[llvm] [AMDGPU] Add regbankselect rules for G_ADD/SUB (PR #159860)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Sep 19 15:09:04 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-globalisel
@llvm/pr-subscribers-backend-amdgpu
Author: Anshil Gandhi (gandhi56)
<details>
<summary>Changes</summary>
This patch adds support for S64 types and updates tests accordingly.
---
Full diff: https://github.com/llvm/llvm-project/pull/159860.diff
4 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/AMDGPURegBankLegalizeRules.cpp (+3-1)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-add.s16.mir (+6-11)
- (added) llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-add.s64.mir (+76)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-add.v2s16.mir (+6-16)
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/AMDGPURegBankLegalizeRules.cpp b/llvm/lib/Target/AMDGPU/AMDGPURegBankLegalizeRules.cpp
index 0776d14a84067..ffc6cd977371b 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPURegBankLegalizeRules.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPURegBankLegalizeRules.cpp
@@ -470,7 +470,9 @@ RegBankLegalizeRules::RegBankLegalizeRules(const GCNSubtarget &_ST,
.Uni(S16, {{Sgpr32Trunc}, {Sgpr32AExt, Sgpr32AExt}})
.Div(S16, {{Vgpr16}, {Vgpr16, Vgpr16}})
.Uni(S32, {{Sgpr32}, {Sgpr32, Sgpr32}})
- .Div(S32, {{Vgpr32}, {Vgpr32, Vgpr32}});
+ .Div(S32, {{Vgpr32}, {Vgpr32, Vgpr32}})
+ .Uni(S64, {{Sgpr64}, {Sgpr64, Sgpr32}})
+ .Div(S64, {{Vgpr64}, {Vgpr64, Vgpr32}});
addRulesForGOpcs({G_MUL}, Standard).Div(S32, {{Vgpr32}, {Vgpr32, Vgpr32}});
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-add.s16.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-add.s16.mir
index 54ee69fcb2204..6e16b2aeea0f8 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-add.s16.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-add.s16.mir
@@ -1,6 +1,6 @@
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
-# RUN: llc -mtriple=amdgcn -mcpu=fiji -run-pass=regbankselect %s -verify-machineinstrs -o - -regbankselect-fast | FileCheck %s
-# RUN: llc -mtriple=amdgcn -mcpu=fiji -run-pass=regbankselect %s -verify-machineinstrs -o - -regbankselect-greedy | FileCheck %s
+# RUN: llc -mtriple=amdgcn -mcpu=fiji -run-pass=amdgpu-regbankselect %s -verify-machineinstrs -o - -regbankselect-fast | FileCheck %s
+# RUN: llc -mtriple=amdgcn -mcpu=fiji -run-pass=amdgpu-regbankselect %s -verify-machineinstrs -o - -regbankselect-greedy | FileCheck %s
---
name: add_s16_ss
legalized: true
@@ -15,11 +15,8 @@ body: |
; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr1
; CHECK-NEXT: [[TRUNC:%[0-9]+]]:sgpr(s16) = G_TRUNC [[COPY]](s32)
; CHECK-NEXT: [[TRUNC1:%[0-9]+]]:sgpr(s16) = G_TRUNC [[COPY1]](s32)
- ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:sgpr(s32) = G_ANYEXT [[TRUNC]](s16)
- ; CHECK-NEXT: [[ANYEXT1:%[0-9]+]]:sgpr(s32) = G_ANYEXT [[TRUNC1]](s16)
- ; CHECK-NEXT: [[ADD:%[0-9]+]]:sgpr(s32) = G_ADD [[ANYEXT]], [[ANYEXT1]]
- ; CHECK-NEXT: [[TRUNC2:%[0-9]+]]:sgpr(s16) = G_TRUNC [[ADD]](s32)
- ; CHECK-NEXT: S_ENDPGM 0, implicit [[TRUNC2]](s16)
+ ; CHECK-NEXT: [[ADD:%[0-9]+]]:sgpr(s16) = G_ADD [[TRUNC]], [[TRUNC1]]
+ ; CHECK-NEXT: S_ENDPGM 0, implicit [[ADD]](s16)
%0:_(s32) = COPY $sgpr0
%1:_(s32) = COPY $sgpr1
%2:_(s16) = G_TRUNC %0
@@ -42,8 +39,7 @@ body: |
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
; CHECK-NEXT: [[TRUNC:%[0-9]+]]:sgpr(s16) = G_TRUNC [[COPY]](s32)
; CHECK-NEXT: [[TRUNC1:%[0-9]+]]:vgpr(s16) = G_TRUNC [[COPY1]](s32)
- ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(s16) = COPY [[TRUNC]](s16)
- ; CHECK-NEXT: [[ADD:%[0-9]+]]:vgpr(s16) = G_ADD [[COPY2]], [[TRUNC1]]
+ ; CHECK-NEXT: [[ADD:%[0-9]+]]:vgpr(s16) = G_ADD [[TRUNC]], [[TRUNC1]]
; CHECK-NEXT: S_ENDPGM 0, implicit [[ADD]](s16)
%0:_(s32) = COPY $sgpr0
%1:_(s32) = COPY $vgpr0
@@ -67,8 +63,7 @@ body: |
; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr(s32) = COPY $sgpr0
; CHECK-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s16) = G_TRUNC [[COPY]](s32)
; CHECK-NEXT: [[TRUNC1:%[0-9]+]]:sgpr(s16) = G_TRUNC [[COPY1]](s32)
- ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(s16) = COPY [[TRUNC1]](s16)
- ; CHECK-NEXT: [[ADD:%[0-9]+]]:vgpr(s16) = G_ADD [[TRUNC]], [[COPY2]]
+ ; CHECK-NEXT: [[ADD:%[0-9]+]]:vgpr(s16) = G_ADD [[TRUNC]], [[TRUNC1]]
; CHECK-NEXT: S_ENDPGM 0, implicit [[ADD]](s16)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $sgpr0
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-add.s64.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-add.s64.mir
new file mode 100644
index 0000000000000..eb93868ccc359
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-add.s64.mir
@@ -0,0 +1,76 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -run-pass=amdgpu-regbankselect %s -o - | FileCheck %s
+
+---
+name: add_s64_ss
+legalized: true
+
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1, $sgpr2_sgpr3
+ ; CHECK-LABEL: name: add_s64_ss
+ ; CHECK: liveins: $sgpr0_sgpr1, $sgpr2_sgpr3
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr(s64) = COPY $sgpr0_sgpr1
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr(s64) = COPY $sgpr2_sgpr3
+ ; CHECK-NEXT: [[ADD:%[0-9]+]]:sgpr(s64) = G_ADD [[COPY]], [[COPY1]]
+ %0:_(s64) = COPY $sgpr0_sgpr1
+ %1:_(s64) = COPY $sgpr2_sgpr3
+ %2:_(s64) = G_ADD %0, %1
+...
+
+---
+name: add_s64_sv
+legalized: true
+
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1, $vgpr0_vgpr1
+ ; CHECK-LABEL: name: add_s64_sv
+ ; CHECK: liveins: $sgpr0_sgpr1, $vgpr0_vgpr1
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr(s64) = COPY $sgpr0_sgpr1
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
+ ; CHECK-NEXT: [[ADD:%[0-9]+]]:vgpr(s64) = G_ADD [[COPY]], [[COPY1]]
+ %0:_(s64) = COPY $sgpr0_sgpr1
+ %1:_(s64) = COPY $vgpr0_vgpr1
+ %2:_(s64) = G_ADD %0, %1
+...
+
+---
+name: add_s64_vs
+legalized: true
+
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1, $vgpr0_vgpr1
+ ; CHECK-LABEL: name: add_s64_vs
+ ; CHECK: liveins: $sgpr0_sgpr1, $vgpr0_vgpr1
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr(s64) = COPY $sgpr0_sgpr1
+ ; CHECK-NEXT: [[ADD:%[0-9]+]]:vgpr(s64) = G_ADD [[COPY]], [[COPY1]]
+ %0:_(s64) = COPY $vgpr0_vgpr1
+ %1:_(s64) = COPY $sgpr0_sgpr1
+ %2:_(s64) = G_ADD %0, %1
+...
+
+---
+name: add_s64_vv
+legalized: true
+
+body: |
+ bb.0:
+ liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
+ ; CHECK-LABEL: name: add_s64_vv
+ ; CHECK: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(s64) = COPY $vgpr0_vgpr1
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(s64) = COPY $vgpr2_vgpr3
+ ; CHECK-NEXT: [[ADD:%[0-9]+]]:vgpr(s64) = G_ADD [[COPY]], [[COPY1]]
+ %0:_(s64) = COPY $vgpr0_vgpr1
+ %1:_(s64) = COPY $vgpr2_vgpr3
+ %2:_(s64) = G_ADD %0, %1
+...
+
+
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-add.v2s16.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-add.v2s16.mir
index 97018fac13a87..cc278503d6965 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-add.v2s16.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-add.v2s16.mir
@@ -1,6 +1,6 @@
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
-# RUN: llc -mtriple=amdgcn -mcpu=gfx900 -run-pass=regbankselect %s -verify-machineinstrs -o - -regbankselect-fast | FileCheck %s
-# RUN: llc -mtriple=amdgcn -mcpu=gfx900 -run-pass=regbankselect %s -verify-machineinstrs -o - -regbankselect-greedy | FileCheck %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx900 -run-pass=amdgpu-regbankselect %s -verify-machineinstrs -o - -regbankselect-fast | FileCheck %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx900 -run-pass=amdgpu-regbankselect %s -verify-machineinstrs -o - -regbankselect-greedy | FileCheck %s
---
name: add_v2s16_ss
@@ -14,16 +14,8 @@ body: |
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr(<2 x s16>) = COPY $sgpr0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr(<2 x s16>) = COPY $sgpr1
- ; CHECK-NEXT: [[BITCAST:%[0-9]+]]:sgpr(s32) = G_BITCAST [[COPY]](<2 x s16>)
- ; CHECK-NEXT: [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 16
- ; CHECK-NEXT: [[LSHR:%[0-9]+]]:sgpr(s32) = G_LSHR [[BITCAST]], [[C]](s32)
- ; CHECK-NEXT: [[BITCAST1:%[0-9]+]]:sgpr(s32) = G_BITCAST [[COPY1]](<2 x s16>)
- ; CHECK-NEXT: [[C1:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 16
- ; CHECK-NEXT: [[LSHR1:%[0-9]+]]:sgpr(s32) = G_LSHR [[BITCAST1]], [[C1]](s32)
- ; CHECK-NEXT: [[ADD:%[0-9]+]]:sgpr(s32) = G_ADD [[BITCAST]], [[BITCAST1]]
- ; CHECK-NEXT: [[ADD1:%[0-9]+]]:sgpr(s32) = G_ADD [[LSHR]], [[LSHR1]]
- ; CHECK-NEXT: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:sgpr(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[ADD]](s32), [[ADD1]](s32)
- ; CHECK-NEXT: S_ENDPGM 0, implicit [[BUILD_VECTOR_TRUNC]](<2 x s16>)
+ ; CHECK-NEXT: [[ADD:%[0-9]+]]:sgpr(<2 x s16>) = G_ADD [[COPY]], [[COPY1]]
+ ; CHECK-NEXT: S_ENDPGM 0, implicit [[ADD]](<2 x s16>)
%0:_(<2 x s16>) = COPY $sgpr0
%1:_(<2 x s16>) = COPY $sgpr1
%2:_(<2 x s16>) = G_ADD %0, %1
@@ -42,8 +34,7 @@ body: |
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr(<2 x s16>) = COPY $sgpr0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr0
- ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(<2 x s16>) = COPY [[COPY]](<2 x s16>)
- ; CHECK-NEXT: [[ADD:%[0-9]+]]:vgpr(<2 x s16>) = G_ADD [[COPY2]], [[COPY1]]
+ ; CHECK-NEXT: [[ADD:%[0-9]+]]:vgpr(<2 x s16>) = G_ADD [[COPY]], [[COPY1]]
; CHECK-NEXT: S_ENDPGM 0, implicit [[ADD]](<2 x s16>)
%0:_(<2 x s16>) = COPY $sgpr0
%1:_(<2 x s16>) = COPY $vgpr0
@@ -63,8 +54,7 @@ body: |
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr(<2 x s16>) = COPY $sgpr0
- ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr(<2 x s16>) = COPY [[COPY1]](<2 x s16>)
- ; CHECK-NEXT: [[ADD:%[0-9]+]]:vgpr(<2 x s16>) = G_ADD [[COPY]], [[COPY2]]
+ ; CHECK-NEXT: [[ADD:%[0-9]+]]:vgpr(<2 x s16>) = G_ADD [[COPY]], [[COPY1]]
%0:_(<2 x s16>) = COPY $vgpr0
%1:_(<2 x s16>) = COPY $sgpr0
%2:_(<2 x s16>) = G_ADD %0, %1
``````````
</details>
https://github.com/llvm/llvm-project/pull/159860
More information about the llvm-commits
mailing list