0x08]
+# GFX11-FAKE16: v_cos_f16_e64 v5, 0.5 mul:2 ; encoding: [0x05,0x00,0xe1,0xd5,0xf0,0x00,0x00,0x08]
0x05,0x00,0xe1,0xd5,0xfd,0x00,0x00,0x10
-# GFX11: v_cos_f16_e64 v5, src_scc mul:4 ; encoding: [0x05,0x00,0xe1,0xd5,0xfd,0x00,0x00,0x10]
+# GFX11-REAL16: v_cos_f16_e64 v5.l, src_scc mul:4 ; encoding: [0x05,0x00,0xe1,0xd5,0xfd,0x00,0x00,0x10]
+# GFX11-FAKE16: v_cos_f16_e64 v5, src_scc mul:4 ; encoding: [0x05,0x00,0xe1,0xd5,0xfd,0x00,0x00,0x10]
0xff,0x81,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00
-# GFX11: v_cos_f16_e64 v255, -|0xfe0b| clamp div:2 ; encoding: [0xff,0x81,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00]
+# GFX11-REAL16: v_cos_f16_e64 v255.l, -|0xfe0b| clamp div:2 ; encoding: [0xff,0x81,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64 v255, -|0xfe0b| clamp div:2 ; encoding: [0xff,0x81,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00]
+
+0x05,0x48,0xe1,0xd5,0x01,0x01,0x00,0x00
+# GFX11-REAL16: v_cos_f16_e64 v5.h, v1.h op_sel:[1,1] ; encoding: [0x05,0x48,0xe1,0xd5,0x01,0x01,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64 v5, v1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00]
+
+0x05,0x08,0xe1,0xd5,0xff,0x01,0x00,0x00
+# GFX11-REAL16: v_cos_f16_e64 v5.l, v255.h op_sel:[1,0] ; encoding: [0x05,0x08,0xe1,0xd5,0xff,0x01,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64 v5, v255 ; encoding: [0x05,0x00,0xe1,0xd5,0xff,0x01,0x00,0x00]
+
+0xff,0xc1,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00
+# GFX11-REAL16: v_cos_f16_e64 v255.h, -|0xfe0b| op_sel:[0,1] clamp div:2 ; encoding: [0xff,0xc1,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00]
+# GFX11-FAKE16: v_cos_f16_e64 v255, -|0xfe0b| clamp div:2 ; encoding: [0xff,0x81,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00]
0x05,0x00,0xb6,0xd5,0x01,0x01,0x00,0x00
# GFX11: v_cos_f32_e64 v5, v1 ; encoding: [0x05,0x00,0xb6,0xd5,0x01,0x01,0x00,0x00]
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop1_dpp16.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop1_dpp16.txt
index a1291b2e34f34b..bd5a4e34ff26d7 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop1_dpp16.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop1_dpp16.txt
@@ -237,46 +237,68 @@
# GFX12: v_clz_i32_u32_dpp v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xfa,0x72,0xfe,0x7f,0xff,0x6f,0x0d,0x30]
0xfa,0xc2,0x0a,0x7e,0x01,0x1b,0x00,0xff
-# GFX12: v_cos_f16_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1b,0x00,0xff]
+# GFX12-REAL16: v_cos_f16_dpp v5.l, v1.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1b,0x00,0xff]
+# GFX12-FAKE16: v_cos_f16_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1b,0x00,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x00,0xff
-# GFX12: v_cos_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x00,0xff]
+# GFX12-REAL16: v_cos_f16_dpp v5.l, v1.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x00,0xff]
+# GFX12-FAKE16: v_cos_f16_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0xe4,0x00,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x40,0x01,0xff
-# GFX12: v_cos_f16_dpp v5, v1 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x40,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_dpp v5.l, v1.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x40,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_dpp v5, v1 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x40,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x41,0x01,0xff
-# GFX12: v_cos_f16_dpp v5, v1 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x41,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_dpp v5.l, v1.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x41,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_dpp v5, v1 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x41,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x01,0x01,0xff
-# GFX12: v_cos_f16_dpp v5, v1 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x01,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_dpp v5.l, v1.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x01,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_dpp v5, v1 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x01,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x0f,0x01,0xff
-# GFX12: v_cos_f16_dpp v5, v1 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x0f,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_dpp v5.l, v1.l row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x0f,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_dpp v5, v1 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x0f,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x11,0x01,0xff
-# GFX12: v_cos_f16_dpp v5, v1 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x11,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_dpp v5.l, v1.l row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x11,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_dpp v5, v1 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x11,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x1f,0x01,0xff
-# GFX12: v_cos_f16_dpp v5, v1 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1f,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_dpp v5.l, v1.l row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1f,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_dpp v5, v1 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x1f,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x21,0x01,0xff
-# GFX12: v_cos_f16_dpp v5, v1 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x21,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_dpp v5.l, v1.l row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x21,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_dpp v5, v1 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x21,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x2f,0x01,0xff
-# GFX12: v_cos_f16_dpp v5, v1 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x2f,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_dpp v5.l, v1.l row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x2f,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_dpp v5, v1 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x2f,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x50,0x01,0xff
-# GFX12: v_cos_f16_dpp v5, v1 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x50,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_dpp v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x50,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_dpp v5, v1 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x50,0x01,0xff]
0xfa,0xc2,0x0a,0x7e,0x01,0x5f,0x01,0x01
-# GFX12: v_cos_f16_dpp v5, v1 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x5f,0x01,0x01]
+# GFX12-REAL16: v_cos_f16_dpp v5.l, v1.l row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x5f,0x01,0x01]
+# GFX12-FAKE16: v_cos_f16_dpp v5, v1 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x5f,0x01,0x01]
0xfa,0xc2,0x0a,0x7e,0x01,0x60,0x01,0x13
-# GFX12: v_cos_f16_dpp v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x60,0x01,0x13]
+# GFX12-REAL16: v_cos_f16_dpp v5.l, v1.l row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x60,0x01,0x13]
+# GFX12-FAKE16: v_cos_f16_dpp v5, v1 row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0xfa,0xc2,0x0a,0x7e,0x01,0x60,0x01,0x13]
0xfa,0xc2,0xfe,0x7e,0x7f,0x6f,0x3d,0x30
-# GFX12: v_cos_f16_dpp v127, -|v127| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xfa,0xc2,0xfe,0x7e,0x7f,0x6f,0x3d,0x30]
+# GFX12-REAL16: v_cos_f16_dpp v127.l, -|v127.l| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xfa,0xc2,0xfe,0x7e,0x7f,0x6f,0x3d,0x30]
+# GFX12-FAKE16: v_cos_f16_dpp v127, -|v127| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xfa,0xc2,0xfe,0x7e,0x7f,0x6f,0x3d,0x30]
+
+0xfa,0xc2,0x0a,0x7f,0x81,0x60,0x01,0x13
+# GFX12-REAL16: v_cos_f16_dpp v5.h, v1.h row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0xfa,0xc2,0x0a,0x7f,0x81,0x60,0x01,0x13]
+# GFX12-FAKE16: v_mul_i32_i24_e32 v128, 1, v176 ; encoding: [0x81,0x60,0x01,0x13]
+
+0xfa,0xc2,0xfe,0x7f,0xff,0x6f,0x3d,0x30
+# GFX12-REAL16: v_cos_f16_dpp v127.h, -|v127.h| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xfa,0xc2,0xfe,0x7f,0xff,0x6f,0x3d,0x30]
+# GFX12-FAKE16: v_lshlrev_b32_e32 v30, v255, v183 ; encoding: [0xff,0x6f,0x3d,0x30]
0xfa,0x6c,0x0a,0x7e,0x01,0x1b,0x00,0xff
# GFX12: v_cos_f32_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x6c,0x0a,0x7e,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop1_dpp8.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop1_dpp8.txt
index 05008bfabc45a3..a6358a6a9f70ca 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop1_dpp8.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop1_dpp8.txt
@@ -44,10 +44,19 @@
# GFX12: v_clz_i32_u32_dpp v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xea,0x72,0xfe,0x7f,0xff,0x00,0x00,0x00]
0xe9,0xc2,0x0a,0x7e,0x01,0x77,0x39,0x05
-# GFX12: v_cos_f16_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xc2,0x0a,0x7e,0x01,0x77,0x39,0x05]
+# GFX12-REAL16: v_cos_f16_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xc2,0x0a,0x7e,0x01,0x77,0x39,0x05]
+# GFX12-FAKE16: v_cos_f16_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xc2,0x0a,0x7e,0x01,0x77,0x39,0x05]
0xea,0xc2,0xfe,0x7e,0x7f,0x00,0x00,0x00
-# GFX12: v_cos_f16_dpp v127, v127 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xea,0xc2,0xfe,0x7e,0x7f,0x00,0x00,0x00]
+# GFX12-REAL16: v_cos_f16_dpp v127.l, v127.l dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xea,0xc2,0xfe,0x7e,0x7f,0x00,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_dpp v127, v127 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xea,0xc2,0xfe,0x7e,0x7f,0x00,0x00,0x00]
+
+0xe9,0xc2,0x0a,0x7f,0x81,0x77,0x39,0x05
+# GFX12-REAL16: v_cos_f16_dpp v5.h, v1.h dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xc2,0x0a,0x7f,0x81,0x77,0x39,0x05]
+# GFX12-FAKE16: v_add_f64_e32 v[156:157], v[129:130], v[187:188] ; encoding: [0x81,0x77,0x39,0x05]
+
+0xea,0xc2,0xfe,0x7f,0xff,0x00,0x00,0x00
+# GFX12-REAL16: v_cos_f16_dpp v127.h, v127.h dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xea,0xc2,0xfe,0x7f,0xff,0x00,0x00,0x00]
0xe9,0x6c,0x0a,0x7e,0x01,0x77,0x39,0x05
# GFX12: v_cos_f32_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0x6c,0x0a,0x7e,0x01,0x77,0x39,0x05]
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1.txt
index bb9f607b6ece67..c347d8ef38975c 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1.txt
@@ -279,49 +279,76 @@
# GFX12: v_clz_i32_u32_e64 v255, 0xaf123456 ; encoding: [0xff,0x00,0xb9,0xd5,0xff,0x00,0x00,0x00,0x56,0x34,0x12,0xaf]
0x05,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00
-# GFX12: v_cos_f16_e64 v5, v1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00]
+# GFX12-REAL16: v_cos_f16_e64 v5.l, v1.l ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64 v5, v1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00]
0x05,0x00,0xe1,0xd5,0xff,0x01,0x00,0x00
-# GFX12: v_cos_f16_e64 v5, v255 ; encoding: [0x05,0x00,0xe1,0xd5,0xff,0x01,0x00,0x00]
+# GFX12-REAL16: v_cos_f16_e64 v5.l, v255.l ; encoding: [0x05,0x00,0xe1,0xd5,0xff,0x01,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64 v5, v255 ; encoding: [0x05,0x00,0xe1,0xd5,0xff,0x01,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x01,0x00,0x00,0x00
-# GFX12: v_cos_f16_e64 v5, s1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x00,0x00,0x00]
+# GFX12-REAL16: v_cos_f16_e64 v5.l, s1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x00,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64 v5, s1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x69,0x00,0x00,0x00
-# GFX12: v_cos_f16_e64 v5, s105 ; encoding: [0x05,0x00,0xe1,0xd5,0x69,0x00,0x00,0x00]
+# GFX12-REAL16: v_cos_f16_e64 v5.l, s105 ; encoding: [0x05,0x00,0xe1,0xd5,0x69,0x00,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64 v5, s105 ; encoding: [0x05,0x00,0xe1,0xd5,0x69,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x6a,0x00,0x00,0x00
-# GFX12: v_cos_f16_e64 v5, vcc_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x6a,0x00,0x00,0x00]
+# GFX12-REAL16: v_cos_f16_e64 v5.l, vcc_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x6a,0x00,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64 v5, vcc_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x6a,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x6b,0x00,0x00,0x00
-# GFX12: v_cos_f16_e64 v5, vcc_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x6b,0x00,0x00,0x00]
+# GFX12-REAL16: v_cos_f16_e64 v5.l, vcc_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x6b,0x00,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64 v5, vcc_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x6b,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x7b,0x00,0x00,0x00
-# GFX12: v_cos_f16_e64 v5, ttmp15 ; encoding: [0x05,0x00,0xe1,0xd5,0x7b,0x00,0x00,0x00]
+# GFX12-REAL16: v_cos_f16_e64 v5.l, ttmp15 ; encoding: [0x05,0x00,0xe1,0xd5,0x7b,0x00,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64 v5, ttmp15 ; encoding: [0x05,0x00,0xe1,0xd5,0x7b,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x7d,0x00,0x00,0x00
-# GFX12: v_cos_f16_e64 v5, m0 ; encoding: [0x05,0x00,0xe1,0xd5,0x7d,0x00,0x00,0x00]
+# GFX12-REAL16: v_cos_f16_e64 v5.l, m0 ; encoding: [0x05,0x00,0xe1,0xd5,0x7d,0x00,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64 v5, m0 ; encoding: [0x05,0x00,0xe1,0xd5,0x7d,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x7e,0x00,0x00,0x00
-# GFX12: v_cos_f16_e64 v5, exec_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x7e,0x00,0x00,0x00]
+# GFX12-REAL16: v_cos_f16_e64 v5.l, exec_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x7e,0x00,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64 v5, exec_lo ; encoding: [0x05,0x00,0xe1,0xd5,0x7e,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x7f,0x00,0x00,0x00
-# GFX12: v_cos_f16_e64 v5, exec_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x7f,0x00,0x00,0x00]
+# GFX12-REAL16: v_cos_f16_e64 v5.l, exec_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x7f,0x00,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64 v5, exec_hi ; encoding: [0x05,0x00,0xe1,0xd5,0x7f,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0x7c,0x00,0x00,0x00
-# GFX12: v_cos_f16_e64 v5, null ; encoding: [0x05,0x00,0xe1,0xd5,0x7c,0x00,0x00,0x00]
+# GFX12-REAL16: v_cos_f16_e64 v5.l, null ; encoding: [0x05,0x00,0xe1,0xd5,0x7c,0x00,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64 v5, null ; encoding: [0x05,0x00,0xe1,0xd5,0x7c,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0xc1,0x00,0x00,0x00
-# GFX12: v_cos_f16_e64 v5, -1 ; encoding: [0x05,0x00,0xe1,0xd5,0xc1,0x00,0x00,0x00]
+# GFX12-REAL16: v_cos_f16_e64 v5.l, -1 ; encoding: [0x05,0x00,0xe1,0xd5,0xc1,0x00,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64 v5, -1 ; encoding: [0x05,0x00,0xe1,0xd5,0xc1,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0xf0,0x00,0x00,0x08
-# GFX12: v_cos_f16_e64 v5, 0.5 mul:2 ; encoding: [0x05,0x00,0xe1,0xd5,0xf0,0x00,0x00,0x08]
+# GFX12-REAL16: v_cos_f16_e64 v5.l, 0.5 mul:2 ; encoding: [0x05,0x00,0xe1,0xd5,0xf0,0x00,0x00,0x08]
+# GFX12-FAKE16: v_cos_f16_e64 v5, 0.5 mul:2 ; encoding: [0x05,0x00,0xe1,0xd5,0xf0,0x00,0x00,0x08]
0x05,0x00,0xe1,0xd5,0xfd,0x00,0x00,0x10
-# GFX12: v_cos_f16_e64 v5, src_scc mul:4 ; encoding: [0x05,0x00,0xe1,0xd5,0xfd,0x00,0x00,0x10]
+# GFX12-REAL16: v_cos_f16_e64 v5.l, src_scc mul:4 ; encoding: [0x05,0x00,0xe1,0xd5,0xfd,0x00,0x00,0x10]
+# GFX12-FAKE16: v_cos_f16_e64 v5, src_scc mul:4 ; encoding: [0x05,0x00,0xe1,0xd5,0xfd,0x00,0x00,0x10]
0xff,0x81,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00
-# GFX12: v_cos_f16_e64 v255, -|0xfe0b| clamp div:2 ; encoding: [0xff,0x81,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00]
+# GFX12-REAL16: v_cos_f16_e64 v255.l, -|0xfe0b| clamp div:2 ; encoding: [0xff,0x81,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64 v255, -|0xfe0b| clamp div:2 ; encoding: [0xff,0x81,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00]
+
+0x05,0x48,0xe1,0xd5,0x01,0x01,0x00,0x00
+# GFX12-REAL16: v_cos_f16_e64 v5.h, v1.h op_sel:[1,1] ; encoding: [0x05,0x48,0xe1,0xd5,0x01,0x01,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64 v5, v1 ; encoding: [0x05,0x00,0xe1,0xd5,0x01,0x01,0x00,0x00]
+
+0x05,0x08,0xe1,0xd5,0xff,0x01,0x00,0x00
+# GFX12-REAL16: v_cos_f16_e64 v5.l, v255.h op_sel:[1,0] ; encoding: [0x05,0x08,0xe1,0xd5,0xff,0x01,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64 v5, v255 ; encoding: [0x05,0x00,0xe1,0xd5,0xff,0x01,0x00,0x00]
+
+0xff,0xc1,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00
+# GFX12-REAL16: v_cos_f16_e64 v255.h, -|0xfe0b| op_sel:[0,1] clamp div:2 ; encoding: [0xff,0xc1,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64 v255, -|0xfe0b| clamp div:2 ; encoding: [0xff,0x81,0xe1,0xd5,0xff,0x00,0x00,0x38,0x0b,0xfe,0x00,0x00]
0x05,0x00,0xb6,0xd5,0x01,0x01,0x00,0x00
# GFX12: v_cos_f32_e64 v5, v1 ; encoding: [0x05,0x00,0xb6,0xd5,0x01,0x01,0x00,0x00]
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1_dpp16.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1_dpp16.txt
index be9f069322da82..dd2d0ccefac335 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1_dpp16.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1_dpp16.txt
@@ -227,46 +227,72 @@
# GFX12: v_clz_i32_u32_e64_dpp v255, v255 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x00,0xb9,0xd5,0xfa,0x00,0x00,0x00,0xff,0x6f,0x0d,0x30]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff
-# GFX12: v_cos_f16_e64_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0xe4,0x00,0xff
-# GFX12: v_cos_f16_e64_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0xe4,0x00,0xff]
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0xe4,0x00,0xff]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0xe4,0x00,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x40,0x01,0xff
-# GFX12: v_cos_f16_e64_dpp v5, v1 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x40,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x40,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x40,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x41,0x01,0xff
-# GFX12: v_cos_f16_e64_dpp v5, v1 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x41,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x41,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x41,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x01,0x01,0xff
-# GFX12: v_cos_f16_e64_dpp v5, v1 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x01,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x01,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x01,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x0f,0x01,0xff
-# GFX12: v_cos_f16_e64_dpp v5, v1 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x0f,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x0f,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x0f,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x11,0x01,0xff
-# GFX12: v_cos_f16_e64_dpp v5, v1 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x11,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x11,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x11,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1f,0x01,0xff
-# GFX12: v_cos_f16_e64_dpp v5, v1 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1f,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1f,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1f,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x21,0x01,0xff
-# GFX12: v_cos_f16_e64_dpp v5, v1 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x21,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x21,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x21,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x2f,0x01,0xff
-# GFX12: v_cos_f16_e64_dpp v5, v1 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x2f,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x2f,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x2f,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x50,0x01,0xff
-# GFX12: v_cos_f16_e64_dpp v5, v1 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x50,0x01,0xff]
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.l row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x50,0x01,0xff]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x00,0x01,0x50,0x01,0xff]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01
-# GFX12: v_cos_f16_e64_dpp v5, v1 mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01]
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.l mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01]
0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x01,0x13
-# GFX12: v_cos_f16_e64_dpp v5, v1 mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x01,0x13]
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.l mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x01,0x13]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x01,0x13]
0xff,0x81,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x0d,0x30
-# GFX12: v_cos_f16_e64_dpp v255, -|v255| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x0d,0x30]
+# GFX12-REAL16: v_cos_f16_e64_dpp v255.l, -|v255.l| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x0d,0x30]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v255, -|v255| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x0d,0x30]
+
+0x05,0x48,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.h, v1.h op_sel:[1,1] mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x48,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x08,0x01,0x5f,0x01,0x01]
+
+0x05,0x08,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x01,0x13
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.h op_sel:[1,0] mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x08,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x01,0x13]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 ; encoding: [0x05,0x00,0xe1,0xd5,0xfa,0x00,0x00,0x10,0x01,0x60,0x01,0x13]
+
+0xff,0xc1,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x0d,0x30
+# GFX12-REAL16: v_cos_f16_e64_dpp v255.h, -|v255.l| op_sel:[0,1] clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0xc1,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x0d,0x30]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v255, -|v255| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:1 fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xfa,0x00,0x00,0x38,0xff,0x6f,0x0d,0x30]
0x05,0x00,0xb6,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff
# GFX12: v_cos_f32_e64_dpp v5, v1 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0xb6,0xd5,0xfa,0x00,0x00,0x00,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1_dpp8.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1_dpp8.txt
index 87115b962a8087..25255d09ccffd3 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1_dpp8.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_from_vop1_dpp8.txt
@@ -49,16 +49,32 @@
# GFX12: v_clz_i32_u32_e64_dpp v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x00,0xb9,0xd5,0xea,0x00,0x00,0x00,0xff,0x00,0x00,0x00]
0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05
-# GFX12: v_cos_f16_e64_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05
-# GFX12: v_cos_f16_e64_dpp v5, v1 mul:2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05]
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.l mul:2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 mul:2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05]
0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x10,0x01,0x77,0x39,0x05
-# GFX12: v_cos_f16_e64_dpp v5, v1 mul:4 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x10,0x01,0x77,0x39,0x05]
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.l mul:4 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x10,0x01,0x77,0x39,0x05]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 mul:4 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x10,0x01,0x77,0x39,0x05]
0xff,0x81,0xe1,0xd5,0xea,0x00,0x00,0x38,0xff,0x00,0x00,0x00
-# GFX12: v_cos_f16_e64_dpp v255, -|v255| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xea,0x00,0x00,0x38,0xff,0x00,0x00,0x00]
+# GFX12-REAL16: v_cos_f16_e64_dpp v255.l, -|v255.l| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xea,0x00,0x00,0x38,0xff,0x00,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v255, -|v255| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xea,0x00,0x00,0x38,0xff,0x00,0x00,0x00]
+
+0x05,0x48,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.h, v1.h op_sel:[1,1] mul:2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x48,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 mul:2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x08,0x01,0x77,0x39,0x05]
+
+0x05,0x08,0xe1,0xd5,0xe9,0x00,0x00,0x10,0x01,0x77,0x39,0x05
+# GFX12-REAL16: v_cos_f16_e64_dpp v5.l, v1.h op_sel:[1,0] mul:4 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x08,0xe1,0xd5,0xe9,0x00,0x00,0x10,0x01,0x77,0x39,0x05]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v5, v1 mul:4 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xe1,0xd5,0xe9,0x00,0x00,0x10,0x01,0x77,0x39,0x05]
+
+0xff,0xc1,0xe1,0xd5,0xea,0x00,0x00,0x38,0xff,0x00,0x00,0x00
+# GFX12-REAL16: v_cos_f16_e64_dpp v255.h, -|v255.l| op_sel:[0,1] clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0xc1,0xe1,0xd5,0xea,0x00,0x00,0x38,0xff,0x00,0x00,0x00]
+# GFX12-FAKE16: v_cos_f16_e64_dpp v255, -|v255| clamp div:2 dpp8:[0,0,0,0,0,0,0,0] fi:1 ; encoding: [0xff,0x81,0xe1,0xd5,0xea,0x00,0x00,0x38,0xff,0x00,0x00,0x00]
0x05,0x00,0xb6,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05
# GFX12: v_cos_f32_e64_dpp v5, v1 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0xb6,0xd5,0xe9,0x00,0x00,0x00,0x01,0x77,0x39,0x05]
More information about the llvm-commits
mailing list