[llvm] [GlobalISel][TableGen] Take first result for multi-output instructions (PR #81130)
Björn Pettersson via llvm-commits
llvm-commits at lists.llvm.org
Thu Feb 15 02:44:08 PST 2024
https://github.com/bjope updated https://github.com/llvm/llvm-project/pull/81130
>From 7d54f3d0a8b45e30218c23512f7bd7e2a9edfb63 Mon Sep 17 00:00:00 2001
From: Bjorn Pettersson <bjorn.a.pettersson at ericsson.com>
Date: Fri, 3 Nov 2023 12:44:38 +0100
Subject: [PATCH 1/3] [GlobalISel][TableGen] Take first result for multi-output
instructions
Previously, tblgen would reject patterns where one of its nested
instructions produced more than one result. These arise when the
instruction definition contains 'outs' as well as 'Defs'. This patch
fixes that by always taking the first result, which is how these
situations are handled in SelectionIDAG.
Differential Revision: https://reviews.llvm.org/D86617
---
.../AMDGPU/GlobalISel/inst-select-fabs.mir | 72 ++++++++++---------
.../AMDGPU/GlobalISel/inst-select-fneg.mir | 72 ++++++++++---------
.../AMDGPU/GlobalISel/inst-select-sext.mir | 16 +++--
.../AMDGPU/GlobalISel/inst-select-zext.mir | 10 +--
...lobalISelEmitter-multiple-output-reject.td | 14 ++++
.../GlobalISelEmitter-multiple-output.td | 33 +++++++++
llvm/utils/TableGen/GlobalISelEmitter.cpp | 27 ++++---
7 files changed, 162 insertions(+), 82 deletions(-)
create mode 100644 llvm/test/TableGen/GlobalISelEmitter-multiple-output-reject.td
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-fabs.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-fabs.mir
index aca51802511b92..ca75fd207607a5 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-fabs.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-fabs.mir
@@ -426,44 +426,48 @@ body: |
; SI: liveins: $sgpr0_sgpr1
; SI-NEXT: {{ $}}
; SI-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
- ; SI-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub0
- ; SI-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub1
; SI-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 2147483647
- ; SI-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY2]], [[S_MOV_B32_]], implicit-def dead $scc
- ; SI-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[S_AND_B32_]], %subreg.sub1
+ ; SI-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[COPY]].sub1
+ ; SI-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def dead $scc
+ ; SI-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY [[S_AND_B32_]]
+ ; SI-NEXT: [[COPY3:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY [[COPY]].sub0
+ ; SI-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY3]], %subreg.sub0, [[COPY2]], %subreg.sub1
; SI-NEXT: S_ENDPGM 0, implicit [[REG_SEQUENCE]]
;
; VI-LABEL: name: fabs_s64_ss
; VI: liveins: $sgpr0_sgpr1
; VI-NEXT: {{ $}}
; VI-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
- ; VI-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub0
- ; VI-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub1
; VI-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 2147483647
- ; VI-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY2]], [[S_MOV_B32_]], implicit-def dead $scc
- ; VI-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[S_AND_B32_]], %subreg.sub1
+ ; VI-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[COPY]].sub1
+ ; VI-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def dead $scc
+ ; VI-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY [[S_AND_B32_]]
+ ; VI-NEXT: [[COPY3:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY [[COPY]].sub0
+ ; VI-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY3]], %subreg.sub0, [[COPY2]], %subreg.sub1
; VI-NEXT: S_ENDPGM 0, implicit [[REG_SEQUENCE]]
;
; GFX9-LABEL: name: fabs_s64_ss
; GFX9: liveins: $sgpr0_sgpr1
; GFX9-NEXT: {{ $}}
; GFX9-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
- ; GFX9-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub0
- ; GFX9-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub1
; GFX9-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 2147483647
- ; GFX9-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY2]], [[S_MOV_B32_]], implicit-def dead $scc
- ; GFX9-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[S_AND_B32_]], %subreg.sub1
+ ; GFX9-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[COPY]].sub1
+ ; GFX9-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def dead $scc
+ ; GFX9-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY [[S_AND_B32_]]
+ ; GFX9-NEXT: [[COPY3:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY [[COPY]].sub0
+ ; GFX9-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY3]], %subreg.sub0, [[COPY2]], %subreg.sub1
; GFX9-NEXT: S_ENDPGM 0, implicit [[REG_SEQUENCE]]
;
; GFX10-LABEL: name: fabs_s64_ss
; GFX10: liveins: $sgpr0_sgpr1
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
- ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub0
- ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub1
; GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 2147483647
- ; GFX10-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY2]], [[S_MOV_B32_]], implicit-def dead $scc
- ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[S_AND_B32_]], %subreg.sub1
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[COPY]].sub1
+ ; GFX10-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def dead $scc
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY [[S_AND_B32_]]
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY [[COPY]].sub0
+ ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY3]], %subreg.sub0, [[COPY2]], %subreg.sub1
; GFX10-NEXT: S_ENDPGM 0, implicit [[REG_SEQUENCE]]
%0:sgpr(s64) = COPY $sgpr0_sgpr1
%1:sgpr(s64) = G_FABS %0
@@ -639,44 +643,48 @@ body: |
; SI: liveins: $sgpr0_sgpr1
; SI-NEXT: {{ $}}
; SI-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
- ; SI-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY [[DEF]].sub0
- ; SI-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[DEF]].sub1
; SI-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 2147483647
- ; SI-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def dead $scc
- ; SI-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[S_AND_B32_]], %subreg.sub1
+ ; SI-NEXT: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY [[DEF]].sub1
+ ; SI-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY]], [[S_MOV_B32_]], implicit-def dead $scc
+ ; SI-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[S_AND_B32_]]
+ ; SI-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY [[DEF]].sub0
+ ; SI-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY2]], %subreg.sub0, [[COPY1]], %subreg.sub1
; SI-NEXT: S_ENDPGM 0, implicit [[REG_SEQUENCE]]
;
; VI-LABEL: name: fabs_s64_ss_no_src_constraint
; VI: liveins: $sgpr0_sgpr1
; VI-NEXT: {{ $}}
; VI-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
- ; VI-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY [[DEF]].sub0
- ; VI-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[DEF]].sub1
; VI-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 2147483647
- ; VI-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def dead $scc
- ; VI-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[S_AND_B32_]], %subreg.sub1
+ ; VI-NEXT: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY [[DEF]].sub1
+ ; VI-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY]], [[S_MOV_B32_]], implicit-def dead $scc
+ ; VI-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[S_AND_B32_]]
+ ; VI-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY [[DEF]].sub0
+ ; VI-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY2]], %subreg.sub0, [[COPY1]], %subreg.sub1
; VI-NEXT: S_ENDPGM 0, implicit [[REG_SEQUENCE]]
;
; GFX9-LABEL: name: fabs_s64_ss_no_src_constraint
; GFX9: liveins: $sgpr0_sgpr1
; GFX9-NEXT: {{ $}}
; GFX9-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
- ; GFX9-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY [[DEF]].sub0
- ; GFX9-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[DEF]].sub1
; GFX9-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 2147483647
- ; GFX9-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def dead $scc
- ; GFX9-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[S_AND_B32_]], %subreg.sub1
+ ; GFX9-NEXT: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY [[DEF]].sub1
+ ; GFX9-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY]], [[S_MOV_B32_]], implicit-def dead $scc
+ ; GFX9-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[S_AND_B32_]]
+ ; GFX9-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY [[DEF]].sub0
+ ; GFX9-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY2]], %subreg.sub0, [[COPY1]], %subreg.sub1
; GFX9-NEXT: S_ENDPGM 0, implicit [[REG_SEQUENCE]]
;
; GFX10-LABEL: name: fabs_s64_ss_no_src_constraint
; GFX10: liveins: $sgpr0_sgpr1
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
- ; GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY [[DEF]].sub0
- ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[DEF]].sub1
; GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 2147483647
- ; GFX10-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def dead $scc
- ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[S_AND_B32_]], %subreg.sub1
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY [[DEF]].sub1
+ ; GFX10-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY]], [[S_MOV_B32_]], implicit-def dead $scc
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[S_AND_B32_]]
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY [[DEF]].sub0
+ ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY2]], %subreg.sub0, [[COPY1]], %subreg.sub1
; GFX10-NEXT: S_ENDPGM 0, implicit [[REG_SEQUENCE]]
%0:sgpr(s64) = IMPLICIT_DEF
%1:sgpr(s64) = G_FABS %0:sgpr(s64)
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-fneg.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-fneg.mir
index e7a52873225ead..acda00231ec612 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-fneg.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-fneg.mir
@@ -426,44 +426,48 @@ body: |
; SI: liveins: $sgpr0_sgpr1
; SI-NEXT: {{ $}}
; SI-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
- ; SI-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub0
- ; SI-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub1
; SI-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 2147483648
- ; SI-NEXT: [[S_XOR_B32_:%[0-9]+]]:sreg_32 = S_XOR_B32 [[COPY2]], [[S_MOV_B32_]], implicit-def dead $scc
- ; SI-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[S_XOR_B32_]], %subreg.sub1
+ ; SI-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[COPY]].sub1
+ ; SI-NEXT: [[S_XOR_B32_:%[0-9]+]]:sreg_32 = S_XOR_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def dead $scc
+ ; SI-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY [[S_XOR_B32_]]
+ ; SI-NEXT: [[COPY3:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY [[COPY]].sub0
+ ; SI-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY3]], %subreg.sub0, [[COPY2]], %subreg.sub1
; SI-NEXT: S_ENDPGM 0, implicit [[REG_SEQUENCE]]
;
; VI-LABEL: name: fneg_s64_ss
; VI: liveins: $sgpr0_sgpr1
; VI-NEXT: {{ $}}
; VI-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
- ; VI-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub0
- ; VI-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub1
; VI-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 2147483648
- ; VI-NEXT: [[S_XOR_B32_:%[0-9]+]]:sreg_32 = S_XOR_B32 [[COPY2]], [[S_MOV_B32_]], implicit-def dead $scc
- ; VI-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[S_XOR_B32_]], %subreg.sub1
+ ; VI-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[COPY]].sub1
+ ; VI-NEXT: [[S_XOR_B32_:%[0-9]+]]:sreg_32 = S_XOR_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def dead $scc
+ ; VI-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY [[S_XOR_B32_]]
+ ; VI-NEXT: [[COPY3:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY [[COPY]].sub0
+ ; VI-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY3]], %subreg.sub0, [[COPY2]], %subreg.sub1
; VI-NEXT: S_ENDPGM 0, implicit [[REG_SEQUENCE]]
;
; GFX9-LABEL: name: fneg_s64_ss
; GFX9: liveins: $sgpr0_sgpr1
; GFX9-NEXT: {{ $}}
; GFX9-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
- ; GFX9-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub0
- ; GFX9-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub1
; GFX9-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 2147483648
- ; GFX9-NEXT: [[S_XOR_B32_:%[0-9]+]]:sreg_32 = S_XOR_B32 [[COPY2]], [[S_MOV_B32_]], implicit-def dead $scc
- ; GFX9-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[S_XOR_B32_]], %subreg.sub1
+ ; GFX9-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[COPY]].sub1
+ ; GFX9-NEXT: [[S_XOR_B32_:%[0-9]+]]:sreg_32 = S_XOR_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def dead $scc
+ ; GFX9-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY [[S_XOR_B32_]]
+ ; GFX9-NEXT: [[COPY3:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY [[COPY]].sub0
+ ; GFX9-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY3]], %subreg.sub0, [[COPY2]], %subreg.sub1
; GFX9-NEXT: S_ENDPGM 0, implicit [[REG_SEQUENCE]]
;
; GFX10-LABEL: name: fneg_s64_ss
; GFX10: liveins: $sgpr0_sgpr1
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
- ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub0
- ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub1
; GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 2147483648
- ; GFX10-NEXT: [[S_XOR_B32_:%[0-9]+]]:sreg_32 = S_XOR_B32 [[COPY2]], [[S_MOV_B32_]], implicit-def dead $scc
- ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[S_XOR_B32_]], %subreg.sub1
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[COPY]].sub1
+ ; GFX10-NEXT: [[S_XOR_B32_:%[0-9]+]]:sreg_32 = S_XOR_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def dead $scc
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY [[S_XOR_B32_]]
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY [[COPY]].sub0
+ ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY3]], %subreg.sub0, [[COPY2]], %subreg.sub1
; GFX10-NEXT: S_ENDPGM 0, implicit [[REG_SEQUENCE]]
%0:sgpr(s64) = COPY $sgpr0_sgpr1
%1:sgpr(s64) = G_FNEG %0
@@ -1023,44 +1027,48 @@ body: |
; SI: liveins: $sgpr0_sgpr1
; SI-NEXT: {{ $}}
; SI-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
- ; SI-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub0
- ; SI-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub1
; SI-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 2147483648
- ; SI-NEXT: [[S_OR_B32_:%[0-9]+]]:sreg_32 = S_OR_B32 [[COPY2]], [[S_MOV_B32_]], implicit-def dead $scc
- ; SI-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[S_OR_B32_]], %subreg.sub1
+ ; SI-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[COPY]].sub1
+ ; SI-NEXT: [[S_OR_B32_:%[0-9]+]]:sreg_32 = S_OR_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def dead $scc
+ ; SI-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY [[S_OR_B32_]]
+ ; SI-NEXT: [[COPY3:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY [[COPY]].sub0
+ ; SI-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY3]], %subreg.sub0, [[COPY2]], %subreg.sub1
; SI-NEXT: S_ENDPGM 0, implicit [[REG_SEQUENCE]]
;
; VI-LABEL: name: fneg_fabs_s64_ss
; VI: liveins: $sgpr0_sgpr1
; VI-NEXT: {{ $}}
; VI-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
- ; VI-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub0
- ; VI-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub1
; VI-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 2147483648
- ; VI-NEXT: [[S_OR_B32_:%[0-9]+]]:sreg_32 = S_OR_B32 [[COPY2]], [[S_MOV_B32_]], implicit-def dead $scc
- ; VI-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[S_OR_B32_]], %subreg.sub1
+ ; VI-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[COPY]].sub1
+ ; VI-NEXT: [[S_OR_B32_:%[0-9]+]]:sreg_32 = S_OR_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def dead $scc
+ ; VI-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY [[S_OR_B32_]]
+ ; VI-NEXT: [[COPY3:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY [[COPY]].sub0
+ ; VI-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY3]], %subreg.sub0, [[COPY2]], %subreg.sub1
; VI-NEXT: S_ENDPGM 0, implicit [[REG_SEQUENCE]]
;
; GFX9-LABEL: name: fneg_fabs_s64_ss
; GFX9: liveins: $sgpr0_sgpr1
; GFX9-NEXT: {{ $}}
; GFX9-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
- ; GFX9-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub0
- ; GFX9-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub1
; GFX9-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 2147483648
- ; GFX9-NEXT: [[S_OR_B32_:%[0-9]+]]:sreg_32 = S_OR_B32 [[COPY2]], [[S_MOV_B32_]], implicit-def dead $scc
- ; GFX9-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[S_OR_B32_]], %subreg.sub1
+ ; GFX9-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[COPY]].sub1
+ ; GFX9-NEXT: [[S_OR_B32_:%[0-9]+]]:sreg_32 = S_OR_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def dead $scc
+ ; GFX9-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY [[S_OR_B32_]]
+ ; GFX9-NEXT: [[COPY3:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY [[COPY]].sub0
+ ; GFX9-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY3]], %subreg.sub0, [[COPY2]], %subreg.sub1
; GFX9-NEXT: S_ENDPGM 0, implicit [[REG_SEQUENCE]]
;
; GFX10-LABEL: name: fneg_fabs_s64_ss
; GFX10: liveins: $sgpr0_sgpr1
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
- ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub0
- ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub1
; GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 2147483648
- ; GFX10-NEXT: [[S_OR_B32_:%[0-9]+]]:sreg_32 = S_OR_B32 [[COPY2]], [[S_MOV_B32_]], implicit-def dead $scc
- ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[S_OR_B32_]], %subreg.sub1
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[COPY]].sub1
+ ; GFX10-NEXT: [[S_OR_B32_:%[0-9]+]]:sreg_32 = S_OR_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def dead $scc
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY [[S_OR_B32_]]
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY [[COPY]].sub0
+ ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY3]], %subreg.sub0, [[COPY2]], %subreg.sub1
; GFX10-NEXT: S_ENDPGM 0, implicit [[REG_SEQUENCE]]
%0:sgpr(s64) = COPY $sgpr0_sgpr1
%1:sgpr(s64) = G_FABS %0
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-sext.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-sext.mir
index 4a91afc88fa599..150d9b72afcee5 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-sext.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-sext.mir
@@ -104,10 +104,13 @@ body: |
; GCN: liveins: $sgpr0
; GCN-NEXT: {{ $}}
; GCN-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
- ; GCN-NEXT: [[DEF:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
- ; GCN-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[DEF]], %subreg.sub1
- ; GCN-NEXT: [[S_BFE_I64_:%[0-9]+]]:sreg_64 = S_BFE_I64 [[REG_SEQUENCE]], 1048576, implicit-def $scc
- ; GCN-NEXT: $sgpr0_sgpr1 = COPY [[S_BFE_I64_]]
+ ; GCN-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 31
+ ; GCN-NEXT: [[S_SEXT_I32_I16_:%[0-9]+]]:sreg_32 = S_SEXT_I32_I16 [[COPY]]
+ ; GCN-NEXT: [[S_ASHR_I32_:%[0-9]+]]:sreg_32 = S_ASHR_I32 [[S_SEXT_I32_I16_]], [[S_MOV_B32_]], implicit-def dead $scc
+ ; GCN-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[S_ASHR_I32_]]
+ ; GCN-NEXT: [[S_SEXT_I32_I16_1:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = S_SEXT_I32_I16 [[COPY]]
+ ; GCN-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[S_SEXT_I32_I16_1]], %subreg.sub0, [[COPY1]], %subreg.sub1
+ ; GCN-NEXT: $sgpr0_sgpr1 = COPY [[REG_SEQUENCE]]
%0:sgpr(s32) = COPY $sgpr0
%1:sgpr(s16) = G_TRUNC %0
%2:sgpr(s64) = G_SEXT %1
@@ -127,9 +130,10 @@ body: |
; GCN-LABEL: name: sext_sgpr_s32_to_sgpr_s64
; GCN: liveins: $sgpr0
; GCN-NEXT: {{ $}}
- ; GCN-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
+ ; GCN-NEXT: [[COPY:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY $sgpr0
; GCN-NEXT: [[S_ASHR_I32_:%[0-9]+]]:sreg_32 = S_ASHR_I32 [[COPY]], 31, implicit-def dead $scc
- ; GCN-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[S_ASHR_I32_]], %subreg.sub1
+ ; GCN-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY [[S_ASHR_I32_]]
+ ; GCN-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
; GCN-NEXT: $sgpr0_sgpr1 = COPY [[REG_SEQUENCE]]
%0:sgpr(s32) = COPY $sgpr0
%1:sgpr(s64) = G_SEXT %0
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-zext.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-zext.mir
index 577a2e7d7d3660..1589172a028265 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-zext.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-zext.mir
@@ -104,10 +104,12 @@ body: |
; GCN: liveins: $sgpr0
; GCN-NEXT: {{ $}}
; GCN-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
- ; GCN-NEXT: [[DEF:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
- ; GCN-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[DEF]], %subreg.sub1
- ; GCN-NEXT: [[S_BFE_U64_:%[0-9]+]]:sreg_64 = S_BFE_U64 [[REG_SEQUENCE]], 1048576, implicit-def $scc
- ; GCN-NEXT: $sgpr0_sgpr1 = COPY [[S_BFE_U64_]]
+ ; GCN-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 0
+ ; GCN-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 65535
+ ; GCN-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY]], [[S_MOV_B32_1]], implicit-def dead $scc
+ ; GCN-NEXT: [[COPY1:%[0-9]+]]:sreg_32_xexec_hi_and_sreg_32_xm0 = COPY [[S_AND_B32_]]
+ ; GCN-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[S_MOV_B32_]], %subreg.sub1
+ ; GCN-NEXT: $sgpr0_sgpr1 = COPY [[REG_SEQUENCE]]
%0:sgpr(s32) = COPY $sgpr0
%1:sgpr(s16) = G_TRUNC %0
%2:sgpr(s64) = G_ZEXT %1
diff --git a/llvm/test/TableGen/GlobalISelEmitter-multiple-output-reject.td b/llvm/test/TableGen/GlobalISelEmitter-multiple-output-reject.td
new file mode 100644
index 00000000000000..b93aa20d9da23b
--- /dev/null
+++ b/llvm/test/TableGen/GlobalISelEmitter-multiple-output-reject.td
@@ -0,0 +1,14 @@
+// RUN: llvm-tblgen -gen-global-isel -optimize-match-table=false -warn-on-skipped-patterns -I %p/../../include -I %p/Common %s -o - < %s 2>&1 | FileCheck %s
+
+include "llvm/Target/Target.td"
+include "GlobalISelEmitterCommon.td"
+
+// Test when the inner instruction in the output pattern has two outs
+
+def TwoOutsInstr : I<(outs GPR32:$out1, GPR32:$out2), (ins GPR32:$src), []>;
+def OtherInstr : I<(outs GPR32:$dst), (ins GPR32:$src), []>;
+
+def : Pat<(i32 (add i32:$src, i32:$src)),
+ (OtherInstr (TwoOutsInstr GPR32:$src))>;
+
+// CHECK: warning: Skipped pattern: Dst pattern child is not having single result
diff --git a/llvm/test/TableGen/GlobalISelEmitter-multiple-output.td b/llvm/test/TableGen/GlobalISelEmitter-multiple-output.td
index f75988dadc73b1..40d79b95928ac9 100644
--- a/llvm/test/TableGen/GlobalISelEmitter-multiple-output.td
+++ b/llvm/test/TableGen/GlobalISelEmitter-multiple-output.td
@@ -10,6 +10,7 @@ include "GlobalISelEmitterCommon.td"
// Verify that patterns with multiple outputs are translated
+//-----------------------------------------------------------------------------
// Test where only the opcode is mutated during ISel
let Constraints = "$ptr_out = $addr" in
@@ -46,6 +47,7 @@ def : Pat<(loadpost (p0 GPR32:$addr), (i32 GPR32:$off)),
// CHECK-NEXT: GIR_MutateOpcode, /*InsnID*/0, /*RecycleInsnID*/0, /*Opcode*/GIMT_Encode2(MyTarget::LDPost),
// CHECK-NEXT: GIR_ConstrainSelectedInstOperands, /*InsnID*/0,
+//-----------------------------------------------------------------------------
// Test where a whole new MIR instruction is created during ISel
def TWO_INS : I<(outs GPR32:$out1, GPR32:$out2), (ins GPR32:$in1, GPR32:$in2), []>;
@@ -84,3 +86,34 @@ def : Pat<(two_in GPR32:$i1, GPR32:$i2), (TWO_INS GPR32:$i2, GPR32:$i1)>;
// CHECK-NEXT: GIR_Copy, /*NewInsnID*/0, /*OldInsnID*/0, /*OpIdx*/2, // i1
// CHECK-NEXT: GIR_ConstrainSelectedInstOperands, /*InsnID*/0,
// CHECK-NEXT: GIR_EraseFromParent, /*InsnID*/0,
+
+//-----------------------------------------------------------------------------
+// Test where implicit defs are added using Defs.
+
+let Defs = [R0] in
+def ImplicitDefInstr : I<(outs GPR32:$dst), (ins GPR32:$src), []>;
+def OtherInstr : I<(outs GPR32:$dst), (ins GPR32:$src), []>;
+
+def : Pat<(i32 (add i32:$src, i32:$src)),
+ (OtherInstr (ImplicitDefInstr GPR32:$src))>;
+
+// CHECK: GIM_CheckOpcode, /*MI*/0, TargetOpcode::G_ADD,
+// CHECK-NEXT: // MIs[0] dst
+// CHECK-NEXT: GIM_CheckType, /*MI*/0, /*Op*/0, /*Type*/GILLT_s32,
+// CHECK-NEXT: GIM_CheckRegBankForClass, /*MI*/0, /*Op*/0, /*RC*/MyTarget::GPR32RegClassID,
+// CHECK-NEXT: // MIs[0] src
+// CHECK-NEXT: GIM_CheckType, /*MI*/0, /*Op*/1, /*Type*/GILLT_s32,
+// CHECK-NEXT: // MIs[0] src
+// CHECK-NEXT: GIM_CheckIsSameOperand, /*MI*/0, /*OpIdx*/2, /*OtherMI*/0, /*OtherOpIdx*/1,
+// CHECK-NEXT: // (add:{ *:[i32] } i32:{ *:[i32] }:$src, i32:{ *:[i32] }:$src) => (OtherInstr:{ *:[i32] } (ImplicitDefInstr:{ *:[i32] }:{ *:[i32] } GPR32:{ *:[i32] }:$src))
+// CHECK-NEXT: GIR_MakeTempReg, /*TempRegID*/0, /*TypeID*/GILLT_s32,
+// CHECK-NEXT: GIR_BuildMI, /*InsnID*/1, /*Opcode*/MyTarget::ImplicitDefInstr,
+// CHECK-NEXT: GIR_AddTempRegister, /*InsnID*/1, /*TempRegID*/0, /*TempRegFlags*/RegState::Define,
+// CHECK-NEXT: GIR_Copy, /*NewInsnID*/1, /*OldInsnID*/0, /*OpIdx*/1, // src
+// CHECK-NEXT: GIR_SetImplicitDefDead, /*InsnID*/1, /*OpIdx for MyTarget::R0*/0,
+// CHECK-NEXT: GIR_ConstrainSelectedInstOperands, /*InsnID*/1,
+// CHECK-NEXT: GIR_BuildMI, /*InsnID*/0, /*Opcode*/MyTarget::OtherInstr,
+// CHECK-NEXT: GIR_Copy, /*NewInsnID*/0, /*OldInsnID*/0, /*OpIdx*/0, // dst
+// CHECK-NEXT: GIR_AddTempRegister, /*InsnID*/0, /*TempRegID*/0, /*TempRegFlags*/0,
+// CHECK-NEXT: GIR_EraseFromParent, /*InsnID*/0,
+// CHECK-NEXT: GIR_ConstrainSelectedInstOperands, /*InsnID*/0,
diff --git a/llvm/utils/TableGen/GlobalISelEmitter.cpp b/llvm/utils/TableGen/GlobalISelEmitter.cpp
index 22e7785275bd70..46bdbb04d8068c 100644
--- a/llvm/utils/TableGen/GlobalISelEmitter.cpp
+++ b/llvm/utils/TableGen/GlobalISelEmitter.cpp
@@ -288,11 +288,21 @@ static std::string getMangledRootDefName(StringRef DefOperandName) {
//===- GlobalISelEmitter class --------------------------------------------===//
-static Expected<LLTCodeGen> getInstResultType(const TreePatternNode *Dst) {
+static Expected<LLTCodeGen> getInstResultType(const TreePatternNode *Dst,
+ const CodeGenTarget &Target) {
+ // While allowing more than one output (both implicit and explicit defs)
+ // below, we only expect one explicit def here.
+ assert(Dst->getOperator()->isSubClassOf("Instruction"));
+ CodeGenInstruction &InstInfo = Target.getInstruction(Dst->getOperator());
+ if (InstInfo.Operands.NumDefs != 1)
+ return failedImport("Dst pattern child is not having single result");
+
ArrayRef<TypeSetByHwMode> ChildTypes = Dst->getExtTypes();
- if (ChildTypes.size() != 1)
- return failedImport("Dst pattern child has multiple results");
+ if (ChildTypes.size() < 1)
+ return failedImport("Dst pattern child has no result");
+ // If there are multiple results, just take the first one (this is how
+ // SelectionDAG does it).
std::optional<LLTCodeGen> MaybeOpTy;
if (ChildTypes.front().isMachineValueType()) {
MaybeOpTy = MVTToLLT(ChildTypes.front().getMachineValueType().SimpleTy);
@@ -1221,7 +1231,7 @@ Expected<action_iterator> GlobalISelEmitter::importExplicitUseRenderer(
}
if (DstChild->getOperator()->isSubClassOf("Instruction")) {
- auto OpTy = getInstResultType(DstChild);
+ auto OpTy = getInstResultType(DstChild, Target);
if (!OpTy)
return OpTy.takeError();
@@ -1556,7 +1566,7 @@ Expected<action_iterator> GlobalISelEmitter::importExplicitUseRenderers(
if (!ValChild->isLeaf()) {
// We really have to handle the source instruction, and then insert a
// copy from the subregister.
- auto ExtractSrcTy = getInstResultType(ValChild);
+ auto ExtractSrcTy = getInstResultType(ValChild, Target);
if (!ExtractSrcTy)
return ExtractSrcTy.takeError();
@@ -1779,10 +1789,11 @@ GlobalISelEmitter::inferRegClassFromPattern(const TreePatternNode *N) {
return getRegClassFromLeaf(N);
// We don't have a leaf node, so we have to try and infer something. Check
- // that we have an instruction that we an infer something from.
+ // that we have an instruction that we can infer something from.
- // Only handle things that produce a single type.
- if (N->getNumTypes() != 1)
+ // Only handle things that produce at least one value (if multiple values,
+ // just take the first one).
+ if (N->getNumTypes() < 1)
return std::nullopt;
Record *OpRec = N->getOperator();
>From d0218883e952d46afcca6a6ac0173db1edecfae5 Mon Sep 17 00:00:00 2001
From: Bjorn Pettersson <bjorn.a.pettersson at ericsson.com>
Date: Thu, 8 Feb 2024 15:06:40 +0100
Subject: [PATCH 2/3] fixup (to be squashed)
---
.../GlobalISelEmitter-multiple-output.td | 18 +++++++++---------
llvm/utils/TableGen/GlobalISelEmitter.cpp | 5 +++--
2 files changed, 12 insertions(+), 11 deletions(-)
diff --git a/llvm/test/TableGen/GlobalISelEmitter-multiple-output.td b/llvm/test/TableGen/GlobalISelEmitter-multiple-output.td
index 40d79b95928ac9..e063ebd4c2bbdd 100644
--- a/llvm/test/TableGen/GlobalISelEmitter-multiple-output.td
+++ b/llvm/test/TableGen/GlobalISelEmitter-multiple-output.td
@@ -97,23 +97,23 @@ def OtherInstr : I<(outs GPR32:$dst), (ins GPR32:$src), []>;
def : Pat<(i32 (add i32:$src, i32:$src)),
(OtherInstr (ImplicitDefInstr GPR32:$src))>;
-// CHECK: GIM_CheckOpcode, /*MI*/0, TargetOpcode::G_ADD,
-// CHECK-NEXT: // MIs[0] dst
+// CHECK: GIM_CheckOpcode, /*MI*/0, GIMT_Encode2(TargetOpcode::G_ADD),
+// CHECK-NEXT: // MIs[0] DstI[dst]
// CHECK-NEXT: GIM_CheckType, /*MI*/0, /*Op*/0, /*Type*/GILLT_s32,
-// CHECK-NEXT: GIM_CheckRegBankForClass, /*MI*/0, /*Op*/0, /*RC*/MyTarget::GPR32RegClassID,
+// CHECK-NEXT: GIM_CheckRegBankForClass, /*MI*/0, /*Op*/0, /*RC*/GIMT_Encode2(MyTarget::GPR32RegClassID),
// CHECK-NEXT: // MIs[0] src
// CHECK-NEXT: GIM_CheckType, /*MI*/0, /*Op*/1, /*Type*/GILLT_s32,
// CHECK-NEXT: // MIs[0] src
// CHECK-NEXT: GIM_CheckIsSameOperand, /*MI*/0, /*OpIdx*/2, /*OtherMI*/0, /*OtherOpIdx*/1,
// CHECK-NEXT: // (add:{ *:[i32] } i32:{ *:[i32] }:$src, i32:{ *:[i32] }:$src) => (OtherInstr:{ *:[i32] } (ImplicitDefInstr:{ *:[i32] }:{ *:[i32] } GPR32:{ *:[i32] }:$src))
// CHECK-NEXT: GIR_MakeTempReg, /*TempRegID*/0, /*TypeID*/GILLT_s32,
-// CHECK-NEXT: GIR_BuildMI, /*InsnID*/1, /*Opcode*/MyTarget::ImplicitDefInstr,
-// CHECK-NEXT: GIR_AddTempRegister, /*InsnID*/1, /*TempRegID*/0, /*TempRegFlags*/RegState::Define,
+// CHECK-NEXT: GIR_BuildMI, /*InsnID*/1, /*Opcode*/GIMT_Encode2(MyTarget::ImplicitDefInstr),
+// CHECK-NEXT: GIR_AddTempRegister, /*InsnID*/1, /*TempRegID*/0, /*TempRegFlags*/GIMT_Encode2(RegState::Define),
// CHECK-NEXT: GIR_Copy, /*NewInsnID*/1, /*OldInsnID*/0, /*OpIdx*/1, // src
// CHECK-NEXT: GIR_SetImplicitDefDead, /*InsnID*/1, /*OpIdx for MyTarget::R0*/0,
// CHECK-NEXT: GIR_ConstrainSelectedInstOperands, /*InsnID*/1,
-// CHECK-NEXT: GIR_BuildMI, /*InsnID*/0, /*Opcode*/MyTarget::OtherInstr,
-// CHECK-NEXT: GIR_Copy, /*NewInsnID*/0, /*OldInsnID*/0, /*OpIdx*/0, // dst
-// CHECK-NEXT: GIR_AddTempRegister, /*InsnID*/0, /*TempRegID*/0, /*TempRegFlags*/0,
-// CHECK-NEXT: GIR_EraseFromParent, /*InsnID*/0,
+// CHECK-NEXT: GIR_BuildMI, /*InsnID*/0, /*Opcode*/GIMT_Encode2(MyTarget::OtherInstr),
+// CHECK-NEXT: GIR_Copy, /*NewInsnID*/0, /*OldInsnID*/0, /*OpIdx*/0, // DstI[dst]
+// CHECK-NEXT: GIR_AddSimpleTempRegister, /*InsnID*/0, /*TempRegID*/0,
// CHECK-NEXT: GIR_ConstrainSelectedInstOperands, /*InsnID*/0,
+// CHECK-NEXT: GIR_EraseFromParent, /*InsnID*/0,
diff --git a/llvm/utils/TableGen/GlobalISelEmitter.cpp b/llvm/utils/TableGen/GlobalISelEmitter.cpp
index 46bdbb04d8068c..2dfa9a6a47f193 100644
--- a/llvm/utils/TableGen/GlobalISelEmitter.cpp
+++ b/llvm/utils/TableGen/GlobalISelEmitter.cpp
@@ -1,3 +1,4 @@
+
//===- GlobalISelEmitter.cpp - Generate an instruction selector -----------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
@@ -290,12 +291,12 @@ static std::string getMangledRootDefName(StringRef DefOperandName) {
static Expected<LLTCodeGen> getInstResultType(const TreePatternNode *Dst,
const CodeGenTarget &Target) {
- // While allowing more than one output (both implicit and explicit defs)
+ // While we allow more than one output (both implicit and explicit defs)
// below, we only expect one explicit def here.
assert(Dst->getOperator()->isSubClassOf("Instruction"));
CodeGenInstruction &InstInfo = Target.getInstruction(Dst->getOperator());
if (InstInfo.Operands.NumDefs != 1)
- return failedImport("Dst pattern child is not having single result");
+ return failedImport("Dst pattern child is not having exactly one result");
ArrayRef<TypeSetByHwMode> ChildTypes = Dst->getExtTypes();
if (ChildTypes.size() < 1)
>From 12af8efebec18e5bffb599fdc07ff4d67cfd35cb Mon Sep 17 00:00:00 2001
From: Bjorn Pettersson <bjorn.a.pettersson at ericsson.com>
Date: Thu, 15 Feb 2024 11:43:34 +0100
Subject: [PATCH 3/3] fixup 2 (to be squashed)
---
llvm/test/TableGen/GlobalISelEmitter-multiple-output-reject.td | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/llvm/test/TableGen/GlobalISelEmitter-multiple-output-reject.td b/llvm/test/TableGen/GlobalISelEmitter-multiple-output-reject.td
index b93aa20d9da23b..98bf42d55a8946 100644
--- a/llvm/test/TableGen/GlobalISelEmitter-multiple-output-reject.td
+++ b/llvm/test/TableGen/GlobalISelEmitter-multiple-output-reject.td
@@ -11,4 +11,4 @@ def OtherInstr : I<(outs GPR32:$dst), (ins GPR32:$src), []>;
def : Pat<(i32 (add i32:$src, i32:$src)),
(OtherInstr (TwoOutsInstr GPR32:$src))>;
-// CHECK: warning: Skipped pattern: Dst pattern child is not having single result
+// CHECK: warning: Skipped pattern: Dst pattern child is not having exactly one result
More information about the llvm-commits
mailing list