derek.holloway
7502bf64a4
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
118 lines
5.9 KiB
LLVM
118 lines
5.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
|
|
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx1250 -mattr=-real-true16 < %s | FileCheck --check-prefixes=GFX1250,GFX1250-SDAG,GFX1250-SDAG-FAKE16 %s
|
|
; RUN: llc -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1250 -mattr=-real-true16 < %s | FileCheck --check-prefixes=GFX1250,GFX1250-GISEL,GFX1250-GISEL-FAKE16 %s
|
|
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx1250 -mattr=+real-true16 < %s | FileCheck --check-prefixes=GFX1250,GFX1250-SDAG,GFX1250-SDAG-REAL16 %s
|
|
; RUN: llc -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1250 -mattr=+real-true16 < %s | FileCheck --check-prefixes=GFX1250,GFX1250-GISEL,GFX1250-GISEL-REAL16 %s
|
|
|
|
define <2 x half> @fminimum3_v2f16(<2 x half> %a, <2 x half> %b, <2 x half> %c) {
|
|
; GFX1250-SDAG-LABEL: fminimum3_v2f16:
|
|
; GFX1250-SDAG: ; %bb.0: ; %entry
|
|
; GFX1250-SDAG-NEXT: s_wait_loadcnt_dscnt 0x0
|
|
; GFX1250-SDAG-NEXT: s_wait_kmcnt 0x0
|
|
; GFX1250-SDAG-NEXT: v_pk_minimum3_f16 v0, v2, v0, v1
|
|
; GFX1250-SDAG-NEXT: s_set_pc_i64 s[30:31]
|
|
;
|
|
; GFX1250-GISEL-LABEL: fminimum3_v2f16:
|
|
; GFX1250-GISEL: ; %bb.0: ; %entry
|
|
; GFX1250-GISEL-NEXT: s_wait_loadcnt_dscnt 0x0
|
|
; GFX1250-GISEL-NEXT: s_wait_kmcnt 0x0
|
|
; GFX1250-GISEL-NEXT: v_pk_minimum3_f16 v0, v0, v1, v1
|
|
; GFX1250-GISEL-NEXT: s_delay_alu instid0(VALU_DEP_1)
|
|
; GFX1250-GISEL-NEXT: v_pk_minimum3_f16 v0, v2, v0, v0
|
|
; GFX1250-GISEL-NEXT: s_set_pc_i64 s[30:31]
|
|
entry:
|
|
%min = call <2 x half> @llvm.minimum.v2f16(<2 x half> %a, <2 x half> %b)
|
|
%res = call <2 x half> @llvm.minimum.v2f16(<2 x half> %c, <2 x half> %min)
|
|
ret <2 x half> %res
|
|
}
|
|
|
|
define <2 x half> @fminimum3_v2f16_vss(<2 x half> %a, <2 x half> inreg %b, <2 x half> inreg %c) {
|
|
; GFX1250-SDAG-LABEL: fminimum3_v2f16_vss:
|
|
; GFX1250-SDAG: ; %bb.0: ; %entry
|
|
; GFX1250-SDAG-NEXT: s_wait_loadcnt_dscnt 0x0
|
|
; GFX1250-SDAG-NEXT: s_wait_kmcnt 0x0
|
|
; GFX1250-SDAG-NEXT: v_pk_minimum3_f16 v0, s1, v0, s0
|
|
; GFX1250-SDAG-NEXT: s_set_pc_i64 s[30:31]
|
|
;
|
|
; GFX1250-GISEL-LABEL: fminimum3_v2f16_vss:
|
|
; GFX1250-GISEL: ; %bb.0: ; %entry
|
|
; GFX1250-GISEL-NEXT: s_wait_loadcnt_dscnt 0x0
|
|
; GFX1250-GISEL-NEXT: s_wait_kmcnt 0x0
|
|
; GFX1250-GISEL-NEXT: v_pk_minimum3_f16 v0, v0, s0, s0
|
|
; GFX1250-GISEL-NEXT: s_delay_alu instid0(VALU_DEP_1)
|
|
; GFX1250-GISEL-NEXT: v_pk_minimum3_f16 v0, s1, v0, v0
|
|
; GFX1250-GISEL-NEXT: s_set_pc_i64 s[30:31]
|
|
entry:
|
|
%min = call <2 x half> @llvm.minimum.v2f16(<2 x half> %a, <2 x half> %b)
|
|
%res = call <2 x half> @llvm.minimum.v2f16(<2 x half> %c, <2 x half> %min)
|
|
ret <2 x half> %res
|
|
}
|
|
|
|
define <3 x half> @fminimum3_v3f16(<3 x half> %a, <3 x half> %b, <3 x half> %c) {
|
|
; GFX1250-SDAG-LABEL: fminimum3_v3f16:
|
|
; GFX1250-SDAG: ; %bb.0: ; %entry
|
|
; GFX1250-SDAG-NEXT: s_wait_loadcnt_dscnt 0x0
|
|
; GFX1250-SDAG-NEXT: s_wait_kmcnt 0x0
|
|
; GFX1250-SDAG-NEXT: v_pk_minimum3_f16 v0, v4, v0, v2
|
|
; GFX1250-SDAG-NEXT: v_pk_minimum3_f16 v1, v5, v1, v3
|
|
; GFX1250-SDAG-NEXT: s_set_pc_i64 s[30:31]
|
|
;
|
|
; GFX1250-GISEL-FAKE16-LABEL: fminimum3_v3f16:
|
|
; GFX1250-GISEL-FAKE16: ; %bb.0: ; %entry
|
|
; GFX1250-GISEL-FAKE16-NEXT: s_wait_loadcnt_dscnt 0x0
|
|
; GFX1250-GISEL-FAKE16-NEXT: s_wait_kmcnt 0x0
|
|
; GFX1250-GISEL-FAKE16-NEXT: v_minimum_f16 v1, v1, v3
|
|
; GFX1250-GISEL-FAKE16-NEXT: v_pk_minimum3_f16 v0, v0, v2, v2
|
|
; GFX1250-GISEL-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
|
|
; GFX1250-GISEL-FAKE16-NEXT: v_minimum_f16 v1, v5, v1
|
|
; GFX1250-GISEL-FAKE16-NEXT: v_pk_minimum3_f16 v0, v4, v0, v0
|
|
; GFX1250-GISEL-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_1)
|
|
; GFX1250-GISEL-FAKE16-NEXT: v_and_b32_e32 v1, 0xffff, v1
|
|
; GFX1250-GISEL-FAKE16-NEXT: v_lshl_or_b32 v1, s0, 16, v1
|
|
; GFX1250-GISEL-FAKE16-NEXT: s_set_pc_i64 s[30:31]
|
|
;
|
|
; GFX1250-GISEL-REAL16-LABEL: fminimum3_v3f16:
|
|
; GFX1250-GISEL-REAL16: ; %bb.0: ; %entry
|
|
; GFX1250-GISEL-REAL16-NEXT: s_wait_loadcnt_dscnt 0x0
|
|
; GFX1250-GISEL-REAL16-NEXT: s_wait_kmcnt 0x0
|
|
; GFX1250-GISEL-REAL16-NEXT: v_pk_minimum3_f16 v0, v0, v2, v2
|
|
; GFX1250-GISEL-REAL16-NEXT: v_minimum_f16 v1.l, v1.l, v3.l
|
|
; GFX1250-GISEL-REAL16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
|
|
; GFX1250-GISEL-REAL16-NEXT: v_pk_minimum3_f16 v0, v4, v0, v0
|
|
; GFX1250-GISEL-REAL16-NEXT: v_minimum_f16 v1.l, v5.l, v1.l
|
|
; GFX1250-GISEL-REAL16-NEXT: s_set_pc_i64 s[30:31]
|
|
entry:
|
|
%min = call <3 x half> @llvm.minimum.v3f16(<3 x half> %a, <3 x half> %b)
|
|
%res = call <3 x half> @llvm.minimum.v3f16(<3 x half> %c, <3 x half> %min)
|
|
ret <3 x half> %res
|
|
}
|
|
|
|
define <4 x half> @fminimum3_v4f16(<4 x half> %a, <4 x half> %b, <4 x half> %c) {
|
|
; GFX1250-SDAG-LABEL: fminimum3_v4f16:
|
|
; GFX1250-SDAG: ; %bb.0: ; %entry
|
|
; GFX1250-SDAG-NEXT: s_wait_loadcnt_dscnt 0x0
|
|
; GFX1250-SDAG-NEXT: s_wait_kmcnt 0x0
|
|
; GFX1250-SDAG-NEXT: v_pk_minimum3_f16 v0, v4, v0, v2
|
|
; GFX1250-SDAG-NEXT: v_pk_minimum3_f16 v1, v5, v1, v3
|
|
; GFX1250-SDAG-NEXT: s_set_pc_i64 s[30:31]
|
|
;
|
|
; GFX1250-GISEL-LABEL: fminimum3_v4f16:
|
|
; GFX1250-GISEL: ; %bb.0: ; %entry
|
|
; GFX1250-GISEL-NEXT: s_wait_loadcnt_dscnt 0x0
|
|
; GFX1250-GISEL-NEXT: s_wait_kmcnt 0x0
|
|
; GFX1250-GISEL-NEXT: v_pk_minimum3_f16 v0, v0, v2, v2
|
|
; GFX1250-GISEL-NEXT: v_pk_minimum3_f16 v1, v1, v3, v3
|
|
; GFX1250-GISEL-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
|
|
; GFX1250-GISEL-NEXT: v_pk_minimum3_f16 v0, v4, v0, v0
|
|
; GFX1250-GISEL-NEXT: v_pk_minimum3_f16 v1, v5, v1, v1
|
|
; GFX1250-GISEL-NEXT: s_set_pc_i64 s[30:31]
|
|
entry:
|
|
%min = call <4 x half> @llvm.minimum.v4f16(<4 x half> %a, <4 x half> %b)
|
|
%res = call <4 x half> @llvm.minimum.v4f16(<4 x half> %c, <4 x half> %min)
|
|
ret <4 x half> %res
|
|
}
|
|
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
|
|
; GFX1250: {{.*}}
|
|
; GFX1250-SDAG-FAKE16: {{.*}}
|
|
; GFX1250-SDAG-REAL16: {{.*}}
|