4a9bc59867
Add signed and unsigned integer version of med3 combine. Source pattern is min(max(Val, K0), K1) or max(min(Val, K1), K0) where K0 and K1 are constants and K0 <= K1. Destination is med3 that corresponds to signedness of min/max in source. Differential Revision: https://reviews.llvm.org/D90050
128 lines
4.6 KiB
LLVM
128 lines
4.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -global-isel -mtriple=amdgcn-amd-mesa3d -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX10 %s
|
|
|
|
define i32 @test_min_max_ValK0_K1_u32(i32 %a) {
|
|
; GFX10-LABEL: test_min_max_ValK0_K1_u32:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-NEXT: v_med3_u32 v0, v0, 12, 17
|
|
; GFX10-NEXT: s_setpc_b64 s[30:31]
|
|
%umax = call i32 @llvm.umax.i32(i32 %a, i32 12)
|
|
%umed = call i32 @llvm.umin.i32(i32 %umax, i32 17)
|
|
ret i32 %umed
|
|
}
|
|
|
|
define i32 @min_max_ValK0_K1_i32(i32 %a) {
|
|
; GFX10-LABEL: min_max_ValK0_K1_i32:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-NEXT: v_med3_u32 v0, v0, 12, 17
|
|
; GFX10-NEXT: s_setpc_b64 s[30:31]
|
|
%umax = call i32 @llvm.umax.i32(i32 12, i32 %a)
|
|
%umed = call i32 @llvm.umin.i32(i32 %umax, i32 17)
|
|
ret i32 %umed
|
|
}
|
|
|
|
define i32 @test_min_K1max_ValK0__u32(i32 %a) {
|
|
; GFX10-LABEL: test_min_K1max_ValK0__u32:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-NEXT: v_med3_u32 v0, v0, 12, 17
|
|
; GFX10-NEXT: s_setpc_b64 s[30:31]
|
|
%umax = call i32 @llvm.umax.i32(i32 %a, i32 12)
|
|
%umed = call i32 @llvm.umin.i32(i32 17, i32 %umax)
|
|
ret i32 %umed
|
|
}
|
|
|
|
define i32 @test_min_K1max_K0Val__u32(i32 %a) {
|
|
; GFX10-LABEL: test_min_K1max_K0Val__u32:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-NEXT: v_med3_u32 v0, v0, 12, 17
|
|
; GFX10-NEXT: s_setpc_b64 s[30:31]
|
|
%umax = call i32 @llvm.umax.i32(i32 12, i32 %a)
|
|
%umed = call i32 @llvm.umin.i32(i32 17, i32 %umax)
|
|
ret i32 %umed
|
|
}
|
|
|
|
define i32 @test_max_min_ValK1_K0_u32(i32 %a) {
|
|
; GFX10-LABEL: test_max_min_ValK1_K0_u32:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-NEXT: v_med3_u32 v0, v0, 12, 17
|
|
; GFX10-NEXT: s_setpc_b64 s[30:31]
|
|
%umin = call i32 @llvm.umin.i32(i32 %a, i32 17)
|
|
%umed = call i32 @llvm.umax.i32(i32 %umin, i32 12)
|
|
ret i32 %umed
|
|
}
|
|
|
|
define i32 @test_max_min_K1Val_K0_u32(i32 %a) {
|
|
; GFX10-LABEL: test_max_min_K1Val_K0_u32:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-NEXT: v_med3_u32 v0, v0, 12, 17
|
|
; GFX10-NEXT: s_setpc_b64 s[30:31]
|
|
%umin = call i32 @llvm.umin.i32(i32 17, i32 %a)
|
|
%umed = call i32 @llvm.umax.i32(i32 %umin, i32 12)
|
|
ret i32 %umed
|
|
}
|
|
|
|
define i32 @test_max_K0min_ValK1__u32(i32 %a) {
|
|
; GFX10-LABEL: test_max_K0min_ValK1__u32:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-NEXT: v_med3_u32 v0, v0, 12, 17
|
|
; GFX10-NEXT: s_setpc_b64 s[30:31]
|
|
%umin = call i32 @llvm.umin.i32(i32 %a, i32 17)
|
|
%umed = call i32 @llvm.umax.i32(i32 12, i32 %umin)
|
|
ret i32 %umed
|
|
}
|
|
|
|
define i32 @test_max_K0min_K1Val__u32(i32 %a) {
|
|
; GFX10-LABEL: test_max_K0min_K1Val__u32:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-NEXT: v_med3_u32 v0, v0, 12, 17
|
|
; GFX10-NEXT: s_setpc_b64 s[30:31]
|
|
%umin = call i32 @llvm.umin.i32(i32 17, i32 %a)
|
|
%umed = call i32 @llvm.umax.i32(i32 12, i32 %umin)
|
|
ret i32 %umed
|
|
}
|
|
|
|
define <2 x i16> @test_max_K0min_K1Val__v2u16(<2 x i16> %a) {
|
|
; GFX10-LABEL: test_max_K0min_K1Val__v2u16:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-NEXT: v_pk_min_u16 v0, 17, v0 op_sel_hi:[0,1]
|
|
; GFX10-NEXT: v_pk_max_u16 v0, 12, v0 op_sel_hi:[0,1]
|
|
; GFX10-NEXT: s_setpc_b64 s[30:31]
|
|
%umin = call <2 x i16> @llvm.umin.v2i16(<2 x i16> <i16 17, i16 17>, <2 x i16> %a)
|
|
%umed = call <2 x i16> @llvm.umax.v2i16(<2 x i16> <i16 12, i16 12>, <2 x i16> %umin)
|
|
ret <2 x i16> %umed
|
|
}
|
|
|
|
define amdgpu_ps i32 @test_uniform_min_max(i32 inreg %a) {
|
|
; GFX10-LABEL: test_uniform_min_max:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_max_u32 s0, s2, 12
|
|
; GFX10-NEXT: s_min_u32 s0, s0, 17
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
%umax = call i32 @llvm.umax.i32(i32 %a, i32 12)
|
|
%umed = call i32 @llvm.umin.i32(i32 %umax, i32 17)
|
|
ret i32 %umed
|
|
}
|
|
|
|
declare i32 @llvm.umin.i32(i32, i32)
|
|
declare i32 @llvm.umax.i32(i32, i32)
|
|
declare <2 x i16> @llvm.umin.v2i16(<2 x i16>, <2 x i16>)
|
|
declare <2 x i16> @llvm.umax.v2i16(<2 x i16>, <2 x i16>)
|