[AMDGPU] Add intrinsics for 16 bit interpolation
Summary:
Added the intrinsics llvm.amdgcn.interp.p1.f16() and
llvm.amdgcn.interp.p2.f16() and related LIT test.
The p1 intrinsic generates code appropriate for both 16 and 32
bank LDS.
Reviewers: #amdgpu, dstuttard, arsenm, tpr
Reviewed By: #amdgpu, arsenm
Subscribers: jvesely, mgorny, arsenm, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D46754
llvm-svn: 352357
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
index f170bc5..a15b2b9 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
@@ -4183,6 +4183,9 @@
NODE_NAME_CASE(INTERP_MOV)
NODE_NAME_CASE(INTERP_P1)
NODE_NAME_CASE(INTERP_P2)
+ NODE_NAME_CASE(INTERP_P1LL_F16)
+ NODE_NAME_CASE(INTERP_P1LV_F16)
+ NODE_NAME_CASE(INTERP_P2_F16)
NODE_NAME_CASE(STORE_MSKOR)
NODE_NAME_CASE(LOAD_CONSTANT)
NODE_NAME_CASE(TBUFFER_STORE_FORMAT)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h
index 557479a..8b8e16e 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h
@@ -462,6 +462,9 @@
INTERP_MOV,
INTERP_P1,
INTERP_P2,
+ INTERP_P1LL_F16,
+ INTERP_P1LV_F16,
+ INTERP_P2_F16,
PC_ADD_REL_OFFSET,
KILL,
DUMMY_CHAIN,
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.td b/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.td
index 3702c3f..73ae5de 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.td
@@ -369,6 +369,17 @@
SDTypeProfile<1, 4, [SDTCisFP<0>]>,
[SDNPInGlue]>;
+def AMDGPUinterp_p1ll_f16 : SDNode<"AMDGPUISD::INTERP_P1LL_F16",
+ SDTypeProfile<1, 7, [SDTCisFP<0>]>,
+ [SDNPInGlue, SDNPOutGlue]>;
+
+def AMDGPUinterp_p1lv_f16 : SDNode<"AMDGPUISD::INTERP_P1LV_F16",
+ SDTypeProfile<1, 9, [SDTCisFP<0>]>,
+ [SDNPInGlue, SDNPOutGlue]>;
+
+def AMDGPUinterp_p2_f16 : SDNode<"AMDGPUISD::INTERP_P2_F16",
+ SDTypeProfile<1, 8, [SDTCisFP<0>]>,
+ [SDNPInGlue]>;
def AMDGPUkill : SDNode<"AMDGPUISD::KILL", AMDGPUKillSDT,
[SDNPHasChain, SDNPSideEffect]>;
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td b/llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td
index cca656b..916b1ef 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td
@@ -48,6 +48,8 @@
def : SourceOfDivergence<int_amdgcn_interp_mov>;
def : SourceOfDivergence<int_amdgcn_interp_p1>;
def : SourceOfDivergence<int_amdgcn_interp_p2>;
+def : SourceOfDivergence<int_amdgcn_interp_p1_f16>;
+def : SourceOfDivergence<int_amdgcn_interp_p2_f16>;
def : SourceOfDivergence<int_amdgcn_mbcnt_hi>;
def : SourceOfDivergence<int_amdgcn_mbcnt_lo>;
def : SourceOfDivergence<int_r600_read_tidig_x>;
diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
index 117014d..0c1fca8 100644
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -5292,6 +5292,59 @@
Op.getOperand(2), Op.getOperand(3), Op.getOperand(4),
Glue);
}
+ case Intrinsic::amdgcn_interp_p1_f16: {
+ SDValue M0 = copyToM0(DAG, DAG.getEntryNode(), DL, Op.getOperand(5));
+ SDValue Glue = M0.getValue(1);
+ if (getSubtarget()->getLDSBankCount() == 16) {
+ // 16 bank LDS
+ SDValue S = DAG.getNode(AMDGPUISD::INTERP_MOV, DL, MVT::f32,
+ DAG.getConstant(2, DL, MVT::i32), // P0
+ Op.getOperand(2), // Attrchan
+ Op.getOperand(3), // Attr
+ Glue);
+ SDValue Ops[] = {
+ Op.getOperand(1), // Src0
+ Op.getOperand(2), // Attrchan
+ Op.getOperand(3), // Attr
+ DAG.getConstant(0, DL, MVT::i32), // $src0_modifiers
+ S, // Src2 - holds two f16 values selected by high
+ DAG.getConstant(0, DL, MVT::i32), // $src2_modifiers
+ Op.getOperand(4), // high
+ DAG.getConstant(0, DL, MVT::i1), // $clamp
+ DAG.getConstant(0, DL, MVT::i32) // $omod
+ };
+ return DAG.getNode(AMDGPUISD::INTERP_P1LV_F16, DL, MVT::f32, Ops);
+ } else {
+ // 32 bank LDS
+ SDValue Ops[] = {
+ Op.getOperand(1), // Src0
+ Op.getOperand(2), // Attrchan
+ Op.getOperand(3), // Attr
+ DAG.getConstant(0, DL, MVT::i32), // $src0_modifiers
+ Op.getOperand(4), // high
+ DAG.getConstant(0, DL, MVT::i1), // $clamp
+ DAG.getConstant(0, DL, MVT::i32), // $omod
+ Glue
+ };
+ return DAG.getNode(AMDGPUISD::INTERP_P1LL_F16, DL, MVT::f32, Ops);
+ }
+ }
+ case Intrinsic::amdgcn_interp_p2_f16: {
+ SDValue M0 = copyToM0(DAG, DAG.getEntryNode(), DL, Op.getOperand(6));
+ SDValue Glue = SDValue(M0.getNode(), 1);
+ SDValue Ops[] = {
+ Op.getOperand(2), // Src0
+ Op.getOperand(3), // Attrchan
+ Op.getOperand(4), // Attr
+ DAG.getConstant(0, DL, MVT::i32), // $src0_modifiers
+ Op.getOperand(1), // Src2
+ DAG.getConstant(0, DL, MVT::i32), // $src2_modifiers
+ Op.getOperand(5), // high
+ DAG.getConstant(0, DL, MVT::i1), // $clamp
+ Glue
+ };
+ return DAG.getNode(AMDGPUISD::INTERP_P2_F16, DL, MVT::f16, Ops);
+ }
case Intrinsic::amdgcn_sin:
return DAG.getNode(AMDGPUISD::SIN_HW, DL, VT, Op.getOperand(1));
diff --git a/llvm/lib/Target/AMDGPU/VOP3Instructions.td b/llvm/lib/Target/AMDGPU/VOP3Instructions.td
index da31f78..babd041 100644
--- a/llvm/lib/Target/AMDGPU/VOP3Instructions.td
+++ b/llvm/lib/Target/AMDGPU/VOP3Instructions.td
@@ -462,7 +462,14 @@
let FPDPRounding = 1 in {
def V_MAD_F16 : VOP3Inst <"v_mad_f16", VOP3_Profile<VOP_F16_F16_F16_F16>, fmad>;
let Uses = [M0, EXEC] in {
-def V_INTERP_P2_F16 : VOP3Interp <"v_interp_p2_f16", VOP3_INTERP16<[f16, f32, i32, f32]>>;
+def V_INTERP_P2_F16 : VOP3Interp <"v_interp_p2_f16", VOP3_INTERP16<[f16, f32, i32, f32]>,
+ [(set f16:$vdst, (AMDGPUinterp_p2_f16 f32:$src0, (i32 imm:$attrchan),
+ (i32 imm:$attr),
+ (i32 imm:$src0_modifiers),
+ (f32 VRegSrc_32:$src2),
+ (i32 imm:$src2_modifiers),
+ (i1 imm:$high),
+ (i1 imm:$clamp)))]>;
} // End Uses = [M0, EXEC]
} // End FPDPRounding = 1
} // End renamedInGFX9 = 1
@@ -477,8 +484,22 @@
} // End SubtargetPredicate = isGFX9
let Uses = [M0, EXEC], FPDPRounding = 1 in {
-def V_INTERP_P1LL_F16 : VOP3Interp <"v_interp_p1ll_f16", VOP3_INTERP16<[f32, f32, i32, untyped]>>;
-def V_INTERP_P1LV_F16 : VOP3Interp <"v_interp_p1lv_f16", VOP3_INTERP16<[f32, f32, i32, f16]>>;
+def V_INTERP_P1LL_F16 : VOP3Interp <"v_interp_p1ll_f16", VOP3_INTERP16<[f32, f32, i32, untyped]>,
+ [(set f32:$vdst, (AMDGPUinterp_p1ll_f16 f32:$src0, (i32 imm:$attrchan),
+ (i32 imm:$attr),
+ (i32 imm:$src0_modifiers),
+ (i1 imm:$high),
+ (i1 imm:$clamp),
+ (i32 imm:$omod)))]>;
+def V_INTERP_P1LV_F16 : VOP3Interp <"v_interp_p1lv_f16", VOP3_INTERP16<[f32, f32, i32, f16]>,
+ [(set f32:$vdst, (AMDGPUinterp_p1lv_f16 f32:$src0, (i32 imm:$attrchan),
+ (i32 imm:$attr),
+ (i32 imm:$src0_modifiers),
+ (f32 VRegSrc_32:$src2),
+ (i32 imm:$src2_modifiers),
+ (i1 imm:$high),
+ (i1 imm:$clamp),
+ (i32 imm:$omod)))]>;
} // End Uses = [M0, EXEC], FPDPRounding = 1
} // End SubtargetPredicate = Has16BitInsts, isCommutable = 1