aboutsummaryrefslogtreecommitdiff
path: root/llvm/test/CodeGen/AMDGPU/fmaximum3.v2f16.ll
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/fmaximum3.v2f16.ll')
-rw-r--r--llvm/test/CodeGen/AMDGPU/fmaximum3.v2f16.ll99
1 files changed, 99 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/fmaximum3.v2f16.ll b/llvm/test/CodeGen/AMDGPU/fmaximum3.v2f16.ll
new file mode 100644
index 0000000..852c9cf
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/fmaximum3.v2f16.ll
@@ -0,0 +1,99 @@
+; 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 < %s | FileCheck --check-prefixes=GFX1250,GFX1250-SDAG %s
+; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx1250 < %s | FileCheck --check-prefixes=GFX1250,GFX1250-GISEL %s
+
+define <2 x half> @fmaximum3_v2f16(<2 x half> %a, <2 x half> %b, <2 x half> %c) {
+; GFX1250-SDAG-LABEL: fmaximum3_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_maximum3_f16 v0, v2, v0, v1
+; GFX1250-SDAG-NEXT: s_set_pc_i64 s[30:31]
+;
+; GFX1250-GISEL-LABEL: fmaximum3_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_maximum3_f16 v0, v0, v1, v1
+; GFX1250-GISEL-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GFX1250-GISEL-NEXT: v_pk_maximum3_f16 v0, v2, v0, v0
+; GFX1250-GISEL-NEXT: s_set_pc_i64 s[30:31]
+entry:
+ %min = call <2 x half> @llvm.maximum.v2f16(<2 x half> %a, <2 x half> %b)
+ %res = call <2 x half> @llvm.maximum.v2f16(<2 x half> %c, <2 x half> %min)
+ ret <2 x half> %res
+}
+
+define <2 x half> @fmaximum3_v2f16_vss(<2 x half> %a, <2 x half> inreg %b, <2 x half> inreg %c) {
+; GFX1250-SDAG-LABEL: fmaximum3_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_maximum3_f16 v0, s1, v0, s0
+; GFX1250-SDAG-NEXT: s_set_pc_i64 s[30:31]
+;
+; GFX1250-GISEL-LABEL: fmaximum3_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_maximum3_f16 v0, v0, s0, s0
+; GFX1250-GISEL-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GFX1250-GISEL-NEXT: v_pk_maximum3_f16 v0, s1, v0, v0
+; GFX1250-GISEL-NEXT: s_set_pc_i64 s[30:31]
+entry:
+ %min = call <2 x half> @llvm.maximum.v2f16(<2 x half> %a, <2 x half> %b)
+ %res = call <2 x half> @llvm.maximum.v2f16(<2 x half> %c, <2 x half> %min)
+ ret <2 x half> %res
+}
+
+define <3 x half> @fmaximum3_v3f16(<3 x half> %a, <3 x half> %b, <3 x half> %c) {
+; GFX1250-SDAG-LABEL: fmaximum3_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_maximum3_f16 v0, v4, v0, v2
+; GFX1250-SDAG-NEXT: v_pk_maximum3_f16 v1, v5, v1, v3
+; GFX1250-SDAG-NEXT: s_set_pc_i64 s[30:31]
+;
+; GFX1250-GISEL-LABEL: fmaximum3_v3f16:
+; 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_maximum3_f16 v0, v0, v2, v2
+; GFX1250-GISEL-NEXT: v_maximum_f16 v1, v1, v3
+; GFX1250-GISEL-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX1250-GISEL-NEXT: v_pk_maximum3_f16 v0, v4, v0, v0
+; GFX1250-GISEL-NEXT: v_maximum_f16 v1, v5, v1
+; GFX1250-GISEL-NEXT: s_set_pc_i64 s[30:31]
+entry:
+ %min = call <3 x half> @llvm.maximum.v3f16(<3 x half> %a, <3 x half> %b)
+ %res = call <3 x half> @llvm.maximum.v3f16(<3 x half> %c, <3 x half> %min)
+ ret <3 x half> %res
+}
+
+define <4 x half> @fmaximum3_v4f16(<4 x half> %a, <4 x half> %b, <4 x half> %c) {
+; GFX1250-SDAG-LABEL: fmaximum3_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_maximum3_f16 v0, v4, v0, v2
+; GFX1250-SDAG-NEXT: v_pk_maximum3_f16 v1, v5, v1, v3
+; GFX1250-SDAG-NEXT: s_set_pc_i64 s[30:31]
+;
+; GFX1250-GISEL-LABEL: fmaximum3_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_maximum3_f16 v0, v0, v2, v2
+; GFX1250-GISEL-NEXT: v_pk_maximum3_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_maximum3_f16 v0, v4, v0, v0
+; GFX1250-GISEL-NEXT: v_pk_maximum3_f16 v1, v5, v1, v1
+; GFX1250-GISEL-NEXT: s_set_pc_i64 s[30:31]
+entry:
+ %min = call <4 x half> @llvm.maximum.v4f16(<4 x half> %a, <4 x half> %b)
+ %res = call <4 x half> @llvm.maximum.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: {{.*}}