CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
304 lines
16 KiB
ArmAsm
304 lines
16 KiB
ArmAsm
// NOTE: Assertions have been autogenerated by utils/update_mc_test_checks.py UTC_ARGS: --version 5
|
|
// RUN: llvm-mc -triple=amdgcn -show-encoding -mcpu=gfx1170 %s | FileCheck --check-prefixes=GFX1170 %s
|
|
// RUN: llvm-mc -triple=amdgcn -show-encoding -mcpu=gfx1170 %s | %extract-encodings | llvm-mc -triple=amdgcn -mcpu=gfx1170 -disassemble -show-encoding | FileCheck --strict-whitespace --check-prefixes=GFX1170 %s
|
|
|
|
v_pk_max_num_f16 v5, v1, v2
|
|
// GFX1170: v_pk_max_num_f16 v5, v1, v2 ; encoding: [0x05,0x40,0x12,0xcc,0x01,0x05,0x02,0x1a]
|
|
|
|
v_pk_max_num_f16 v5, v255, v255
|
|
// GFX1170: v_pk_max_num_f16 v5, v255, v255 ; encoding: [0x05,0x40,0x12,0xcc,0xff,0xff,0x03,0x1a]
|
|
|
|
v_pk_max_num_f16 v5, s1, s2
|
|
// GFX1170: v_pk_max_num_f16 v5, s1, s2 ; encoding: [0x05,0x40,0x12,0xcc,0x01,0x04,0x00,0x1a]
|
|
|
|
v_pk_max_num_f16 v5, s105, s105
|
|
// GFX1170: v_pk_max_num_f16 v5, s105, s105 ; encoding: [0x05,0x40,0x12,0xcc,0x69,0xd2,0x00,0x1a]
|
|
|
|
v_pk_max_num_f16 v5, vcc_lo, ttmp15
|
|
// GFX1170: v_pk_max_num_f16 v5, vcc_lo, ttmp15 ; encoding: [0x05,0x40,0x12,0xcc,0x6a,0xf6,0x00,0x1a]
|
|
|
|
v_pk_max_num_f16 v5, vcc_hi, 0xfe0b
|
|
// GFX1170: v_pk_max_num_f16 v5, vcc_hi, 0xfe0b ; encoding: [0x05,0x40,0x12,0xcc,0x6b,0xfe,0x01,0x1a,0x0b,0xfe,0x00,0x00]
|
|
|
|
v_pk_max_num_f16 v5, ttmp15, src_scc
|
|
// GFX1170: v_pk_max_num_f16 v5, ttmp15, src_scc ; encoding: [0x05,0x40,0x12,0xcc,0x7b,0xfa,0x01,0x1a]
|
|
|
|
v_pk_max_num_f16 v5, m0, 0.5
|
|
// GFX1170: v_pk_max_num_f16 v5, m0, 0.5 ; encoding: [0x05,0x40,0x12,0xcc,0x7d,0xe0,0x01,0x1a]
|
|
|
|
v_pk_max_num_f16 v5, exec_lo, -1
|
|
// GFX1170: v_pk_max_num_f16 v5, exec_lo, -1 ; encoding: [0x05,0x40,0x12,0xcc,0x7e,0x82,0x01,0x1a]
|
|
|
|
v_pk_max_num_f16 v5, exec_hi, null
|
|
// GFX1170: v_pk_max_num_f16 v5, exec_hi, null ; encoding: [0x05,0x40,0x12,0xcc,0x7f,0xf8,0x00,0x1a]
|
|
|
|
v_pk_max_num_f16 v5, null, exec_lo
|
|
// GFX1170: v_pk_max_num_f16 v5, null, exec_lo ; encoding: [0x05,0x40,0x12,0xcc,0x7c,0xfc,0x00,0x1a]
|
|
|
|
v_pk_max_num_f16 v5, -1, exec_hi op_sel:[1,1] op_sel_hi:[0,0] neg_lo:[1,0] neg_hi:[1,0]
|
|
// GFX1170: v_pk_max_num_f16 v5, -1, exec_hi op_sel:[1,1] op_sel_hi:[0,0] neg_lo:[1,0] neg_hi:[1,0] ; encoding: [0x05,0x59,0x12,0xcc,0xc1,0xfe,0x00,0x22]
|
|
|
|
v_pk_max_num_f16 v5, 0.5, m0 op_sel:[0,0] op_sel_hi:[1,1] neg_lo:[0,1] neg_hi:[0,1]
|
|
// GFX1170: v_pk_max_num_f16 v5, 0.5, m0 neg_lo:[0,1] neg_hi:[0,1] ; encoding: [0x05,0x42,0x12,0xcc,0xf0,0xfa,0x00,0x5a]
|
|
|
|
v_pk_max_num_f16 v5, src_scc, vcc_lo op_sel:[1,0] op_sel_hi:[0,1] neg_lo:[0,0] neg_hi:[0,0]
|
|
// GFX1170: v_pk_max_num_f16 v5, src_scc, vcc_lo op_sel:[1,0] op_sel_hi:[0,1] ; encoding: [0x05,0x48,0x12,0xcc,0xfd,0xd4,0x00,0x12]
|
|
|
|
v_pk_max_num_f16 v255, 0xfe0b, vcc_hi op_sel:[0,1] op_sel_hi:[1,0] neg_lo:[1,1] neg_hi:[1,1] clamp
|
|
// GFX1170: v_pk_max_num_f16 v255, 0xfe0b, vcc_hi op_sel:[0,1] op_sel_hi:[1,0] neg_lo:[1,1] neg_hi:[1,1] clamp ; encoding: [0xff,0xd3,0x12,0xcc,0xff,0xd6,0x00,0x6a,0x0b,0xfe,0x00,0x00]
|
|
|
|
v_pk_min_num_f16 v5, v1, v2
|
|
// GFX1170: v_pk_min_num_f16 v5, v1, v2 ; encoding: [0x05,0x40,0x11,0xcc,0x01,0x05,0x02,0x1a]
|
|
|
|
v_pk_min_num_f16 v5, v255, v255
|
|
// GFX1170: v_pk_min_num_f16 v5, v255, v255 ; encoding: [0x05,0x40,0x11,0xcc,0xff,0xff,0x03,0x1a]
|
|
|
|
v_pk_min_num_f16 v5, s1, s2
|
|
// GFX1170: v_pk_min_num_f16 v5, s1, s2 ; encoding: [0x05,0x40,0x11,0xcc,0x01,0x04,0x00,0x1a]
|
|
|
|
v_pk_min_num_f16 v5, s105, s105
|
|
// GFX1170: v_pk_min_num_f16 v5, s105, s105 ; encoding: [0x05,0x40,0x11,0xcc,0x69,0xd2,0x00,0x1a]
|
|
|
|
v_pk_min_num_f16 v5, vcc_lo, ttmp15
|
|
// GFX1170: v_pk_min_num_f16 v5, vcc_lo, ttmp15 ; encoding: [0x05,0x40,0x11,0xcc,0x6a,0xf6,0x00,0x1a]
|
|
|
|
v_pk_min_num_f16 v5, vcc_hi, 0xfe0b
|
|
// GFX1170: v_pk_min_num_f16 v5, vcc_hi, 0xfe0b ; encoding: [0x05,0x40,0x11,0xcc,0x6b,0xfe,0x01,0x1a,0x0b,0xfe,0x00,0x00]
|
|
|
|
v_pk_min_num_f16 v5, ttmp15, src_scc
|
|
// GFX1170: v_pk_min_num_f16 v5, ttmp15, src_scc ; encoding: [0x05,0x40,0x11,0xcc,0x7b,0xfa,0x01,0x1a]
|
|
|
|
v_pk_min_num_f16 v5, m0, 0.5
|
|
// GFX1170: v_pk_min_num_f16 v5, m0, 0.5 ; encoding: [0x05,0x40,0x11,0xcc,0x7d,0xe0,0x01,0x1a]
|
|
|
|
v_pk_min_num_f16 v5, exec_lo, -1
|
|
// GFX1170: v_pk_min_num_f16 v5, exec_lo, -1 ; encoding: [0x05,0x40,0x11,0xcc,0x7e,0x82,0x01,0x1a]
|
|
|
|
v_pk_min_num_f16 v5, exec_hi, null
|
|
// GFX1170: v_pk_min_num_f16 v5, exec_hi, null ; encoding: [0x05,0x40,0x11,0xcc,0x7f,0xf8,0x00,0x1a]
|
|
|
|
v_pk_min_num_f16 v5, null, exec_lo
|
|
// GFX1170: v_pk_min_num_f16 v5, null, exec_lo ; encoding: [0x05,0x40,0x11,0xcc,0x7c,0xfc,0x00,0x1a]
|
|
|
|
v_pk_min_num_f16 v5, -1, exec_hi op_sel:[1,1] op_sel_hi:[0,0] neg_lo:[1,0] neg_hi:[1,0]
|
|
// GFX1170: v_pk_min_num_f16 v5, -1, exec_hi op_sel:[1,1] op_sel_hi:[0,0] neg_lo:[1,0] neg_hi:[1,0] ; encoding: [0x05,0x59,0x11,0xcc,0xc1,0xfe,0x00,0x22]
|
|
|
|
v_pk_min_num_f16 v5, 0.5, m0 op_sel:[0,0] op_sel_hi:[1,1] neg_lo:[0,1] neg_hi:[0,1]
|
|
// GFX1170: v_pk_min_num_f16 v5, 0.5, m0 neg_lo:[0,1] neg_hi:[0,1] ; encoding: [0x05,0x42,0x11,0xcc,0xf0,0xfa,0x00,0x5a]
|
|
|
|
v_pk_min_num_f16 v5, src_scc, vcc_lo op_sel:[1,0] op_sel_hi:[0,1] neg_lo:[0,0] neg_hi:[0,0]
|
|
// GFX1170: v_pk_min_num_f16 v5, src_scc, vcc_lo op_sel:[1,0] op_sel_hi:[0,1] ; encoding: [0x05,0x48,0x11,0xcc,0xfd,0xd4,0x00,0x12]
|
|
|
|
v_pk_min_num_f16 v255, 0xfe0b, vcc_hi op_sel:[0,1] op_sel_hi:[1,0] neg_lo:[1,1] neg_hi:[1,1] clamp
|
|
// GFX1170: v_pk_min_num_f16 v255, 0xfe0b, vcc_hi op_sel:[0,1] op_sel_hi:[1,0] neg_lo:[1,1] neg_hi:[1,1] clamp ; encoding: [0xff,0xd3,0x11,0xcc,0xff,0xd6,0x00,0x6a,0x0b,0xfe,0x00,0x00]
|
|
|
|
v_pk_minimum_f16 v5, v1, v2
|
|
// GFX1170: v_pk_minimum_f16 v5, v1, v2 ; encoding: [0x05,0x40,0x1d,0xcc,0x01,0x05,0x02,0x1a]
|
|
|
|
v_pk_minimum_f16 v5, v255, v255
|
|
// GFX1170: v_pk_minimum_f16 v5, v255, v255 ; encoding: [0x05,0x40,0x1d,0xcc,0xff,0xff,0x03,0x1a]
|
|
|
|
v_pk_minimum_f16 v5, s1, s2
|
|
// GFX1170: v_pk_minimum_f16 v5, s1, s2 ; encoding: [0x05,0x40,0x1d,0xcc,0x01,0x04,0x00,0x1a]
|
|
|
|
v_pk_minimum_f16 v5, s105, s105
|
|
// GFX1170: v_pk_minimum_f16 v5, s105, s105 ; encoding: [0x05,0x40,0x1d,0xcc,0x69,0xd2,0x00,0x1a]
|
|
|
|
v_pk_minimum_f16 v5, vcc_lo, ttmp15
|
|
// GFX1170: v_pk_minimum_f16 v5, vcc_lo, ttmp15 ; encoding: [0x05,0x40,0x1d,0xcc,0x6a,0xf6,0x00,0x1a]
|
|
|
|
v_pk_minimum_f16 v5, vcc_hi, 0xfe0b
|
|
// GFX1170: v_pk_minimum_f16 v5, vcc_hi, 0xfe0b ; encoding: [0x05,0x40,0x1d,0xcc,0x6b,0xfe,0x01,0x1a,0x0b,0xfe,0x00,0x00]
|
|
|
|
v_pk_minimum_f16 v5, ttmp15, src_scc
|
|
// GFX1170: v_pk_minimum_f16 v5, ttmp15, src_scc ; encoding: [0x05,0x40,0x1d,0xcc,0x7b,0xfa,0x01,0x1a]
|
|
|
|
v_pk_minimum_f16 v5, m0, 0.5
|
|
// GFX1170: v_pk_minimum_f16 v5, m0, 0.5 ; encoding: [0x05,0x40,0x1d,0xcc,0x7d,0xe0,0x01,0x1a]
|
|
|
|
v_pk_minimum_f16 v5, exec_lo, -1
|
|
// GFX1170: v_pk_minimum_f16 v5, exec_lo, -1 ; encoding: [0x05,0x40,0x1d,0xcc,0x7e,0x82,0x01,0x1a]
|
|
|
|
v_pk_minimum_f16 v5, exec_hi, null
|
|
// GFX1170: v_pk_minimum_f16 v5, exec_hi, null ; encoding: [0x05,0x40,0x1d,0xcc,0x7f,0xf8,0x00,0x1a]
|
|
|
|
v_pk_minimum_f16 v5, null, exec_lo
|
|
// GFX1170: v_pk_minimum_f16 v5, null, exec_lo ; encoding: [0x05,0x40,0x1d,0xcc,0x7c,0xfc,0x00,0x1a]
|
|
|
|
v_pk_minimum_f16 v5, -1, exec_hi op_sel:[1,1] op_sel_hi:[0,0] neg_lo:[1,0] neg_hi:[1,0]
|
|
// GFX1170: v_pk_minimum_f16 v5, -1, exec_hi op_sel:[1,1] op_sel_hi:[0,0] neg_lo:[1,0] neg_hi:[1,0] ; encoding: [0x05,0x59,0x1d,0xcc,0xc1,0xfe,0x00,0x22]
|
|
|
|
v_pk_minimum_f16 v5, 0.5, m0 op_sel:[0,0] op_sel_hi:[1,1] neg_lo:[0,1] neg_hi:[0,1]
|
|
// GFX1170: v_pk_minimum_f16 v5, 0.5, m0 neg_lo:[0,1] neg_hi:[0,1] ; encoding: [0x05,0x42,0x1d,0xcc,0xf0,0xfa,0x00,0x5a]
|
|
|
|
v_pk_minimum_f16 v5, src_scc, vcc_lo op_sel:[1,0] op_sel_hi:[0,1] neg_lo:[0,0] neg_hi:[0,0]
|
|
// GFX1170: v_pk_minimum_f16 v5, src_scc, vcc_lo op_sel:[1,0] op_sel_hi:[0,1] ; encoding: [0x05,0x48,0x1d,0xcc,0xfd,0xd4,0x00,0x12]
|
|
|
|
v_pk_minimum_f16 v255, 0xfe0b, vcc_hi op_sel:[0,1] op_sel_hi:[1,0] neg_lo:[1,1] neg_hi:[1,1] clamp
|
|
// GFX1170: v_pk_minimum_f16 v255, 0xfe0b, vcc_hi op_sel:[0,1] op_sel_hi:[1,0] neg_lo:[1,1] neg_hi:[1,1] clamp ; encoding: [0xff,0xd3,0x1d,0xcc,0xff,0xd6,0x00,0x6a,0x0b,0xfe,0x00,0x00]
|
|
|
|
v_pk_maximum_f16 v5, v1, v2
|
|
// GFX1170: v_pk_maximum_f16 v5, v1, v2 ; encoding: [0x05,0x40,0x1e,0xcc,0x01,0x05,0x02,0x1a]
|
|
|
|
v_pk_maximum_f16 v5, v255, v255
|
|
// GFX1170: v_pk_maximum_f16 v5, v255, v255 ; encoding: [0x05,0x40,0x1e,0xcc,0xff,0xff,0x03,0x1a]
|
|
|
|
v_pk_maximum_f16 v5, s1, s2
|
|
// GFX1170: v_pk_maximum_f16 v5, s1, s2 ; encoding: [0x05,0x40,0x1e,0xcc,0x01,0x04,0x00,0x1a]
|
|
|
|
v_pk_maximum_f16 v5, s105, s105
|
|
// GFX1170: v_pk_maximum_f16 v5, s105, s105 ; encoding: [0x05,0x40,0x1e,0xcc,0x69,0xd2,0x00,0x1a]
|
|
|
|
v_pk_maximum_f16 v5, vcc_lo, ttmp15
|
|
// GFX1170: v_pk_maximum_f16 v5, vcc_lo, ttmp15 ; encoding: [0x05,0x40,0x1e,0xcc,0x6a,0xf6,0x00,0x1a]
|
|
|
|
v_pk_maximum_f16 v5, vcc_hi, 0xfe0b
|
|
// GFX1170: v_pk_maximum_f16 v5, vcc_hi, 0xfe0b ; encoding: [0x05,0x40,0x1e,0xcc,0x6b,0xfe,0x01,0x1a,0x0b,0xfe,0x00,0x00]
|
|
|
|
v_pk_maximum_f16 v5, ttmp15, src_scc
|
|
// GFX1170: v_pk_maximum_f16 v5, ttmp15, src_scc ; encoding: [0x05,0x40,0x1e,0xcc,0x7b,0xfa,0x01,0x1a]
|
|
|
|
v_pk_maximum_f16 v5, m0, 0.5
|
|
// GFX1170: v_pk_maximum_f16 v5, m0, 0.5 ; encoding: [0x05,0x40,0x1e,0xcc,0x7d,0xe0,0x01,0x1a]
|
|
|
|
v_pk_maximum_f16 v5, exec_lo, -1
|
|
// GFX1170: v_pk_maximum_f16 v5, exec_lo, -1 ; encoding: [0x05,0x40,0x1e,0xcc,0x7e,0x82,0x01,0x1a]
|
|
|
|
v_pk_maximum_f16 v5, exec_hi, null
|
|
// GFX1170: v_pk_maximum_f16 v5, exec_hi, null ; encoding: [0x05,0x40,0x1e,0xcc,0x7f,0xf8,0x00,0x1a]
|
|
|
|
v_pk_maximum_f16 v5, null, exec_lo
|
|
// GFX1170: v_pk_maximum_f16 v5, null, exec_lo ; encoding: [0x05,0x40,0x1e,0xcc,0x7c,0xfc,0x00,0x1a]
|
|
|
|
v_pk_maximum_f16 v5, -1, exec_hi op_sel:[1,1] op_sel_hi:[0,0] neg_lo:[1,0] neg_hi:[1,0]
|
|
// GFX1170: v_pk_maximum_f16 v5, -1, exec_hi op_sel:[1,1] op_sel_hi:[0,0] neg_lo:[1,0] neg_hi:[1,0] ; encoding: [0x05,0x59,0x1e,0xcc,0xc1,0xfe,0x00,0x22]
|
|
|
|
v_pk_maximum_f16 v5, 0.5, m0 op_sel:[0,0] op_sel_hi:[1,1] neg_lo:[0,1] neg_hi:[0,1]
|
|
// GFX1170: v_pk_maximum_f16 v5, 0.5, m0 neg_lo:[0,1] neg_hi:[0,1] ; encoding: [0x05,0x42,0x1e,0xcc,0xf0,0xfa,0x00,0x5a]
|
|
|
|
v_pk_maximum_f16 v5, src_scc, vcc_lo op_sel:[1,0] op_sel_hi:[0,1] neg_lo:[0,0] neg_hi:[0,0]
|
|
// GFX1170: v_pk_maximum_f16 v5, src_scc, vcc_lo op_sel:[1,0] op_sel_hi:[0,1] ; encoding: [0x05,0x48,0x1e,0xcc,0xfd,0xd4,0x00,0x12]
|
|
|
|
v_pk_maximum_f16 v255, 0xfe0b, vcc_hi op_sel:[0,1] op_sel_hi:[1,0] neg_lo:[1,1] neg_hi:[1,1] clamp
|
|
// GFX1170: v_pk_maximum_f16 v255, 0xfe0b, vcc_hi op_sel:[0,1] op_sel_hi:[1,0] neg_lo:[1,1] neg_hi:[1,1] clamp ; encoding: [0xff,0xd3,0x1e,0xcc,0xff,0xd6,0x00,0x6a,0x0b,0xfe,0x00,0x00]
|
|
|
|
v_dot4_f32_fp8_bf8 v0, v1, v2, v3
|
|
// GFX1170: v_dot4_f32_fp8_bf8 v0, v1, v2, v3 ; encoding: [0x00,0x40,0x24,0xcc,0x01,0x05,0x0e,0x1c]
|
|
|
|
v_dot4_f32_fp8_bf8 v0, v1, v2, v3 neg_lo:[0,0,1]
|
|
// GFX1170: v_dot4_f32_fp8_bf8 v0, v1, v2, v3 neg_lo:[0,0,1] ; encoding: [0x00,0x40,0x24,0xcc,0x01,0x05,0x0e,0x9c]
|
|
|
|
v_dot4_f32_fp8_bf8 v0, v1, v2, v3 neg_hi:[0,0,1]
|
|
// GFX1170: v_dot4_f32_fp8_bf8 v0, v1, v2, v3 neg_hi:[0,0,1] ; encoding: [0x00,0x44,0x24,0xcc,0x01,0x05,0x0e,0x1c]
|
|
|
|
v_dot4_f32_fp8_bf8 v0, s0, v2, v3
|
|
// GFX1170: v_dot4_f32_fp8_bf8 v0, s0, v2, v3 ; encoding: [0x00,0x40,0x24,0xcc,0x00,0x04,0x0e,0x1c]
|
|
|
|
v_dot4_f32_fp8_bf8 v0, v1, s0, v3
|
|
// GFX1170: v_dot4_f32_fp8_bf8 v0, v1, s0, v3 ; encoding: [0x00,0x40,0x24,0xcc,0x01,0x01,0x0c,0x1c]
|
|
|
|
v_dot4_f32_fp8_bf8 v0, v1, v2, s0
|
|
// GFX1170: v_dot4_f32_fp8_bf8 v0, v1, v2, s0 ; encoding: [0x00,0x40,0x24,0xcc,0x01,0x05,0x02,0x18]
|
|
|
|
v_dot4_f32_fp8_bf8 v0, 1.0, v2, v3
|
|
// GFX1170: v_dot4_f32_fp8_bf8 v0, 1.0, v2, v3 ; encoding: [0x00,0x40,0x24,0xcc,0xf2,0x04,0x0e,0x1c]
|
|
|
|
v_dot4_f32_fp8_bf8 v0, v1, 1.0, v3
|
|
// GFX1170: v_dot4_f32_fp8_bf8 v0, v1, 1.0, v3 ; encoding: [0x00,0x40,0x24,0xcc,0x01,0xe5,0x0d,0x1c]
|
|
|
|
v_dot4_f32_fp8_bf8 v0, v1, v2, 1.0
|
|
// GFX1170: v_dot4_f32_fp8_bf8 v0, v1, v2, 1.0 ; encoding: [0x00,0x40,0x24,0xcc,0x01,0x05,0xca,0x1b]
|
|
|
|
v_dot4_f32_fp8_bf8 v0, v1, v2, 1
|
|
// GFX1170: v_dot4_f32_fp8_bf8 v0, v1, v2, 1 ; encoding: [0x00,0x40,0x24,0xcc,0x01,0x05,0x06,0x1a]
|
|
|
|
v_dot4_f32_bf8_fp8 v0, v1, v2, v3
|
|
// GFX1170: v_dot4_f32_bf8_fp8 v0, v1, v2, v3 ; encoding: [0x00,0x40,0x25,0xcc,0x01,0x05,0x0e,0x1c]
|
|
|
|
v_dot4_f32_bf8_fp8 v0, v1, v2, v3 neg_lo:[0,0,1]
|
|
// GFX1170: v_dot4_f32_bf8_fp8 v0, v1, v2, v3 neg_lo:[0,0,1] ; encoding: [0x00,0x40,0x25,0xcc,0x01,0x05,0x0e,0x9c]
|
|
|
|
v_dot4_f32_bf8_fp8 v0, v1, v2, v3 neg_hi:[0,0,1]
|
|
// GFX1170: v_dot4_f32_bf8_fp8 v0, v1, v2, v3 neg_hi:[0,0,1] ; encoding: [0x00,0x44,0x25,0xcc,0x01,0x05,0x0e,0x1c]
|
|
|
|
v_dot4_f32_bf8_fp8 v0, s0, v2, v3
|
|
// GFX1170: v_dot4_f32_bf8_fp8 v0, s0, v2, v3 ; encoding: [0x00,0x40,0x25,0xcc,0x00,0x04,0x0e,0x1c]
|
|
|
|
v_dot4_f32_bf8_fp8 v0, v1, s0, v3
|
|
// GFX1170: v_dot4_f32_bf8_fp8 v0, v1, s0, v3 ; encoding: [0x00,0x40,0x25,0xcc,0x01,0x01,0x0c,0x1c]
|
|
|
|
v_dot4_f32_bf8_fp8 v0, v1, v2, s0
|
|
// GFX1170: v_dot4_f32_bf8_fp8 v0, v1, v2, s0 ; encoding: [0x00,0x40,0x25,0xcc,0x01,0x05,0x02,0x18]
|
|
|
|
v_dot4_f32_bf8_fp8 v0, 1.0, v2, v3
|
|
// GFX1170: v_dot4_f32_bf8_fp8 v0, 1.0, v2, v3 ; encoding: [0x00,0x40,0x25,0xcc,0xf2,0x04,0x0e,0x1c]
|
|
|
|
v_dot4_f32_bf8_fp8 v0, v1, 1.0, v3
|
|
// GFX1170: v_dot4_f32_bf8_fp8 v0, v1, 1.0, v3 ; encoding: [0x00,0x40,0x25,0xcc,0x01,0xe5,0x0d,0x1c]
|
|
|
|
v_dot4_f32_bf8_fp8 v0, v1, v2, 1.0
|
|
// GFX1170: v_dot4_f32_bf8_fp8 v0, v1, v2, 1.0 ; encoding: [0x00,0x40,0x25,0xcc,0x01,0x05,0xca,0x1b]
|
|
|
|
v_dot4_f32_bf8_fp8 v0, v1, v2, 1
|
|
// GFX1170: v_dot4_f32_bf8_fp8 v0, v1, v2, 1 ; encoding: [0x00,0x40,0x25,0xcc,0x01,0x05,0x06,0x1a]
|
|
|
|
v_dot4_f32_fp8_fp8 v0, v1, v2, v3
|
|
// GFX1170: v_dot4_f32_fp8_fp8 v0, v1, v2, v3 ; encoding: [0x00,0x40,0x26,0xcc,0x01,0x05,0x0e,0x1c]
|
|
|
|
v_dot4_f32_fp8_fp8 v0, v1, v2, v3 neg_lo:[0,0,1]
|
|
// GFX1170: v_dot4_f32_fp8_fp8 v0, v1, v2, v3 neg_lo:[0,0,1] ; encoding: [0x00,0x40,0x26,0xcc,0x01,0x05,0x0e,0x9c]
|
|
|
|
v_dot4_f32_fp8_fp8 v0, v1, v2, v3 neg_hi:[0,0,1]
|
|
// GFX1170: v_dot4_f32_fp8_fp8 v0, v1, v2, v3 neg_hi:[0,0,1] ; encoding: [0x00,0x44,0x26,0xcc,0x01,0x05,0x0e,0x1c]
|
|
|
|
v_dot4_f32_fp8_fp8 v0, s0, v2, v3
|
|
// GFX1170: v_dot4_f32_fp8_fp8 v0, s0, v2, v3 ; encoding: [0x00,0x40,0x26,0xcc,0x00,0x04,0x0e,0x1c]
|
|
|
|
v_dot4_f32_fp8_fp8 v0, v1, s0, v3
|
|
// GFX1170: v_dot4_f32_fp8_fp8 v0, v1, s0, v3 ; encoding: [0x00,0x40,0x26,0xcc,0x01,0x01,0x0c,0x1c]
|
|
|
|
v_dot4_f32_fp8_fp8 v0, v1, v2, s0
|
|
// GFX1170: v_dot4_f32_fp8_fp8 v0, v1, v2, s0 ; encoding: [0x00,0x40,0x26,0xcc,0x01,0x05,0x02,0x18]
|
|
|
|
v_dot4_f32_fp8_fp8 v0, 1.0, v2, v3
|
|
// GFX1170: v_dot4_f32_fp8_fp8 v0, 1.0, v2, v3 ; encoding: [0x00,0x40,0x26,0xcc,0xf2,0x04,0x0e,0x1c]
|
|
|
|
v_dot4_f32_fp8_fp8 v0, v1, 1.0, v3
|
|
// GFX1170: v_dot4_f32_fp8_fp8 v0, v1, 1.0, v3 ; encoding: [0x00,0x40,0x26,0xcc,0x01,0xe5,0x0d,0x1c]
|
|
|
|
v_dot4_f32_fp8_fp8 v0, v1, v2, 1.0
|
|
// GFX1170: v_dot4_f32_fp8_fp8 v0, v1, v2, 1.0 ; encoding: [0x00,0x40,0x26,0xcc,0x01,0x05,0xca,0x1b]
|
|
|
|
v_dot4_f32_fp8_fp8 v0, v1, v2, 1
|
|
// GFX1170: v_dot4_f32_fp8_fp8 v0, v1, v2, 1 ; encoding: [0x00,0x40,0x26,0xcc,0x01,0x05,0x06,0x1a]
|
|
|
|
v_dot4_f32_bf8_bf8 v0, v1, v2, v3
|
|
// GFX1170: v_dot4_f32_bf8_bf8 v0, v1, v2, v3 ; encoding: [0x00,0x40,0x27,0xcc,0x01,0x05,0x0e,0x1c]
|
|
|
|
v_dot4_f32_bf8_bf8 v0, v1, v2, v3 neg_lo:[0,0,1]
|
|
// GFX1170: v_dot4_f32_bf8_bf8 v0, v1, v2, v3 neg_lo:[0,0,1] ; encoding: [0x00,0x40,0x27,0xcc,0x01,0x05,0x0e,0x9c]
|
|
|
|
v_dot4_f32_bf8_bf8 v0, v1, v2, v3 neg_hi:[0,0,1]
|
|
// GFX1170: v_dot4_f32_bf8_bf8 v0, v1, v2, v3 neg_hi:[0,0,1] ; encoding: [0x00,0x44,0x27,0xcc,0x01,0x05,0x0e,0x1c]
|
|
|
|
v_dot4_f32_bf8_bf8 v0, s0, v2, v3
|
|
// GFX1170: v_dot4_f32_bf8_bf8 v0, s0, v2, v3 ; encoding: [0x00,0x40,0x27,0xcc,0x00,0x04,0x0e,0x1c]
|
|
|
|
v_dot4_f32_bf8_bf8 v0, v1, s0, v3
|
|
// GFX1170: v_dot4_f32_bf8_bf8 v0, v1, s0, v3 ; encoding: [0x00,0x40,0x27,0xcc,0x01,0x01,0x0c,0x1c]
|
|
|
|
v_dot4_f32_bf8_bf8 v0, v1, v2, s0
|
|
// GFX1170: v_dot4_f32_bf8_bf8 v0, v1, v2, s0 ; encoding: [0x00,0x40,0x27,0xcc,0x01,0x05,0x02,0x18]
|
|
|
|
v_dot4_f32_bf8_bf8 v0, 1.0, v2, v3
|
|
// GFX1170: v_dot4_f32_bf8_bf8 v0, 1.0, v2, v3 ; encoding: [0x00,0x40,0x27,0xcc,0xf2,0x04,0x0e,0x1c]
|
|
|
|
v_dot4_f32_bf8_bf8 v0, v1, 1.0, v3
|
|
// GFX1170: v_dot4_f32_bf8_bf8 v0, v1, 1.0, v3 ; encoding: [0x00,0x40,0x27,0xcc,0x01,0xe5,0x0d,0x1c]
|
|
|
|
v_dot4_f32_bf8_bf8 v0, v1, v2, 1.0
|
|
// GFX1170: v_dot4_f32_bf8_bf8 v0, v1, v2, 1.0 ; encoding: [0x00,0x40,0x27,0xcc,0x01,0x05,0xca,0x1b]
|
|
|
|
v_dot4_f32_bf8_bf8 v0, v1, v2, 1
|
|
// GFX1170: v_dot4_f32_bf8_bf8 v0, v1, v2, 1 ; encoding: [0x00,0x40,0x27,0xcc,0x01,0x05,0x06,0x1a]
|