[AMDGPU] Fixed some instructions latencies

Differential Revision: https://reviews.llvm.org/D45073

llvm-svn: 328874

2 files changed, 13 insertions, 13 deletions

diff --git a/llvm/lib/Target/AMDGPU/VOP1Instructions.td b/llvm/lib/Target/AMDGPU/VOP1Instructions.td
index f793fe6b249..38bca6ca35b 100644
--- a/llvm/lib/Target/AMDGPU/VOP1Instructions.td
+++ b/llvm/lib/Target/AMDGPU/VOP1Instructions.td
@@ -193,13 +193,14 @@ 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>;
-defm V_EXP_F32 : VOP1Inst <"v_exp_f32", VOP_F32_F32, fexp2>;
 
 let SchedRW = [WriteQuarterRate32] in {
+defm V_EXP_F32 : VOP1Inst <"v_exp_f32", VOP_F32_F32, fexp2>;
 defm V_LOG_F32 : VOP1Inst <"v_log_f32", VOP_F32_F32, flog2>;
 defm V_RCP_F32 : VOP1Inst <"v_rcp_f32", VOP_F32_F32, AMDGPUrcp>;
 defm V_RCP_IFLAG_F32 : VOP1Inst <"v_rcp_iflag_f32", VOP_F32_F32>;
 defm V_RSQ_F32 : VOP1Inst <"v_rsq_f32", VOP_F32_F32, AMDGPUrsq>;
+defm V_SQRT_F32 : VOP1Inst <"v_sqrt_f32", VOP_F32_F32, fsqrt>;
 } // End SchedRW = [WriteQuarterRate32]
 
 let SchedRW = [WriteDouble] in {
@@ -207,8 +208,6 @@ defm V_RCP_F64 : VOP1Inst <"v_rcp_f64", VOP_F64_F64, AMDGPUrcp>;
 defm V_RSQ_F64 : VOP1Inst <"v_rsq_f64", VOP_F64_F64, AMDGPUrsq>;
 } // End SchedRW = [WriteDouble];
 
-defm V_SQRT_F32 : VOP1Inst <"v_sqrt_f32", VOP_F32_F32, fsqrt>;
-
 let SchedRW = [WriteDouble] in {
 defm V_SQRT_F64 : VOP1Inst <"v_sqrt_f64", VOP_F64_F64, fsqrt>;
 } // End SchedRW = [WriteDouble]
@@ -223,9 +222,9 @@ defm V_BFREV_B32 : VOP1Inst <"v_bfrev_b32", VOP_I32_I32>;
 defm V_FFBH_U32 : VOP1Inst <"v_ffbh_u32", VOP_I32_I32>;
 defm V_FFBL_B32 : VOP1Inst <"v_ffbl_b32", VOP_I32_I32>;
 defm V_FFBH_I32 : VOP1Inst <"v_ffbh_i32", VOP_I32_I32>;
-defm V_FREXP_EXP_I32_F64 : VOP1Inst <"v_frexp_exp_i32_f64", VOP_I32_F64, int_amdgcn_frexp_exp>;
 
 let SchedRW = [WriteDoubleAdd] in {
+defm V_FREXP_EXP_I32_F64 : VOP1Inst <"v_frexp_exp_i32_f64", VOP_I32_F64, int_amdgcn_frexp_exp>;
 defm V_FREXP_MANT_F64 : VOP1Inst <"v_frexp_mant_f64", VOP_F64_F64, int_amdgcn_frexp_mant>;
 defm V_FRACT_F64 : VOP1Inst <"v_fract_f64", VOP_F64_F64, AMDGPUfract>;
 } // End SchedRW = [WriteDoubleAdd]
@@ -289,9 +288,7 @@ defm V_MOVRELS_B32 : VOP1Inst <"v_movrels_b32", VOP_I32_VI32_NO_EXT>;
 defm V_MOVRELSD_B32 : VOP1Inst <"v_movrelsd_b32", VOP_NO_EXT<VOP_I32_I32>>;
 } // End Uses = [M0, EXEC]
 
-let SchedRW = [WriteQuarterRate32] in {
 defm V_MOV_FED_B32 : VOP1Inst <"v_mov_fed_b32", VOP_I32_I32>;
-}
 
 // These instruction only exist on SI and CI
 let SubtargetPredicate = isSICI in {
@@ -335,11 +332,15 @@ defm V_CVT_F16_U16 : VOP1Inst <"v_cvt_f16_u16", VOP1_F16_I16, uint_to_fp>;
 defm V_CVT_F16_I16 : VOP1Inst <"v_cvt_f16_i16", VOP1_F16_I16, sint_to_fp>;
 defm V_CVT_U16_F16 : VOP1Inst <"v_cvt_u16_f16", VOP_I16_F16, fp_to_uint>;
 defm V_CVT_I16_F16 : VOP1Inst <"v_cvt_i16_f16", VOP_I16_F16, fp_to_sint>;
+let SchedRW = [WriteQuarterRate32] in {
 defm V_RCP_F16 : VOP1Inst <"v_rcp_f16", VOP_F16_F16, AMDGPUrcp>;
 defm V_SQRT_F16 : VOP1Inst <"v_sqrt_f16", VOP_F16_F16, fsqrt>;
 defm V_RSQ_F16 : VOP1Inst <"v_rsq_f16", VOP_F16_F16, AMDGPUrsq>;
 defm V_LOG_F16 : VOP1Inst <"v_log_f16", VOP_F16_F16, flog2>;
 defm V_EXP_F16 : VOP1Inst <"v_exp_f16", VOP_F16_F16, fexp2>;
+defm V_SIN_F16 : VOP1Inst <"v_sin_f16", VOP_F16_F16, AMDGPUsin>;
+defm V_COS_F16 : VOP1Inst <"v_cos_f16", VOP_F16_F16, AMDGPUcos>;
+} // End SchedRW = [WriteQuarterRate32]
 defm V_FREXP_MANT_F16 : VOP1Inst <"v_frexp_mant_f16", VOP_F16_F16, int_amdgcn_frexp_mant>;
 defm V_FREXP_EXP_I16_F16 : VOP1Inst <"v_frexp_exp_i16_f16", VOP_I16_F16, int_amdgcn_frexp_exp>;
 defm V_FLOOR_F16 : VOP1Inst <"v_floor_f16", VOP_F16_F16, ffloor>;
@@ -347,8 +348,6 @@ defm V_CEIL_F16 : VOP1Inst <"v_ceil_f16", VOP_F16_F16, fceil>;
 defm V_TRUNC_F16 : VOP1Inst <"v_trunc_f16", VOP_F16_F16, ftrunc>;
 defm V_RNDNE_F16 : VOP1Inst <"v_rndne_f16", VOP_F16_F16, frint>;
 defm V_FRACT_F16 : VOP1Inst <"v_fract_f16", VOP_F16_F16, AMDGPUfract>;
-defm V_SIN_F16 : VOP1Inst <"v_sin_f16", VOP_F16_F16, AMDGPUsin>;
-defm V_COS_F16 : VOP1Inst <"v_cos_f16", VOP_F16_F16, AMDGPUcos>;
 
 }
 
diff --git a/llvm/lib/Target/AMDGPU/VOP3Instructions.td b/llvm/lib/Target/AMDGPU/VOP3Instructions.td
index 8c1a83b5d50..922187c1d12 100644
--- a/llvm/lib/Target/AMDGPU/VOP3Instructions.td
+++ b/llvm/lib/Target/AMDGPU/VOP3Instructions.td
@@ -283,10 +283,10 @@ def V_MAD_F32 : VOP3Inst <"v_mad_f32", VOP3_Profile<VOP_F32_F32_F32_F32>, fmad>;
 def V_MAD_I32_I24 : VOP3Inst <"v_mad_i32_i24", VOP3_Profile<VOP_I32_I32_I32_I32, VOP3_CLAMP>>;
 def V_MAD_U32_U24 : VOP3Inst <"v_mad_u32_u24", VOP3_Profile<VOP_I32_I32_I32_I32, VOP3_CLAMP>>;
 def V_FMA_F32 : VOP3Inst <"v_fma_f32", VOP3_Profile<VOP_F32_F32_F32_F32>, fma>;
-def V_FMA_F64 : VOP3Inst <"v_fma_f64", VOP3_Profile<VOP_F64_F64_F64_F64>, fma>;
 def V_LERP_U8 : VOP3Inst <"v_lerp_u8", VOP3_Profile<VOP_I32_I32_I32_I32>, int_amdgcn_lerp>;
 
 let SchedRW = [WriteDoubleAdd] in {
+def V_FMA_F64 : VOP3Inst <"v_fma_f64", VOP3_Profile<VOP_F64_F64_F64_F64>, fma>;
 def V_ADD_F64 : VOP3Inst <"v_add_f64", VOP3_Profile<VOP_F64_F64_F64>, fadd, 1>;
 def V_MUL_F64 : VOP3Inst <"v_mul_f64", VOP3_Profile<VOP_F64_F64_F64>, fmul, 1>;
 def V_MIN_F64 : VOP3Inst <"v_min_f64", VOP3_Profile<VOP_F64_F64_F64>, fminnum, 1>;
@@ -374,6 +374,7 @@ def V_TRIG_PREOP_F64 : VOP3Inst <"v_trig_preop_f64", VOP3_Profile<VOP_F64_F64_I3
   let SchedRW = [WriteDouble];
 }
 
+let SchedRW = [Write64Bit] in {
 // These instructions only exist on SI and CI
 let SubtargetPredicate = isSICI in {
 def V_LSHL_B64 : VOP3Inst <"v_lshl_b64", VOP3_Profile<VOP_I64_I64_I32>>;
@@ -387,17 +388,17 @@ def V_LSHLREV_B64 : VOP3Inst <"v_lshlrev_b64", VOP3_Profile<VOP_I64_I32_I64>>;
 def V_LSHRREV_B64 : VOP3Inst <"v_lshrrev_b64", VOP3_Profile<VOP_I64_I32_I64>>;
 def V_ASHRREV_I64 : VOP3Inst <"v_ashrrev_i64", VOP3_Profile<VOP_I64_I32_I64>>;
 } // End SubtargetPredicate = isVI
-
+} // End SchedRW = [Write64Bit]
 
 let SubtargetPredicate = isCIVI in {
 
-let Constraints = "@earlyclobber $vdst" in {
+let Constraints = "@earlyclobber $vdst", SchedRW = [WriteQuarterRate32] in {
 def V_QSAD_PK_U16_U8 : VOP3Inst <"v_qsad_pk_u16_u8", VOP3_Profile<VOP_I64_I64_I32_I64, VOP3_CLAMP>>;
 def V_MQSAD_U32_U8 : VOP3Inst <"v_mqsad_u32_u8", VOP3_Profile<VOP_V4I32_I64_I32_V4I32, VOP3_CLAMP>>;
-} // End Constraints = "@earlyclobber $vdst"
+} // End Constraints = "@earlyclobber $vdst", SchedRW = [WriteQuarterRate32]
 
 let isCommutable = 1 in {
-let SchedRW = [WriteDouble, WriteSALU] in {
+let SchedRW = [WriteQuarterRate32, WriteSALU] in {
 def V_MAD_U64_U32 : VOP3Inst <"v_mad_u64_u32", VOP3b_I64_I1_I32_I32_I64>;
 def V_MAD_I64_I32 : VOP3Inst <"v_mad_i64_i32", VOP3b_I64_I1_I32_I32_I64>;
 } // End SchedRW = [WriteDouble, WriteSALU]