[AMDGPU] V_CVT_F32_UBYTE{0,1,2,3} are full rate instructions

[critson]

Summary

Fix a bug in the scheduling model where V_CVT_F32_UBYTE{0,1,2,3} are incorrectly marked as quarter rate instructions.

[rampitec]

LGTM

llvm/trunk/lib/Target/AMDGPU/VOP1Instructions.td

 defm V_CVT_F16_F32 : VOP1Inst <"v_cvt_f16_f32", VOP_F16_F32, fpround>;
 } // End FPDPRounding = 1
 defm V_CVT_F32_F16 : VOP1Inst <"v_cvt_f32_f16", VOP_F32_F16, fpextend>;
 defm V_CVT_RPI_I32_F32 : VOP1Inst <"v_cvt_rpi_i32_f32", VOP_I32_F32, cvt_rpi_i32_f32>;
 defm V_CVT_FLR_I32_F32 : VOP1Inst <"v_cvt_flr_i32_f32", VOP_I32_F32, cvt_flr_i32_f32>;
 defm V_CVT_OFF_F32_I4 : VOP1Inst  <"v_cvt_off_f32_i4", VOP1_F32_I32>;
 defm V_CVT_F32_F64 : VOP1Inst <"v_cvt_f32_f64", VOP_F32_F64, fpround>;
 defm V_CVT_F64_F32 : VOP1Inst <"v_cvt_f64_f32", VOP_F64_F32, fpextend>;
+defm V_CVT_U32_F64 : VOP1Inst <"v_cvt_u32_f64", VOP_I32_F64, fp_to_uint>;
+defm V_CVT_F64_U32 : VOP1Inst <"v_cvt_f64_u32", VOP1_F64_I32, uint_to_fp>;
+} // End SchedRW = [WriteQuarterRate32]
+
 defm V_CVT_F32_UBYTE0 : VOP1Inst <"v_cvt_f32_ubyte0", VOP1_F32_I32, AMDGPUcvt_f32_ubyte0>;
 defm V_CVT_F32_UBYTE1 : VOP1Inst <"v_cvt_f32_ubyte1", VOP1_F32_I32, AMDGPUcvt_f32_ubyte1>;
 defm V_CVT_F32_UBYTE2 : VOP1Inst <"v_cvt_f32_ubyte2", VOP1_F32_I32, AMDGPUcvt_f32_ubyte2>;
 defm V_CVT_F32_UBYTE3 : VOP1Inst <"v_cvt_f32_ubyte3", VOP1_F32_I32, AMDGPUcvt_f32_ubyte3>;
-defm V_CVT_U32_F64 : VOP1Inst <"v_cvt_u32_f64", VOP_I32_F64, fp_to_uint>;
-defm V_CVT_F64_U32 : VOP1Inst <"v_cvt_f64_u32", VOP1_F64_I32, uint_to_fp>;
-} // End SchedRW = [WriteQuarterRate32]
 
 defm V_FRACT_F32 : VOP1Inst <"v_fract_f32", VOP_F32_F32, AMDGPUfract>;
 defm V_TRUNC_F32 : VOP1Inst <"v_trunc_f32", VOP_F32_F32, ftrunc>;
 defm V_CEIL_F32 : VOP1Inst <"v_ceil_f32", VOP_F32_F32, fceil>;
 defm V_RNDNE_F32 : VOP1Inst <"v_rndne_f32", VOP_F32_F32, frint>;
 defm V_FLOOR_F32 : VOP1Inst <"v_floor_f32", VOP_F32_F32, ffloor>;
 
 let SchedRW = [WriteQuarterRate32] in {

llvm/trunk/test/CodeGen/AMDGPU/cvt_f32_ubyte.ll

 ; SI-DAG: v_and_b32_e32 v{{[0-9]+}}, 0xffff,
 ; SI-DAG: v_and_b32_e32 v{{[0-9]+}}, 0xff00,
 ; SI-DAG: v_add_i32
 
 ; VI-DAG: v_and_b32_e32 v{{[0-9]+}}, 0xffffff00,
 ; VI-DAG: v_add_u16_e32
 ; VI-DAG: v_add_u16_e32
 
-; GCN: {{buffer|flat}}_store_dwordx4
-; GCN: {{buffer|flat}}_store_dword
+; GCN-DAG: {{buffer|flat}}_store_dwordx4
+; GCN-DAG: {{buffer|flat}}_store_dword
 
 ; GCN: s_endpgm
 define amdgpu_kernel void @load_v4i8_to_v4f32_2_uses(<4 x float> addrspace(1)* noalias %out, <4 x i8> addrspace(1)* noalias %out2, <4 x i8> addrspace(1)* noalias %in) nounwind {
   %tid.x = call i32 @llvm.amdgcn.workitem.id.x()
   %in.ptr = getelementptr <4 x i8>, <4 x i8> addrspace(1)* %in, i32 %tid.x
   %load = load <4 x i8>, <4 x i8> addrspace(1)* %in.ptr, align 4
   %cvt = uitofp <4 x i8> %load to <4 x float>
   store <4 x float> %cvt, <4 x float> addrspace(1)* %out, align 16

llvm/trunk/test/CodeGen/AMDGPU/udivrem24.ll

 ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
 ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
 ; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
 
 ; FUNC-LABEL: {{^}}udiv24_i8:
 ; SI: v_cvt_f32_ubyte
-; SI: v_cvt_f32_ubyte
-; SI: v_rcp_iflag_f32
+; SI-DAG: v_cvt_f32_ubyte
+; SI-DAG: v_rcp_iflag_f32
 ; SI: v_cvt_u32_f32
 
 ; EG: UINT_TO_FLT
 ; EG-DAG: UINT_TO_FLT
 ; EG-DAG: RECIP_IEEE
 ; EG: FLT_TO_UINT
 define amdgpu_kernel void @udiv24_i8(i8 addrspace(1)* %out, i8 addrspace(1)* %in) {
   %den_ptr = getelementptr i8, i8 addrspace(1)* %in, i8 1
define amdgpu_kernel void @test_no_udiv24_i32_2(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
   %den.i24 = lshr i32 %den.i24.0, 8
   %result = udiv i32 %num.i24, %den.i24
   store i32 %result, i32 addrspace(1)* %out, align 4
   ret void
 }
 
 ; FUNC-LABEL: {{^}}urem24_i8:
 ; SI: v_cvt_f32_ubyte
-; SI: v_cvt_f32_ubyte
-; SI: v_rcp_iflag_f32
+; SI-DAG: v_cvt_f32_ubyte
+; SI-DAG: v_rcp_iflag_f32
 ; SI: v_cvt_u32_f32
 
 ; EG: UINT_TO_FLT
 ; EG-DAG: UINT_TO_FLT
 ; EG-DAG: RECIP_IEEE
 ; EG: FLT_TO_UINT
 define amdgpu_kernel void @urem24_i8(i8 addrspace(1)* %out, i8 addrspace(1)* %in) {
   %den_ptr = getelementptr i8, i8 addrspace(1)* %in, i8 1