[llvm] DAG: Handle vector legalization of minimumnum/maximumnum (PR #109779)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Sep 24 03:10:17 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-selectiondag
Author: Matt Arsenault (arsenm)
<details>
<summary>Changes</summary>
Follow the same patterns as the other min/max variants.
---
Patch is 110.01 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/109779.diff
5 Files Affected:
- (modified) llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp (+2)
- (modified) llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp (+3)
- (modified) llvm/lib/Target/AMDGPU/SIISelLowering.cpp (+4-1)
- (modified) llvm/test/CodeGen/AMDGPU/maximumnum.ll (+1265)
- (modified) llvm/test/CodeGen/AMDGPU/minimumnum.ll (+1265)
``````````diff
diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
index 1c466ed0b77997..0a22f06271984e 100644
--- a/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
@@ -4537,6 +4537,8 @@ void DAGTypeLegalizer::WidenVectorResult(SDNode *N, unsigned ResNo) {
case ISD::VP_FMINIMUM:
case ISD::FMAXIMUM:
case ISD::VP_FMAXIMUM:
+ case ISD::FMINIMUMNUM:
+ case ISD::FMAXIMUMNUM:
case ISD::SMIN: case ISD::VP_SMIN:
case ISD::SMAX: case ISD::VP_SMAX:
case ISD::UMIN: case ISD::VP_UMIN:
diff --git a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
index a2a232ed93b72f..f19975557a0a77 100644
--- a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -8606,6 +8606,9 @@ SDValue TargetLowering::expandFMINIMUMNUM_FMAXIMUMNUM(SDNode *Node,
return DAG.getNode(IEEE2008Op, DL, VT, LHS, RHS, Flags);
}
+ if (VT.isVector() && !isOperationLegalOrCustom(ISD::VSELECT, VT))
+ return DAG.UnrollVectorOp(Node);
+
// If only one operand is NaN, override it with another operand.
if (!Flags.hasNoNaNs() && !DAG.isKnownNeverNaN(LHS)) {
LHS = DAG.getSelectCC(DL, LHS, LHS, RHS, LHS, ISD::SETUO);
diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
index a9754ba357893f..749be5632733a1 100644
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -753,7 +753,8 @@ SITargetLowering::SITargetLowering(const TargetMachine &TM,
setOperationAction({ISD::FMAXNUM, ISD::FMINNUM}, MVT::f16, Custom);
setOperationAction({ISD::FMAXNUM_IEEE, ISD::FMINNUM_IEEE}, MVT::f16, Legal);
- setOperationAction({ISD::FMINNUM_IEEE, ISD::FMAXNUM_IEEE},
+ setOperationAction({ISD::FMINNUM_IEEE, ISD::FMAXNUM_IEEE, ISD::FMINIMUMNUM,
+ ISD::FMAXIMUMNUM},
{MVT::v4f16, MVT::v8f16, MVT::v16f16, MVT::v32f16},
Custom);
@@ -5842,6 +5843,8 @@ SDValue SITargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
case ISD::FMAXNUM_IEEE:
case ISD::FMINIMUM:
case ISD::FMAXIMUM:
+ case ISD::FMINIMUMNUM:
+ case ISD::FMAXIMUMNUM:
case ISD::UADDSAT:
case ISD::USUBSAT:
case ISD::SADDSAT:
diff --git a/llvm/test/CodeGen/AMDGPU/maximumnum.ll b/llvm/test/CodeGen/AMDGPU/maximumnum.ll
index 506f40516c9e6e..25a6c80b917946 100644
--- a/llvm/test/CodeGen/AMDGPU/maximumnum.ll
+++ b/llvm/test/CodeGen/AMDGPU/maximumnum.ll
@@ -1734,3 +1734,1268 @@ define double @v_maximumnum_f64_fneg(double %x, double %y) {
%result = call double @llvm.maximumnum.f64(double %fneg.x, double %fneg.y)
ret double %result
}
+
+define <2 x half> @v_maximumnum_v2f16(<2 x half> %x, <2 x half> %y) {
+; GFX8-LABEL: v_maximumnum_v2f16:
+; GFX8: ; %bb.0:
+; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX8-NEXT: v_max_f16_sdwa v2, v1, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_sdwa v3, v0, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_e32 v1, v1, v1
+; GFX8-NEXT: v_max_f16_e32 v0, v0, v0
+; GFX8-NEXT: v_max_f16_sdwa v2, v3, v2 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD
+; GFX8-NEXT: v_max_f16_e32 v0, v0, v1
+; GFX8-NEXT: v_or_b32_e32 v0, v0, v2
+; GFX8-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-LABEL: v_maximumnum_v2f16:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_pk_max_f16 v1, v1, v1
+; GFX9-NEXT: v_pk_max_f16 v0, v0, v0
+; GFX9-NEXT: v_pk_max_f16 v0, v0, v1
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: v_maximumnum_v2f16:
+; GFX10: ; %bb.0:
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: v_pk_max_f16 v1, v1, v1
+; GFX10-NEXT: v_pk_max_f16 v0, v0, v0
+; GFX10-NEXT: v_pk_max_f16 v0, v0, v1
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX11-LABEL: v_maximumnum_v2f16:
+; GFX11: ; %bb.0:
+; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX11-NEXT: v_pk_max_f16 v1, v1, v1
+; GFX11-NEXT: v_pk_max_f16 v0, v0, v0
+; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GFX11-NEXT: v_pk_max_f16 v0, v0, v1
+; GFX11-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX12-LABEL: v_maximumnum_v2f16:
+; GFX12: ; %bb.0:
+; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX12-NEXT: s_wait_expcnt 0x0
+; GFX12-NEXT: s_wait_samplecnt 0x0
+; GFX12-NEXT: s_wait_bvhcnt 0x0
+; GFX12-NEXT: s_wait_kmcnt 0x0
+; GFX12-NEXT: v_pk_max_num_f16 v1, v1, v1
+; GFX12-NEXT: v_pk_max_num_f16 v0, v0, v0
+; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GFX12-NEXT: v_pk_max_num_f16 v0, v0, v1
+; GFX12-NEXT: s_setpc_b64 s[30:31]
+ %result = call <2 x half> @llvm.maximumnum.v2f16(<2 x half> %x, <2 x half> %y)
+ ret <2 x half> %result
+}
+
+define <2 x half> @v_maximumnum_v2f16_nnan(<2 x half> %x, <2 x half> %y) {
+; GFX8-LABEL: v_maximumnum_v2f16_nnan:
+; GFX8: ; %bb.0:
+; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX8-NEXT: v_max_f16_sdwa v2, v0, v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_e32 v0, v0, v1
+; GFX8-NEXT: v_or_b32_e32 v0, v0, v2
+; GFX8-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-LABEL: v_maximumnum_v2f16_nnan:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_pk_max_f16 v0, v0, v1
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: v_maximumnum_v2f16_nnan:
+; GFX10: ; %bb.0:
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: v_pk_max_f16 v0, v0, v1
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX11-LABEL: v_maximumnum_v2f16_nnan:
+; GFX11: ; %bb.0:
+; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX11-NEXT: v_pk_max_f16 v0, v0, v1
+; GFX11-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX12-LABEL: v_maximumnum_v2f16_nnan:
+; GFX12: ; %bb.0:
+; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX12-NEXT: s_wait_expcnt 0x0
+; GFX12-NEXT: s_wait_samplecnt 0x0
+; GFX12-NEXT: s_wait_bvhcnt 0x0
+; GFX12-NEXT: s_wait_kmcnt 0x0
+; GFX12-NEXT: v_pk_max_num_f16 v0, v0, v1
+; GFX12-NEXT: s_setpc_b64 s[30:31]
+ %result = call nnan <2 x half> @llvm.maximumnum.v2f16(<2 x half> %x, <2 x half> %y)
+ ret <2 x half> %result
+}
+
+define <3 x half> @v_maximumnum_v3f16(<3 x half> %x, <3 x half> %y) {
+; GFX8-LABEL: v_maximumnum_v3f16:
+; GFX8: ; %bb.0:
+; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX8-NEXT: v_max_f16_sdwa v4, v2, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_sdwa v5, v0, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_e32 v2, v2, v2
+; GFX8-NEXT: v_max_f16_e32 v0, v0, v0
+; GFX8-NEXT: v_max_f16_sdwa v4, v5, v4 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD
+; GFX8-NEXT: v_max_f16_e32 v0, v0, v2
+; GFX8-NEXT: v_max_f16_e32 v2, v3, v3
+; GFX8-NEXT: v_max_f16_e32 v1, v1, v1
+; GFX8-NEXT: v_or_b32_e32 v0, v0, v4
+; GFX8-NEXT: v_max_f16_e32 v1, v1, v2
+; GFX8-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-LABEL: v_maximumnum_v3f16:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_pk_max_f16 v2, v2, v2
+; GFX9-NEXT: v_pk_max_f16 v0, v0, v0
+; GFX9-NEXT: v_pk_max_f16 v0, v0, v2
+; GFX9-NEXT: v_pk_max_f16 v2, v3, v3
+; GFX9-NEXT: v_pk_max_f16 v1, v1, v1
+; GFX9-NEXT: v_pk_max_f16 v1, v1, v2
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: v_maximumnum_v3f16:
+; GFX10: ; %bb.0:
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: v_pk_max_f16 v2, v2, v2
+; GFX10-NEXT: v_pk_max_f16 v0, v0, v0
+; GFX10-NEXT: v_pk_max_f16 v3, v3, v3
+; GFX10-NEXT: v_pk_max_f16 v1, v1, v1
+; GFX10-NEXT: v_pk_max_f16 v0, v0, v2
+; GFX10-NEXT: v_pk_max_f16 v1, v1, v3
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX11-LABEL: v_maximumnum_v3f16:
+; GFX11: ; %bb.0:
+; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX11-NEXT: v_pk_max_f16 v2, v2, v2
+; GFX11-NEXT: v_pk_max_f16 v0, v0, v0
+; GFX11-NEXT: v_pk_max_f16 v3, v3, v3
+; GFX11-NEXT: v_pk_max_f16 v1, v1, v1
+; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX11-NEXT: v_pk_max_f16 v0, v0, v2
+; GFX11-NEXT: v_pk_max_f16 v1, v1, v3
+; GFX11-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX12-LABEL: v_maximumnum_v3f16:
+; GFX12: ; %bb.0:
+; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX12-NEXT: s_wait_expcnt 0x0
+; GFX12-NEXT: s_wait_samplecnt 0x0
+; GFX12-NEXT: s_wait_bvhcnt 0x0
+; GFX12-NEXT: s_wait_kmcnt 0x0
+; GFX12-NEXT: v_pk_max_num_f16 v2, v2, v2
+; GFX12-NEXT: v_pk_max_num_f16 v0, v0, v0
+; GFX12-NEXT: v_pk_max_num_f16 v3, v3, v3
+; GFX12-NEXT: v_pk_max_num_f16 v1, v1, v1
+; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX12-NEXT: v_pk_max_num_f16 v0, v0, v2
+; GFX12-NEXT: v_pk_max_num_f16 v1, v1, v3
+; GFX12-NEXT: s_setpc_b64 s[30:31]
+ %result = call <3 x half> @llvm.maximumnum.v3f16(<3 x half> %x, <3 x half> %y)
+ ret <3 x half> %result
+}
+
+define <3 x half> @v_maximumnum_v3f16_nnan(<3 x half> %x, <3 x half> %y) {
+; GFX8-LABEL: v_maximumnum_v3f16_nnan:
+; GFX8: ; %bb.0:
+; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX8-NEXT: v_max_f16_sdwa v4, v0, v2 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_e32 v0, v0, v2
+; GFX8-NEXT: v_or_b32_e32 v0, v0, v4
+; GFX8-NEXT: v_max_f16_e32 v1, v1, v3
+; GFX8-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-LABEL: v_maximumnum_v3f16_nnan:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_pk_max_f16 v0, v0, v2
+; GFX9-NEXT: v_pk_max_f16 v1, v1, v3
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: v_maximumnum_v3f16_nnan:
+; GFX10: ; %bb.0:
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: v_pk_max_f16 v0, v0, v2
+; GFX10-NEXT: v_pk_max_f16 v1, v1, v3
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX11-LABEL: v_maximumnum_v3f16_nnan:
+; GFX11: ; %bb.0:
+; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX11-NEXT: v_pk_max_f16 v0, v0, v2
+; GFX11-NEXT: v_pk_max_f16 v1, v1, v3
+; GFX11-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX12-LABEL: v_maximumnum_v3f16_nnan:
+; GFX12: ; %bb.0:
+; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX12-NEXT: s_wait_expcnt 0x0
+; GFX12-NEXT: s_wait_samplecnt 0x0
+; GFX12-NEXT: s_wait_bvhcnt 0x0
+; GFX12-NEXT: s_wait_kmcnt 0x0
+; GFX12-NEXT: v_pk_max_num_f16 v0, v0, v2
+; GFX12-NEXT: v_pk_max_num_f16 v1, v1, v3
+; GFX12-NEXT: s_setpc_b64 s[30:31]
+ %result = call nnan <3 x half> @llvm.maximumnum.v3f16(<3 x half> %x, <3 x half> %y)
+ ret <3 x half> %result
+}
+
+define <4 x half> @v_maximumnum_v4f16(<4 x half> %x, <4 x half> %y) {
+; GFX8-LABEL: v_maximumnum_v4f16:
+; GFX8: ; %bb.0:
+; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX8-NEXT: v_max_f16_sdwa v4, v2, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_sdwa v5, v0, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_e32 v2, v2, v2
+; GFX8-NEXT: v_max_f16_e32 v0, v0, v0
+; GFX8-NEXT: v_max_f16_sdwa v4, v5, v4 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD
+; GFX8-NEXT: v_max_f16_e32 v0, v0, v2
+; GFX8-NEXT: v_or_b32_e32 v0, v0, v4
+; GFX8-NEXT: v_max_f16_sdwa v2, v3, v3 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_sdwa v4, v1, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_e32 v3, v3, v3
+; GFX8-NEXT: v_max_f16_e32 v1, v1, v1
+; GFX8-NEXT: v_max_f16_sdwa v2, v4, v2 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD
+; GFX8-NEXT: v_max_f16_e32 v1, v1, v3
+; GFX8-NEXT: v_or_b32_e32 v1, v1, v2
+; GFX8-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-LABEL: v_maximumnum_v4f16:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_pk_max_f16 v2, v2, v2
+; GFX9-NEXT: v_pk_max_f16 v0, v0, v0
+; GFX9-NEXT: v_pk_max_f16 v0, v0, v2
+; GFX9-NEXT: v_pk_max_f16 v2, v3, v3
+; GFX9-NEXT: v_pk_max_f16 v1, v1, v1
+; GFX9-NEXT: v_pk_max_f16 v1, v1, v2
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: v_maximumnum_v4f16:
+; GFX10: ; %bb.0:
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: v_pk_max_f16 v2, v2, v2
+; GFX10-NEXT: v_pk_max_f16 v0, v0, v0
+; GFX10-NEXT: v_pk_max_f16 v3, v3, v3
+; GFX10-NEXT: v_pk_max_f16 v1, v1, v1
+; GFX10-NEXT: v_pk_max_f16 v0, v0, v2
+; GFX10-NEXT: v_pk_max_f16 v1, v1, v3
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX11-LABEL: v_maximumnum_v4f16:
+; GFX11: ; %bb.0:
+; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX11-NEXT: v_pk_max_f16 v2, v2, v2
+; GFX11-NEXT: v_pk_max_f16 v0, v0, v0
+; GFX11-NEXT: v_pk_max_f16 v3, v3, v3
+; GFX11-NEXT: v_pk_max_f16 v1, v1, v1
+; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX11-NEXT: v_pk_max_f16 v0, v0, v2
+; GFX11-NEXT: v_pk_max_f16 v1, v1, v3
+; GFX11-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX12-LABEL: v_maximumnum_v4f16:
+; GFX12: ; %bb.0:
+; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX12-NEXT: s_wait_expcnt 0x0
+; GFX12-NEXT: s_wait_samplecnt 0x0
+; GFX12-NEXT: s_wait_bvhcnt 0x0
+; GFX12-NEXT: s_wait_kmcnt 0x0
+; GFX12-NEXT: v_pk_max_num_f16 v2, v2, v2
+; GFX12-NEXT: v_pk_max_num_f16 v0, v0, v0
+; GFX12-NEXT: v_pk_max_num_f16 v3, v3, v3
+; GFX12-NEXT: v_pk_max_num_f16 v1, v1, v1
+; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX12-NEXT: v_pk_max_num_f16 v0, v0, v2
+; GFX12-NEXT: v_pk_max_num_f16 v1, v1, v3
+; GFX12-NEXT: s_setpc_b64 s[30:31]
+ %result = call <4 x half> @llvm.maximumnum.v4f16(<4 x half> %x, <4 x half> %y)
+ ret <4 x half> %result
+}
+
+define <4 x half> @v_maximumnum_v4f16_nnan(<4 x half> %x, <4 x half> %y) {
+; GFX8-LABEL: v_maximumnum_v4f16_nnan:
+; GFX8: ; %bb.0:
+; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX8-NEXT: v_max_f16_sdwa v4, v0, v2 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_e32 v0, v0, v2
+; GFX8-NEXT: v_max_f16_sdwa v2, v1, v3 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_e32 v1, v1, v3
+; GFX8-NEXT: v_or_b32_e32 v0, v0, v4
+; GFX8-NEXT: v_or_b32_e32 v1, v1, v2
+; GFX8-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-LABEL: v_maximumnum_v4f16_nnan:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_pk_max_f16 v0, v0, v2
+; GFX9-NEXT: v_pk_max_f16 v1, v1, v3
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: v_maximumnum_v4f16_nnan:
+; GFX10: ; %bb.0:
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: v_pk_max_f16 v0, v0, v2
+; GFX10-NEXT: v_pk_max_f16 v1, v1, v3
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX11-LABEL: v_maximumnum_v4f16_nnan:
+; GFX11: ; %bb.0:
+; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX11-NEXT: v_pk_max_f16 v0, v0, v2
+; GFX11-NEXT: v_pk_max_f16 v1, v1, v3
+; GFX11-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX12-LABEL: v_maximumnum_v4f16_nnan:
+; GFX12: ; %bb.0:
+; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX12-NEXT: s_wait_expcnt 0x0
+; GFX12-NEXT: s_wait_samplecnt 0x0
+; GFX12-NEXT: s_wait_bvhcnt 0x0
+; GFX12-NEXT: s_wait_kmcnt 0x0
+; GFX12-NEXT: v_pk_max_num_f16 v0, v0, v2
+; GFX12-NEXT: v_pk_max_num_f16 v1, v1, v3
+; GFX12-NEXT: s_setpc_b64 s[30:31]
+ %result = call nnan <4 x half> @llvm.maximumnum.v4f16(<4 x half> %x, <4 x half> %y)
+ ret <4 x half> %result
+}
+
+define <6 x half> @v_maximumnum_v6f16(<6 x half> %x, <6 x half> %y) {
+; GFX8-LABEL: v_maximumnum_v6f16:
+; GFX8: ; %bb.0:
+; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX8-NEXT: v_max_f16_sdwa v6, v3, v3 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_sdwa v7, v0, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_e32 v3, v3, v3
+; GFX8-NEXT: v_max_f16_e32 v0, v0, v0
+; GFX8-NEXT: v_max_f16_sdwa v6, v7, v6 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD
+; GFX8-NEXT: v_max_f16_e32 v0, v0, v3
+; GFX8-NEXT: v_or_b32_e32 v0, v0, v6
+; GFX8-NEXT: v_max_f16_sdwa v3, v4, v4 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_sdwa v6, v1, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_e32 v4, v4, v4
+; GFX8-NEXT: v_max_f16_e32 v1, v1, v1
+; GFX8-NEXT: v_max_f16_sdwa v3, v6, v3 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD
+; GFX8-NEXT: v_max_f16_e32 v1, v1, v4
+; GFX8-NEXT: v_or_b32_e32 v1, v1, v3
+; GFX8-NEXT: v_max_f16_sdwa v3, v5, v5 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_sdwa v4, v2, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX8-NEXT: v_max_f16_sdwa v3, v4, v3 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD
+; GFX8-NEXT: v_max_f16_e32 v4, v5, v5
+; GFX8-NEXT: v_max_f16_e32 v2, v2, v2
+; GFX8-NEXT: v_max_f16_e32 v2, v2, v4
+; GFX8-NEXT: v_or_b32_e32 v2, v2, v3
+; GFX8-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-LABEL: v_maximumnum_v6f16:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_pk_max_f16 v3, v3, v3
+; GFX9-NEXT: v_pk_max_f16 v0, v0, v0
+; GFX9-NEXT: v_pk_max_f16 v0, v0, v3
+; GFX9-NEXT: v_pk_max_f16 v3, v4, v4
+; GFX9-NEXT: v_pk_max_f16 v1, v1, v1
+; GFX9-NEXT: v_pk_max_f16 v1, v1, v3
+; GFX9-NEXT: v_pk_max_f16 v3, v5, v5
+; GFX9-NEXT: v_pk_max_f16 v2, v2, v2
+; GFX9-NEXT: v_pk_max_f16 v2, v2, v3
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: v_maximumnum_v6f16:
+; GFX10: ; %bb.0:
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: v_pk_max_f16 v3, v3, v3
+; GFX10-NEXT: v_pk_max_f16 v0, v0, v0
+; GFX10-NEXT: v_pk_max_f16 v4, v4, v4
+; GFX10-NEXT: v_pk_max_f16 v1, v1, v1
+; GFX10-NEXT: v_pk_max_f16 v5, v5, v5
+; GFX10-NEXT: v_pk_max_f16 v2, v2, v2
+; GFX10-NEXT: v_pk_max_f16 v0, v0, v3
+; GFX10-NEXT: v_pk_max_f16 v1, v1, v4
+; GFX10-NEXT: v_pk_max_f16 v2, v2, v5
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX11-LABEL: v_maximumnum_v6f16:
+; GFX11: ; %bb.0:
+; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX11-NEXT: v_pk_max_f16 v3, v3, v3
+; GFX11-NEXT: v_pk_max_f16 v0, v0, v0
+; GFX11-NEXT: v_pk_max_f16 v4, v4, v4
+; GFX11-NEXT: v_pk_max_f16 v1, v1, v1
+; GFX11-NEXT: v_pk_max_f16 v5, v5, v5
+; GFX11-NEXT: v_pk_max_f16 v2, v2, v2
+; GFX11-NEXT: v_pk_max_f16 v0, v0, v3
+; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_4) | instskip(NEXT) | instid1(VALU_DEP_3)
+; GFX11-NEXT: v_pk_max_f16 v1, v1, v4
+; GFX11-NEXT: v_pk_max_f16 v2, v2, v5
+; GFX11-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX12-LABEL: v_maximumnum_v6f16:
+; GFX12: ; %bb.0:
+; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX12-NEXT: s_wait_expcnt 0x0
+; GFX12-NEXT: s_wait_samplecnt 0x0
+; GFX12-NEXT: s_wait_bvhcnt 0x0
+; GFX12-NEXT: s_wait_kmcnt 0x0
+; GFX12-NEXT: v_pk_max_num_f16 v3, v3, v3
+; GFX12-NEXT: v_pk_max_num_f16 v0, v0, v0
+; GFX12-NEXT: v_pk_max_num_f16 v4, v4, v4
+; GFX12-NEXT: v_pk_max_num_f16 v1, v1, v1
+; GFX12-NEXT: v_pk_max_num_f16 v5, v5, v5
+; GFX12-NEXT: v_pk_max_num_f16 v2, v2, v2
+; GFX12-NEXT: v_pk_max_num_f16 v0, v0, v3
+; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_4) | instskip(NEXT) | instid1(...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/109779
More information about the llvm-commits
mailing list