| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4 | |
| ; RUN: llc -global-isel=0 -mtriple=amdgpu12.50 -mattr=-real-true16 < %s | FileCheck --check-prefixes=GFX1250,GFX1250-SDAG,GFX1250-SDAG-FAKE16 %s | |
| ; RUN: llc -global-isel=1 -mtriple=amdgpu12.50 -mattr=-real-true16 < %s | FileCheck --check-prefixes=GFX1250,GFX1250-GISEL,GFX1250-GISEL-FAKE16 %s | |
| ; RUN: llc -global-isel=0 -mtriple=amdgpu12.50 -mattr=+real-true16 < %s | FileCheck --check-prefixes=GFX1250,GFX1250-SDAG,GFX1250-SDAG-REAL16 %s | |
| ; RUN: llc -global-isel=1 -mtriple=amdgpu12.50 -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-LABEL: fminimum3_v2f16: | |
| ; GFX1250: ; %bb.0: ; %entry | |
| ; GFX1250-NEXT: s_wait_loadcnt_dscnt 0x0 | |
| ; GFX1250-NEXT: s_wait_kmcnt 0x0 | |
| ; GFX1250-NEXT: v_pk_minimum3_f16 v0, v2, v0, v1 | |
| ; GFX1250-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-LABEL: fminimum3_v2f16_vss: | |
| ; GFX1250: ; %bb.0: ; %entry | |
| ; GFX1250-NEXT: s_wait_loadcnt_dscnt 0x0 | |
| ; GFX1250-NEXT: s_wait_kmcnt 0x0 | |
| ; GFX1250-NEXT: v_pk_minimum3_f16 v0, s1, v0, s0 | |
| ; GFX1250-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_minimum3_f16 v1, v1, v3, v5 | |
| ; GFX1250-GISEL-FAKE16-NEXT: v_pk_minimum3_f16 v0, v4, v0, v2 | |
| ; 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, v4, v0, v2 | |
| ; GFX1250-GISEL-REAL16-NEXT: v_minimum3_f16 v1.l, v1.l, v3.l, v5.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-LABEL: fminimum3_v4f16: | |
| ; GFX1250: ; %bb.0: ; %entry | |
| ; GFX1250-NEXT: s_wait_loadcnt_dscnt 0x0 | |
| ; GFX1250-NEXT: s_wait_kmcnt 0x0 | |
| ; GFX1250-NEXT: v_pk_minimum3_f16 v0, v4, v0, v2 | |
| ; GFX1250-NEXT: v_pk_minimum3_f16 v1, v5, v1, v3 | |
| ; GFX1250-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-GISEL: {{.*}} | |
| ; GFX1250-SDAG-FAKE16: {{.*}} | |
| ; GFX1250-SDAG-REAL16: {{.*}} |