[AMDGPU] Precommit some scheduler related test updates

[foad]

Summary

The point of this is to make some tests with manual checks robust
against scheduler tweaks, so that only autogenerated test updates will
be required when pushing D68338 "[AMDGPU] Remove dubious logic in
bidirectional list scheduler".

[rampitec]

LGTM

llvm/test/CodeGen/AMDGPU/fadd.f16.ll

-; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI %s
-; RUN: llc -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
+; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs -enable-misched=false < %s | FileCheck -check-prefix=GCN -check-prefix=SI %s
+; RUN: llc -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs -enable-misched=false < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
 
 ; GCN-LABEL: {{^}}fadd_f16
 ; GCN: {{buffer|flat}}_load_ushort v[[A_F16:[0-9]+]]
 ; GCN: {{buffer|flat}}_load_ushort v[[B_F16:[0-9]+]]
 ; SI:  v_cvt_f32_f16_e32 v[[A_F32:[0-9]+]], v[[A_F16]]
 ; SI:  v_cvt_f32_f16_e32 v[[B_F32:[0-9]+]], v[[B_F16]]
 ; SI:  v_add_f32_e32 v[[R_F32:[0-9]+]], v[[A_F32]], v[[B_F32]]
 ; SI:  v_cvt_f16_f32_e32 v[[R_F16:[0-9]+]], v[[R_F32]]

llvm/test/CodeGen/AMDGPU/global-saddr.ll

 ; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -amdgpu-enable-global-sgpr-addr < %s | FileCheck -check-prefix=GFX9 %s
 
 ; Test for a conv2d like sequence of loads.
 
-; GFX9: global_load_dwordx4 v{{\[[0-9]+:[0-9]+\]}}, v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}{{$}}
-; GFX9: global_load_dwordx4 v{{\[[0-9]+:[0-9]+\]}}, v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}} offset:16{{$}}
-; GFX9: global_load_dwordx4 v{{\[[0-9]+:[0-9]+\]}}, v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}} offset:-16{{$}}
-; GFX9: global_load_dwordx4 v{{\[[0-9]+:[0-9]+\]}}, v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}} offset:-32{{$}}
-; GFX9: global_load_dwordx2 v{{\[[0-9]+:[0-9]+\]}}, v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}} offset:32{{$}}
+; GFX9-DAG: global_load_dwordx4 v{{\[[0-9]+:[0-9]+\]}}, v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}{{$}}
+; GFX9-DAG: global_load_dwordx4 v{{\[[0-9]+:[0-9]+\]}}, v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}} offset:16{{$}}
+; GFX9-DAG: global_load_dwordx2 v{{\[[0-9]+:[0-9]+\]}}, v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}} offset:32{{$}}
+; GFX9-DAG: global_load_dwordx4 v{{\[[0-9]+:[0-9]+\]}}, v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}} offset:-32{{$}}
+; GFX9-DAG: global_load_dwordx4 v{{\[[0-9]+:[0-9]+\]}}, v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}} offset:-16{{$}}
 ; GFX9: global_store_dwordx2 v{{\[[0-9]+:[0-9]+\]}}, v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}} offset:8{{$}}
 
 define hidden amdgpu_kernel void @simpleSaddrs(i64 addrspace(1)* %dst_image, i64 addrspace(1)* %src_image ) {
 entry:
   %id = call i32 @llvm.amdgcn.workitem.id.x()
   %idx = zext i32 %id to i64
   %gep = getelementptr i64, i64 addrspace(1)* %src_image, i64 %idx
   %ptr0 = getelementptr inbounds i64, i64 addrspace(1)* %gep, i64 1

llvm/test/CodeGen/AMDGPU/insert_vector_elt.v2i16.subtest-nosaddr.ll

-; RUN: llc -verify-machineinstrs -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -enable-amdgpu-aa=0 -mattr=+flat-for-global < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,VI,GFX89 %s
-; RUN: llc -verify-machineinstrs -mtriple=amdgcn-amd-amdhsa -mcpu=hawaii -enable-amdgpu-aa=0 -mattr=+flat-for-global < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,CI %s
+; RUN: llc -verify-machineinstrs -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -enable-amdgpu-aa=0 -mattr=+flat-for-global -enable-misched=false < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,VI,GFX89 %s
+; RUN: llc -verify-machineinstrs -mtriple=amdgcn-amd-amdhsa -mcpu=hawaii -enable-amdgpu-aa=0 -mattr=+flat-for-global -enable-misched=false < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,CI %s
 
 ; GCN-LABEL: {{^}}v_insertelement_v2i16_dynamic_vgpr:
-; GFX89-DAG: s_mov_b32 [[MASKK:s[0-9]+]], 0xffff{{$}}
-; GCN-DAG: s_mov_b32 [[K:s[0-9]+]], 0x3e703e7
 
 ; GCN: {{flat|global}}_load_dword [[IDX:v[0-9]+]]
 ; GCN: {{flat|global}}_load_dword [[VEC:v[0-9]+]]
 
-; GFX89-DAG: v_lshlrev_b32_e32 [[SCALED_IDX:v[0-9]+]], 4, [[IDX]]
-; GFX89-DAG: v_lshlrev_b32_e64 [[MASK:v[0-9]+]], [[SCALED_IDX]], [[MASKK]]
+; GFX89: s_mov_b32 [[MASKK:s[0-9]+]], 0xffff{{$}}
 
-; CI-DAG: v_lshlrev_b32_e32 [[SCALED_IDX:v[0-9]+]], 4, [[IDX]]
-; CI-DAG: v_lshl_b32_e32 [[MASK:v[0-9]+]], 0xffff, [[SCALED_IDX]]
+; GFX89: v_lshlrev_b32_e32 [[SCALED_IDX:v[0-9]+]], 4, [[IDX]]
+; GFX89: v_lshlrev_b32_e64 [[MASK:v[0-9]+]], [[SCALED_IDX]], [[MASKK]]
+
+; GCN: s_mov_b32 [[K:s[0-9]+]], 0x3e703e7
+
+; CI: v_lshlrev_b32_e32 [[SCALED_IDX:v[0-9]+]], 4, [[IDX]]
+; CI: v_lshl_b32_e32 [[MASK:v[0-9]+]], 0xffff, [[SCALED_IDX]]
 
 ; GCN: v_bfi_b32 [[RESULT:v[0-9]+]], [[MASK]], [[K]], [[VEC]]
 ; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[RESULT]]
 define amdgpu_kernel void @v_insertelement_v2i16_dynamic_vgpr(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in, i32 addrspace(1)* %idx.ptr) #0 {
   %tid = call i32 @llvm.amdgcn.workitem.id.x() #1
   %tid.ext = sext i32 %tid to i64
   %in.gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
   %idx.gep = getelementptr inbounds i32, i32 addrspace(1)* %idx.ptr, i64 %tid.ext

llvm/test/CodeGen/AMDGPU/insert_vector_elt.v2i16.subtest-saddr.ll

-; RUN: llc -verify-machineinstrs -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -enable-amdgpu-aa=0 -mattr=+flat-for-global,-fp64-fp16-denormals -amdgpu-enable-global-sgpr-addr < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9,GFX89 %s
+; RUN: llc -verify-machineinstrs -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -enable-amdgpu-aa=0 -mattr=+flat-for-global,-fp64-fp16-denormals -amdgpu-enable-global-sgpr-addr -enable-misched=false < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9,GFX89 %s
 
 ; GCN-LABEL: {{^}}v_insertelement_v2i16_dynamic_vgpr:
 
 ; GCN: {{flat|global}}_load_dword [[IDX:v[0-9]+]]
 ; GCN: {{flat|global}}_load_dword [[VEC:v[0-9]+]]
 
 ; GFX89-DAG: s_mov_b32 [[MASKK:s[0-9]+]], 0xffff{{$}}
 ; GCN-DAG: s_mov_b32 [[K:s[0-9]+]], 0x3e7

llvm/test/CodeGen/AMDGPU/mad-mix-lo.ll

-; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s
-; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,VI %s
-; RUN: llc -march=amdgcn -mcpu=hawaii -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,CI %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -enable-misched=false < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s
+; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs -enable-misched=false < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,VI %s
+; RUN: llc -march=amdgcn -mcpu=hawaii -verify-machineinstrs -enable-misched=false < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CIVI,CI %s
 
 ; GCN-LABEL: mixlo_simple:
 ; GCN: s_waitcnt
 ; GFX9-NEXT: v_mad_mixlo_f16 v0, v0, v1, v2{{$}}
 ; GFX9-NEXT: s_setpc_b64
 
 ; CIVI: v_mac_f32_e32
 ; CIVI: v_cvt_f16_f32_e32
define <2 x half> @v_mad_mix_v2f32_clamp_postcvt_hi(<2 x half> %src0, <2 x half> %src1, <2 x half> %src2) #0 {
   %max.hi = call half @llvm.maxnum.f16(half %cvt.hi, half 0.0)
   %clamp.hi = call half @llvm.minnum.f16(half %max.hi, half 1.0)
   %insert = insertelement <2 x half> %cvt.result, half %clamp.hi, i32 1
   ret <2 x half> %insert
 }
 
 ; FIXME: Should be able to use mixlo/mixhi
 ; GCN-LABEL: {{^}}v_mad_mix_v2f32_clamp_precvt:
-; GFX9: v_mad_mix_f32 v3, v0, v1, v2 op_sel_hi:[1,1,1] clamp
-; GFX9-NEXT: v_mad_mix_f32 v0, v0, v1, v2 op_sel:[1,1,1] op_sel_hi:[1,1,1] clamp
-; GFX9: v_cvt_f16_f32_e32 v1, v3
+; GFX9: v_mad_mix_f32 v3, v0, v1, v2 op_sel:[1,1,1] op_sel_hi:[1,1,1] clamp
+; GFX9-NEXT: v_mad_mix_f32 v0, v0, v1, v2 op_sel_hi:[1,1,1] clamp
 ; GFX9: v_cvt_f16_f32_e32 v0, v0
-; GFX9: v_and_b32_e32 v1, 0xffff, v1
-; GFX9: v_lshl_or_b32 v0, v0, 16, v1
+; GFX9: v_cvt_f16_f32_e32 v1, v3
+; GFX9: v_and_b32_e32 v0, 0xffff, v0
+; GFX9: v_lshl_or_b32 v0, v1, 16, v0
 ; GFX9: s_setpc_b64
 define <2 x half> @v_mad_mix_v2f32_clamp_precvt(<2 x half> %src0, <2 x half> %src1, <2 x half> %src2) #0 {
   %src0.ext = fpext <2 x half> %src0 to <2 x float>
   %src1.ext = fpext <2 x half> %src1 to <2 x float>
   %src2.ext = fpext <2 x half> %src2 to <2 x float>
   %result = tail call <2 x float> @llvm.fmuladd.v2f32(<2 x float> %src0.ext, <2 x float> %src1.ext, <2 x float> %src2.ext)
   %max = call <2 x float> @llvm.maxnum.v2f32(<2 x float> %result, <2 x float> zeroinitializer)
   %clamp = call <2 x float> @llvm.minnum.v2f32(<2 x float> %max, <2 x float> <float 1.0, float 1.0>)
   %cvt.result = fptrunc <2 x float> %clamp to <2 x half>
   ret <2 x half> %cvt.result
 }
 
 ; FIXME: Handling undef 4th component
 ; GCN-LABEL: {{^}}v_mad_mix_v3f32_clamp_precvt:
 ; GCN: s_waitcnt
-; GFX9-NEXT: v_mad_mix_f32 v6, v0, v2, v4 op_sel:[1,1,1] op_sel_hi:[1,1,1] clamp
+; GFX9-NEXT: v_mad_mix_f32 v1, v1, v3, v5 op_sel_hi:[1,1,1] clamp
+; GFX9-NEXT: v_mad_mix_f32 v3, v0, v2, v4 op_sel:[1,1,1] op_sel_hi:[1,1,1] clamp
 ; GFX9-NEXT: v_mad_mix_f32 v0, v0, v2, v4 op_sel_hi:[1,1,1] clamp
 ; GFX9-NEXT: v_cvt_f16_f32_e32 v0, v0
-; GFX9-NEXT: v_mad_mix_f32 v1, v1, v3, v5 op_sel_hi:[1,1,1] clamp
-; GFX9-NEXT: v_cvt_f16_f32_e32 v2, v6
+; GFX9-NEXT: v_cvt_f16_f32_e32 v2, v3
 ; GFX9-NEXT: v_cvt_f16_f32_e32 v1, v1
 ; GFX9-NEXT: v_and_b32_e32 v0, 0xffff, v0
 ; GFX9-NEXT: v_lshl_or_b32 v0, v2, 16, v0
 ; GFX9-NEXT: s_setpc_b64
 define <3 x half> @v_mad_mix_v3f32_clamp_precvt(<3 x half> %src0, <3 x half> %src1, <3 x half> %src2) #0 {
   %src0.ext = fpext <3 x half> %src0 to <3 x float>
   %src1.ext = fpext <3 x half> %src1 to <3 x float>
   %src2.ext = fpext <3 x half> %src2 to <3 x float>

llvm/test/CodeGen/AMDGPU/nsa-reassign.ll

-; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -enable-misched=0 < %s | FileCheck -check-prefix=GCN %s
 
 ; GCN-LABEL: {{^}}sample_contig_nsa:
 ; GCN-DAG: image_sample_c_l v{{[0-9]+}}, v[{{[0-9]+:[0-9]+}}],
 ; GCN-DAG: image_sample v{{[0-9]+}}, v[{{[0-9]+:[0-9]+}}],
 define amdgpu_ps <2 x float> @sample_contig_nsa(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, float %s1, float %t1, float %r1, float %lod, float %r2, float %s2, float %t2) {
 main_body:
   %zcompare.1 = fadd float %zcompare, 1.0
   %s1.1 = fadd float %s1, 1.0
   %t1.1 = fadd float %t1, 1.0
   %r1.1 = fadd float %r1, 1.0
   %s2.1 = fadd float %s2, 1.0
   %t2.1 = fadd float %t2, 1.0
   %r2.1 = fadd float %r2, 1.0
   %lod.1 = fadd float %lod, 1.0
   %v1 = call float @llvm.amdgcn.image.sample.c.l.3d.f32.f32(i32 1, float %zcompare.1, float %s1.1, float %t1.1, float %r1.1, float %lod.1, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
   %v2 = call float @llvm.amdgcn.image.sample.3d.f32.f32(i32 1, float %s2.1, float %t2.1, float %r2.1, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
   %r.0 = insertelement <2 x float> undef, float %v1, i32 0
   %r = insertelement <2 x float> %r.0, float %v2, i32 1
   ret <2 x float> %r
 }
 
 ; GCN-LABEL: {{^}}sample_contig_nsa_10vgprs:
-; GCN-DAG: image_sample_c_l v{{[0-9]+}}, [{{v[0-9]+, v[0-9]+, v[0-9]+, v[0-9]+, v[0-9]+}}],
-; GCN-DAG: image_sample v{{[0-9]+}}, [{{v[0-9]+, v[0-9]+, v[0-9]+}}],
+; GCN-DAG: image_sample_c_l v{{[0-9]+}}, v[{{[0-9]+:[0-9]+}}],
+; GCN-DAG: image_sample v{{[0-9]+}}, v[{{[0-9]+:[0-9]+}}],
 define amdgpu_ps <2 x float> @sample_contig_nsa_10vgprs(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, float %s1, float %t1, float %r1, float %lod, float %r2, float %s2, float %t2) #0 {
 main_body:
   %zcompare.1 = fadd float %zcompare, 1.0
   %s1.1 = fadd float %s1, 1.0
   %t1.1 = fadd float %t1, 1.0
   %r1.1 = fadd float %r1, 1.0
   %s2.1 = fadd float %s2, 1.0
   %t2.1 = fadd float %t2, 1.0