[llvm] [AMDGPU] Define VS_128*. NFCI (PR #161798)
Stanislav Mekhanoshin via llvm-commits
llvm-commits at lists.llvm.org
Thu Oct 2 23:41:36 PDT 2025
https://github.com/rampitec created https://github.com/llvm/llvm-project/pull/161798
Needed for future patch.
>From 6c66b220a8c23bff686bc78071acf2355ff9a58a Mon Sep 17 00:00:00 2001
From: Stanislav Mekhanoshin <Stanislav.Mekhanoshin at amd.com>
Date: Thu, 2 Oct 2025 23:40:29 -0700
Subject: [PATCH] [AMDGPU] Define VS_128*. NFCI
Needed for future patch.
---
llvm/lib/Target/AMDGPU/SIRegisterInfo.td | 16 +++++++
.../coalesce-copy-to-agpr-to-av-registers.mir | 48 +++++++++----------
...class-vgpr-mfma-to-av-with-load-source.mir | 12 ++---
llvm/test/CodeGen/AMDGPU/inline-asm.i128.ll | 24 +++++-----
...al-regcopy-and-spill-missed-at-regalloc.ll | 8 ++--
...gpr-mfma-to-agpr-subreg-insert-extract.mir | 12 ++---
...te-vgpr-mfma-to-agpr-subreg-src2-chain.mir | 16 +++----
7 files changed, 76 insertions(+), 60 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.td b/llvm/lib/Target/AMDGPU/SIRegisterInfo.td
index 8f1dd6244f20d..56305804e816a 100644
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.td
+++ b/llvm/lib/Target/AMDGPU/SIRegisterInfo.td
@@ -1163,6 +1163,22 @@ def VS_64_Lo256 : SIRegisterClass<"AMDGPU", VReg_64.RegTypes, 32,
let HasSGPR = 1;
let Size = 64;
}
+
+def VS_128 : SIRegisterClass<"AMDGPU", VReg_128.RegTypes, 32,
+ (add VReg_128, SReg_128)> {
+ let isAllocatable = 0;
+ let HasVGPR = 1;
+ let HasSGPR = 1;
+ let Size = 128;
+}
+
+def VS_128_Align2 : SIRegisterClass<"AMDGPU", VReg_128.RegTypes, 32,
+ (add VReg_128_Align2, SReg_128)> {
+ let isAllocatable = 0;
+ let HasVGPR = 1;
+ let HasSGPR = 1;
+ let Size = 128;
+}
} // End GeneratePressureSet = 0
// Define a register tuple class, along with one requiring an even
diff --git a/llvm/test/CodeGen/AMDGPU/coalesce-copy-to-agpr-to-av-registers.mir b/llvm/test/CodeGen/AMDGPU/coalesce-copy-to-agpr-to-av-registers.mir
index 029aa3957d32b..ce1ea4d2e3cbc 100644
--- a/llvm/test/CodeGen/AMDGPU/coalesce-copy-to-agpr-to-av-registers.mir
+++ b/llvm/test/CodeGen/AMDGPU/coalesce-copy-to-agpr-to-av-registers.mir
@@ -128,13 +128,13 @@ body: |
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
; CHECK-NEXT: undef [[COPY2:%[0-9]+]].sub0_sub1:areg_128 = COPY [[COPY]]
; CHECK-NEXT: [[COPY2:%[0-9]+]].sub2_sub3:areg_128 = COPY [[COPY1]]
- ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8323081 /* reguse:AReg_128 */, [[COPY2]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8847369 /* reguse:AReg_128 */, [[COPY2]]
; CHECK-NEXT: SI_RETURN
%0:vreg_64 = COPY $vgpr0_vgpr1
%1:vreg_64 = COPY $vgpr2_vgpr3
undef %2.sub0_sub1:areg_128 = COPY %0
%2.sub2_sub3:areg_128 = COPY %1
- INLINEASM &"; use $0", 0 /* attdialect */, 8323081 /* reguse:AReg_128 */, killed %2
+ INLINEASM &"; use $0", 0 /* attdialect */, 8847369 /* reguse:AReg_128 */, killed %2
SI_RETURN
...
@@ -153,13 +153,13 @@ body: |
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
; CHECK-NEXT: undef [[COPY2:%[0-9]+]].sub0_sub1:areg_128_align2 = COPY [[COPY]]
; CHECK-NEXT: [[COPY2:%[0-9]+]].sub2_sub3:areg_128_align2 = COPY [[COPY1]]
- ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8650761 /* reguse:AReg_128_Align2 */, [[COPY2]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 9568265 /* reguse:AReg_128_Align2 */, [[COPY2]]
; CHECK-NEXT: SI_RETURN
%0:vreg_64 = COPY $vgpr0_vgpr1
%1:vreg_64 = COPY $vgpr2_vgpr3
undef %2.sub0_sub1:areg_128_align2 = COPY %0
%2.sub2_sub3:areg_128_align2 = COPY %1
- INLINEASM &"; use $0", 0 /* attdialect */, 8650761 /* reguse:AReg_128_Align2 */, %2
+ INLINEASM &"; use $0", 0 /* attdialect */, 9568265 /* reguse:AReg_128_Align2 */, %2
SI_RETURN
...
@@ -398,14 +398,14 @@ body: |
; CHECK-NEXT: [[COPY1:%[0-9]+]].sub1:areg_128 = COPY [[COPY]]
; CHECK-NEXT: [[COPY1:%[0-9]+]].sub2:areg_128 = COPY [[COPY]]
; CHECK-NEXT: [[COPY1:%[0-9]+]].sub3:areg_128 = COPY [[COPY]]
- ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8323081 /* reguse:AReg_128 */, [[COPY1]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8847369 /* reguse:AReg_128 */, [[COPY1]]
; CHECK-NEXT: SI_RETURN
%0:vgpr_32 = COPY $vgpr0
undef %1.sub0:areg_128 = COPY %0
%1.sub1:areg_128 = COPY %0
%1.sub2:areg_128 = COPY %0
%1.sub3:areg_128 = COPY %0
- INLINEASM &"; use $0", 0 /* attdialect */, 8323081 /* reguse:AReg_128 */, killed %1
+ INLINEASM &"; use $0", 0 /* attdialect */, 8847369 /* reguse:AReg_128 */, killed %1
SI_RETURN
...
@@ -425,14 +425,14 @@ body: |
; CHECK-NEXT: [[COPY1:%[0-9]+]].sub1:areg_128_align2 = COPY [[COPY]]
; CHECK-NEXT: [[COPY1:%[0-9]+]].sub2:areg_128_align2 = COPY [[COPY]]
; CHECK-NEXT: [[COPY1:%[0-9]+]].sub3:areg_128_align2 = COPY [[COPY]]
- ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8650761 /* reguse:AReg_128_Align2 */, [[COPY1]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 9568265 /* reguse:AReg_128_Align2 */, [[COPY1]]
; CHECK-NEXT: SI_RETURN
%0:vgpr_32 = COPY $vgpr0
undef %1.sub0:areg_128_align2 = COPY %0
%1.sub1:areg_128_align2 = COPY %0
%1.sub2:areg_128_align2 = COPY %0
%1.sub3:areg_128_align2 = COPY %0
- INLINEASM &"; use $0", 0 /* attdialect */, 8650761 /* reguse:AReg_128_Align2 */, %1
+ INLINEASM &"; use $0", 0 /* attdialect */, 9568265 /* reguse:AReg_128_Align2 */, %1
SI_RETURN
...
@@ -641,13 +641,13 @@ body: |
; CHECK-NEXT: [[COPY:%[0-9]+]].sub2_sub3:vreg_128 = COPY $vgpr2_vgpr3
; CHECK-NEXT: undef [[COPY1:%[0-9]+]].sub0_sub1:areg_128 = COPY [[COPY]].sub0_sub1
; CHECK-NEXT: [[COPY1:%[0-9]+]].sub2_sub3:areg_128 = COPY [[COPY]].sub2_sub3
- ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8323081 /* reguse:AReg_128 */, [[COPY1]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8847369 /* reguse:AReg_128 */, [[COPY1]]
; CHECK-NEXT: SI_RETURN
undef %0.sub0_sub1:vreg_128 =COPY $vgpr0_vgpr1
%0.sub2_sub3:vreg_128 = COPY $vgpr2_vgpr3
undef %2.sub0_sub1:areg_128 = COPY %0.sub0_sub1
%2.sub2_sub3:areg_128 = COPY %0.sub2_sub3
- INLINEASM &"; use $0", 0 /* attdialect */, 8323081 /* reguse:AReg_128 */, killed %2
+ INLINEASM &"; use $0", 0 /* attdialect */, 8847369 /* reguse:AReg_128 */, killed %2
SI_RETURN
...
@@ -668,13 +668,13 @@ body: |
; CHECK-NEXT: [[COPY:%[0-9]+]].sub1:vreg_128 = COPY $vgpr2_vgpr3
; CHECK-NEXT: undef [[COPY1:%[0-9]+]].sub0_sub1:areg_128_align2 = COPY [[COPY]].sub0
; CHECK-NEXT: [[COPY1:%[0-9]+]].sub2_sub3:areg_128_align2 = COPY [[COPY]].sub1
- ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8650761 /* reguse:AReg_128_Align2 */, [[COPY1]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 9568265 /* reguse:AReg_128_Align2 */, [[COPY1]]
; CHECK-NEXT: SI_RETURN
undef %0.sub0:vreg_128 =COPY $vgpr0_vgpr1
%0.sub1:vreg_128 = COPY $vgpr2_vgpr3
undef %2.sub0_sub1:areg_128_align2 = COPY %0.sub0
%2.sub2_sub3:areg_128_align2 = COPY %0.sub1
- INLINEASM &"; use $0", 0 /* attdialect */, 8650761 /* reguse:AReg_128_Align2 */, %2
+ INLINEASM &"; use $0", 0 /* attdialect */, 9568265 /* reguse:AReg_128_Align2 */, %2
SI_RETURN
...
@@ -890,14 +890,14 @@ body: |
; CHECK-NEXT: [[COPY1:%[0-9]+]].sub1:areg_128 = COPY [[COPY]].sub0
; CHECK-NEXT: [[COPY1:%[0-9]+]].sub2:areg_128 = COPY [[COPY]].sub0
; CHECK-NEXT: [[COPY1:%[0-9]+]].sub3:areg_128 = COPY [[COPY]].sub0
- ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8323081 /* reguse:AReg_128 */, [[COPY1]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8847369 /* reguse:AReg_128 */, [[COPY1]]
; CHECK-NEXT: SI_RETURN
undef %0.sub0:vreg_64 = COPY $vgpr0
undef %1.sub0:areg_128 = COPY %0.sub0
%1.sub1:areg_128 = COPY %0.sub0
%1.sub2:areg_128 = COPY %0.sub0
%1.sub3:areg_128 = COPY %0.sub0
- INLINEASM &"; use $0", 0 /* attdialect */, 8323081 /* reguse:AReg_128 */, killed %1
+ INLINEASM &"; use $0", 0 /* attdialect */, 8847369 /* reguse:AReg_128 */, killed %1
SI_RETURN
...
@@ -917,14 +917,14 @@ body: |
; CHECK-NEXT: [[COPY1:%[0-9]+]].sub1:areg_128_align2 = COPY [[COPY]].sub0
; CHECK-NEXT: [[COPY1:%[0-9]+]].sub2:areg_128_align2 = COPY [[COPY]].sub0
; CHECK-NEXT: [[COPY1:%[0-9]+]].sub3:areg_128_align2 = COPY [[COPY]].sub0
- ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8650761 /* reguse:AReg_128_Align2 */, [[COPY1]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 9568265 /* reguse:AReg_128_Align2 */, [[COPY1]]
; CHECK-NEXT: SI_RETURN
undef %0.sub0:vreg_64 = COPY $vgpr0
undef %1.sub0:areg_128_align2 = COPY %0.sub0
%1.sub1:areg_128_align2 = COPY %0.sub0
%1.sub2:areg_128_align2 = COPY %0.sub0
%1.sub3:areg_128_align2 = COPY %0.sub0
- INLINEASM &"; use $0", 0 /* attdialect */, 8650761 /* reguse:AReg_128_Align2 */, %1
+ INLINEASM &"; use $0", 0 /* attdialect */, 9568265 /* reguse:AReg_128_Align2 */, %1
SI_RETURN
...
@@ -1051,13 +1051,13 @@ body: |
; CHECK-NEXT: [[COPY:%[0-9]+]].sub2_sub3:vreg_128 = COPY $vgpr2_vgpr3
; CHECK-NEXT: undef [[COPY1:%[0-9]+]].sub0_sub1:areg_128 = COPY [[COPY]].sub0_sub1
; CHECK-NEXT: [[COPY1:%[0-9]+]].sub2_sub3:areg_128 = COPY [[COPY]].sub2_sub3
- ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8323081 /* reguse:AReg_128 */, [[COPY1]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8847369 /* reguse:AReg_128 */, [[COPY1]]
; CHECK-NEXT: SI_RETURN
undef %0.sub0_sub1:vreg_128 = COPY $vgpr0_vgpr1
%0.sub2_sub3:vreg_128 = COPY $vgpr2_vgpr3
undef %2.sub0_sub1:areg_128 = COPY %0.sub0_sub1
%2.sub2_sub3:areg_128 = COPY %0.sub2_sub3
- INLINEASM &"; use $0", 0 /* attdialect */, 8323081 /* reguse:AReg_128 */, killed %2
+ INLINEASM &"; use $0", 0 /* attdialect */, 8847369 /* reguse:AReg_128 */, killed %2
SI_RETURN
...
@@ -1076,13 +1076,13 @@ body: |
; CHECK-NEXT: [[COPY:%[0-9]+]].sub2_sub3:vreg_128_align2 = COPY $vgpr2_vgpr3
; CHECK-NEXT: undef [[COPY1:%[0-9]+]].sub0_sub1:areg_128_align2 = COPY [[COPY]].sub0_sub1
; CHECK-NEXT: [[COPY1:%[0-9]+]].sub2_sub3:areg_128_align2 = COPY [[COPY]].sub2_sub3
- ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8650761 /* reguse:AReg_128_Align2 */, [[COPY1]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 9568265 /* reguse:AReg_128_Align2 */, [[COPY1]]
; CHECK-NEXT: SI_RETURN
undef %0.sub0_sub1:vreg_128_align2 = COPY $vgpr0_vgpr1
%0.sub2_sub3:vreg_128_align2 = COPY $vgpr2_vgpr3
undef %2.sub0_sub1:areg_128_align2 = COPY %0.sub0_sub1
%2.sub2_sub3:areg_128_align2 = COPY %0.sub2_sub3
- INLINEASM &"; use $0", 0 /* attdialect */, 8650761 /* reguse:AReg_128_Align2 */, %2
+ INLINEASM &"; use $0", 0 /* attdialect */, 9568265 /* reguse:AReg_128_Align2 */, %2
SI_RETURN
...
@@ -1358,11 +1358,11 @@ body: |
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:vreg_128 = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK-NEXT: [[COPY1:%[0-9]+]]:areg_128 = COPY [[COPY]]
- ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8323081 /* reguse:AReg_128 */, [[COPY1]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8847369 /* reguse:AReg_128 */, [[COPY1]]
; CHECK-NEXT: SI_RETURN
%0:vreg_128 = COPY $vgpr0_vgpr1_vgpr2_vgpr3
%2:areg_128 = COPY %0
- INLINEASM &"; use $0", 0 /* attdialect */, 8323081 /* reguse:AReg_128 */, killed %2
+ INLINEASM &"; use $0", 0 /* attdialect */, 8847369 /* reguse:AReg_128 */, killed %2
SI_RETURN
...
@@ -1379,11 +1379,11 @@ body: |
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:vreg_128_align2 = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK-NEXT: [[COPY1:%[0-9]+]]:areg_128_align2 = COPY [[COPY]]
- ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 8650761 /* reguse:AReg_128_Align2 */, [[COPY1]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 0 /* attdialect */, 9568265 /* reguse:AReg_128_Align2 */, [[COPY1]]
; CHECK-NEXT: SI_RETURN
%0:vreg_128_align2 = COPY $vgpr0_vgpr1_vgpr2_vgpr3
%2:areg_128_align2 = COPY %0
- INLINEASM &"; use $0", 0 /* attdialect */, 8650761 /* reguse:AReg_128_Align2 */, %2
+ INLINEASM &"; use $0", 0 /* attdialect */, 9568265 /* reguse:AReg_128_Align2 */, %2
SI_RETURN
...
diff --git a/llvm/test/CodeGen/AMDGPU/inflate-reg-class-vgpr-mfma-to-av-with-load-source.mir b/llvm/test/CodeGen/AMDGPU/inflate-reg-class-vgpr-mfma-to-av-with-load-source.mir
index 92836d8417ed3..63db24a63a54a 100644
--- a/llvm/test/CodeGen/AMDGPU/inflate-reg-class-vgpr-mfma-to-av-with-load-source.mir
+++ b/llvm/test/CodeGen/AMDGPU/inflate-reg-class-vgpr-mfma-to-av-with-load-source.mir
@@ -486,7 +486,7 @@ body: |
; CHECK-NEXT: S_NOP 0, implicit-def $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55
; CHECK-NEXT: S_NOP 0, implicit-def $vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63
; CHECK-NEXT: renamable $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY killed renamable $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
- ; CHECK-NEXT: INLINEASM &"; use $0 ", 1 /* sideeffect attdialect */, 39190537 /* reguse:VReg_512_Align2 */, killed renamable $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15
+ ; CHECK-NEXT: INLINEASM &"; use $0 ", 1 /* sideeffect attdialect */, 40239113 /* reguse:VReg_512_Align2 */, killed renamable $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15
; CHECK-NEXT: S_ENDPGM 0
bb.0:
S_NOP 0, implicit-def $agpr0
@@ -516,7 +516,7 @@ body: |
S_NOP 0, implicit-def $vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47
S_NOP 0, implicit-def $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55
S_NOP 0, implicit-def $vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63
- INLINEASM &"; use $0 ", 1 /* sideeffect attdialect */, 39190537 /* reguse:VReg_512_Align2 */, %0:vreg_512_align2
+ INLINEASM &"; use $0 ", 1 /* sideeffect attdialect */, 40239113 /* reguse:VReg_512_Align2 */, %0:vreg_512_align2
S_ENDPGM 0
...
@@ -1368,7 +1368,7 @@ body: |
; CHECK-NEXT: renamable $vgpr0_vgpr1 = GLOBAL_LOAD_DWORDX2 undef renamable $vgpr0_vgpr1, 0, 0, implicit $exec :: (load (s64), addrspace 1)
; CHECK-NEXT: early-clobber renamable $vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31_vgpr32_vgpr33 = V_MFMA_F32_32X32X8F16_vgprcd_e64 $vgpr16_vgpr17, $vgpr16_vgpr17, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, 0, 0, 0, implicit $mode, implicit $exec
; CHECK-NEXT: early-clobber renamable $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = V_MFMA_F32_32X32X8F16_vgprcd_e64 $vgpr16_vgpr17, $vgpr16_vgpr17, $vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31_vgpr32_vgpr33, 0, 0, 0, implicit $mode, implicit $exec
- ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 39190537 /* reguse:VReg_512_Align2 */, killed renamable $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15
+ ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 40239113 /* reguse:VReg_512_Align2 */, killed renamable $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15
; CHECK-NEXT: S_CBRANCH_VCCNZ %bb.1, implicit $vcc
; CHECK-NEXT: S_BRANCH %bb.2
; CHECK-NEXT: {{ $}}
@@ -1408,7 +1408,7 @@ body: |
undef %2.sub0_sub1:vreg_512_align2 = GLOBAL_LOAD_DWORDX2 undef %3:vreg_64_align2, 0, 0, implicit $exec :: (load (s64), addrspace 1)
early-clobber %0:vreg_512_align2 = V_MFMA_F32_32X32X8F16_vgprcd_e64 %1, %1, %2, 0, 0, 0, implicit $mode, implicit $exec
early-clobber %4:vreg_512_align2 = V_MFMA_F32_32X32X8F16_vgprcd_e64 %1, %1, %0, 0, 0, 0, implicit $mode, implicit $exec
- INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 39190537 /* reguse:VReg_512_Align2 */, %4
+ INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 40239113 /* reguse:VReg_512_Align2 */, %4
S_CBRANCH_VCCNZ %bb.1, implicit $vcc
S_BRANCH %bb.2
@@ -1726,7 +1726,7 @@ body: |
; CHECK-NEXT: renamable $vgpr0_vgpr1 = GLOBAL_LOAD_DWORDX2 undef renamable $vgpr0_vgpr1, 0, 0, implicit $exec :: (load (s64), addrspace 1)
; CHECK-NEXT: renamable $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = V_MFMA_F32_32X32X8F16_mac_vgprcd_e64 $vgpr16_vgpr17, $vgpr16_vgpr17, $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, 0, 0, 0, implicit $mode, implicit $exec
; CHECK-NEXT: early-clobber renamable $vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31_vgpr32_vgpr33 = V_MFMA_F32_32X32X8F16_vgprcd_e64 $vgpr16_vgpr17, $vgpr16_vgpr17, killed $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, 0, 0, 0, implicit $mode, implicit $exec
- ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 39190537 /* reguse:VReg_512_Align2 */, renamable $vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31_vgpr32_vgpr33
+ ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 40239113 /* reguse:VReg_512_Align2 */, renamable $vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31_vgpr32_vgpr33
; CHECK-NEXT: S_CBRANCH_VCCNZ %bb.1, implicit $vcc
; CHECK-NEXT: S_BRANCH %bb.2
; CHECK-NEXT: {{ $}}
@@ -1763,7 +1763,7 @@ body: |
undef %0.sub0_sub1:vreg_512_align2 = GLOBAL_LOAD_DWORDX2 undef %3:vreg_64_align2, 0, 0, implicit $exec :: (load (s64), addrspace 1)
%0:vreg_512_align2 = V_MFMA_F32_32X32X8F16_mac_vgprcd_e64 %1, %1, %0, 0, 0, 0, implicit $mode, implicit $exec
%4:vreg_512_align2 = V_MFMA_F32_32X32X8F16_vgprcd_e64 %1, %1, %0, 0, 0, 0, implicit $mode, implicit $exec
- INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 39190537 /* reguse:VReg_512_Align2 */, %4
+ INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 40239113 /* reguse:VReg_512_Align2 */, %4
S_CBRANCH_VCCNZ %bb.1, implicit $vcc
S_BRANCH %bb.2
diff --git a/llvm/test/CodeGen/AMDGPU/inline-asm.i128.ll b/llvm/test/CodeGen/AMDGPU/inline-asm.i128.ll
index 9cbdc3867e374..5b3e48698c32b 100644
--- a/llvm/test/CodeGen/AMDGPU/inline-asm.i128.ll
+++ b/llvm/test/CodeGen/AMDGPU/inline-asm.i128.ll
@@ -8,16 +8,16 @@
define amdgpu_kernel void @s_input_output_i128() {
; GFX908-LABEL: name: s_input_output_i128
; GFX908: bb.0 (%ir-block.0):
- ; GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 9633802 /* regdef:SGPR_128 */, def %13
+ ; GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 10682378 /* regdef:SGPR_128 */, def %13
; GFX908-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY %13
- ; GFX908-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 9633801 /* reguse:SGPR_128 */, [[COPY]]
+ ; GFX908-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 10682377 /* reguse:SGPR_128 */, [[COPY]]
; GFX908-NEXT: S_ENDPGM 0
;
; GFX90A-LABEL: name: s_input_output_i128
; GFX90A: bb.0 (%ir-block.0):
- ; GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 9633802 /* regdef:SGPR_128 */, def %11
+ ; GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 10682378 /* regdef:SGPR_128 */, def %11
; GFX90A-NEXT: [[COPY:%[0-9]+]]:sgpr_128 = COPY %11
- ; GFX90A-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 9633801 /* reguse:SGPR_128 */, [[COPY]]
+ ; GFX90A-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 10682377 /* reguse:SGPR_128 */, [[COPY]]
; GFX90A-NEXT: S_ENDPGM 0
%val = tail call i128 asm sideeffect "; def $0", "=s"()
call void asm sideeffect "; use $0", "s"(i128 %val)
@@ -27,16 +27,16 @@ define amdgpu_kernel void @s_input_output_i128() {
define amdgpu_kernel void @v_input_output_i128() {
; GFX908-LABEL: name: v_input_output_i128
; GFX908: bb.0 (%ir-block.0):
- ; GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 7798794 /* regdef:VReg_128 */, def %13
+ ; GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 7929866 /* regdef:VReg_128 */, def %13
; GFX908-NEXT: [[COPY:%[0-9]+]]:vreg_128 = COPY %13
- ; GFX908-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 7798793 /* reguse:VReg_128 */, [[COPY]]
+ ; GFX908-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 7929865 /* reguse:VReg_128 */, [[COPY]]
; GFX908-NEXT: S_ENDPGM 0
;
; GFX90A-LABEL: name: v_input_output_i128
; GFX90A: bb.0 (%ir-block.0):
- ; GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 7995402 /* regdef:VReg_128_Align2 */, def %11
+ ; GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 8257546 /* regdef:VReg_128_Align2 */, def %11
; GFX90A-NEXT: [[COPY:%[0-9]+]]:vreg_128_align2 = COPY %11
- ; GFX90A-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 7995401 /* reguse:VReg_128_Align2 */, [[COPY]]
+ ; GFX90A-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8257545 /* reguse:VReg_128_Align2 */, [[COPY]]
; GFX90A-NEXT: S_ENDPGM 0
%val = tail call i128 asm sideeffect "; def $0", "=v"()
call void asm sideeffect "; use $0", "v"(i128 %val)
@@ -47,16 +47,16 @@ define amdgpu_kernel void @a_input_output_i128() {
; GFX908-LABEL: name: a_input_output_i128
; GFX908: bb.0 (%ir-block.0):
- ; GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 8323082 /* regdef:AReg_128 */, def %13
+ ; GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 8847370 /* regdef:AReg_128 */, def %13
; GFX908-NEXT: [[COPY:%[0-9]+]]:areg_128 = COPY %13
- ; GFX908-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8323081 /* reguse:AReg_128 */, [[COPY]]
+ ; GFX908-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8847369 /* reguse:AReg_128 */, [[COPY]]
; GFX908-NEXT: S_ENDPGM 0
;
; GFX90A-LABEL: name: a_input_output_i128
; GFX90A: bb.0 (%ir-block.0):
- ; GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 8650762 /* regdef:AReg_128_Align2 */, def %11
+ ; GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 9568266 /* regdef:AReg_128_Align2 */, def %11
; GFX90A-NEXT: [[COPY:%[0-9]+]]:areg_128_align2 = COPY %11
- ; GFX90A-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8650761 /* reguse:AReg_128_Align2 */, [[COPY]]
+ ; GFX90A-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 9568265 /* reguse:AReg_128_Align2 */, [[COPY]]
; GFX90A-NEXT: S_ENDPGM 0
%val = call i128 asm sideeffect "; def $0", "=a"()
call void asm sideeffect "; use $0", "a"(i128 %val)
diff --git a/llvm/test/CodeGen/AMDGPU/partial-regcopy-and-spill-missed-at-regalloc.ll b/llvm/test/CodeGen/AMDGPU/partial-regcopy-and-spill-missed-at-regalloc.ll
index 6509d8010dd95..f88b1bfae2c68 100644
--- a/llvm/test/CodeGen/AMDGPU/partial-regcopy-and-spill-missed-at-regalloc.ll
+++ b/llvm/test/CodeGen/AMDGPU/partial-regcopy-and-spill-missed-at-regalloc.ll
@@ -12,7 +12,7 @@ define amdgpu_kernel void @partial_copy(<4 x i32> %arg) #0 {
; REGALLOC-GFX908-NEXT: liveins: $sgpr4_sgpr5
; REGALLOC-GFX908-NEXT: {{ $}}
; REGALLOC-GFX908-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 2424841 /* reguse:AGPR_32 */, undef %6:agpr_32
- ; REGALLOC-GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 7798794 /* regdef:VReg_128 */, def %25
+ ; REGALLOC-GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 7929866 /* regdef:VReg_128 */, def %25
; REGALLOC-GFX908-NEXT: [[COPY:%[0-9]+]]:av_128 = COPY %25
; REGALLOC-GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 3735562 /* regdef:VReg_64 */, def %27
; REGALLOC-GFX908-NEXT: SI_SPILL_AV64_SAVE %27, %stack.0, $sgpr32, 0, implicit $exec :: (store (s64) into %stack.0, align 4, addrspace 5)
@@ -37,7 +37,7 @@ define amdgpu_kernel void @partial_copy(<4 x i32> %arg) #0 {
; PEI-GFX908-NEXT: $sgpr12 = S_ADD_U32 $sgpr12, $sgpr9, implicit-def $scc, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
; PEI-GFX908-NEXT: $sgpr13 = S_ADDC_U32 $sgpr13, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
; PEI-GFX908-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 2424841 /* reguse:AGPR_32 */, undef renamable $agpr0
- ; PEI-GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 7798794 /* regdef:VReg_128 */, def renamable $vgpr0_vgpr1_vgpr2_vgpr3
+ ; PEI-GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 7929866 /* regdef:VReg_128 */, def renamable $vgpr0_vgpr1_vgpr2_vgpr3
; PEI-GFX908-NEXT: renamable $agpr0_agpr1_agpr2_agpr3 = COPY killed renamable $vgpr0_vgpr1_vgpr2_vgpr3, implicit $exec
; PEI-GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 3735562 /* regdef:VReg_64 */, def renamable $vgpr0_vgpr1
; PEI-GFX908-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr12_sgpr13_sgpr14_sgpr15, 0, 0, 0, 0, implicit $exec, implicit-def $vgpr0_vgpr1, implicit $vgpr0_vgpr1 :: (store (s32) into %stack.0, addrspace 5)
@@ -61,7 +61,7 @@ define amdgpu_kernel void @partial_copy(<4 x i32> %arg) #0 {
; REGALLOC-GFX90A-NEXT: liveins: $sgpr4_sgpr5
; REGALLOC-GFX90A-NEXT: {{ $}}
; REGALLOC-GFX90A-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 2424841 /* reguse:AGPR_32 */, undef %6:agpr_32
- ; REGALLOC-GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 7995402 /* regdef:VReg_128_Align2 */, def %23
+ ; REGALLOC-GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 8257546 /* regdef:VReg_128_Align2 */, def %23
; REGALLOC-GFX90A-NEXT: [[COPY:%[0-9]+]]:av_128_align2 = COPY %23
; REGALLOC-GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 3997706 /* regdef:VReg_64_Align2 */, def %21
; REGALLOC-GFX90A-NEXT: [[COPY1:%[0-9]+]]:av_64_align2 = COPY %21
@@ -80,7 +80,7 @@ define amdgpu_kernel void @partial_copy(<4 x i32> %arg) #0 {
; PEI-GFX90A-NEXT: liveins: $sgpr4_sgpr5
; PEI-GFX90A-NEXT: {{ $}}
; PEI-GFX90A-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 2424841 /* reguse:AGPR_32 */, undef renamable $agpr0
- ; PEI-GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 7995402 /* regdef:VReg_128_Align2 */, def renamable $vgpr0_vgpr1_vgpr2_vgpr3
+ ; PEI-GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 8257546 /* regdef:VReg_128_Align2 */, def renamable $vgpr0_vgpr1_vgpr2_vgpr3
; PEI-GFX90A-NEXT: renamable $agpr0_agpr1_agpr2_agpr3 = COPY killed renamable $vgpr0_vgpr1_vgpr2_vgpr3, implicit $exec
; PEI-GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 3997706 /* regdef:VReg_64_Align2 */, def renamable $vgpr2_vgpr3
; PEI-GFX90A-NEXT: GLOBAL_STORE_DWORDX4 undef renamable $vgpr0_vgpr1, killed renamable $agpr0_agpr1_agpr2_agpr3, 0, 0, implicit $exec :: (volatile store (s128) into `ptr addrspace(1) poison`, addrspace 1)
diff --git a/llvm/test/CodeGen/AMDGPU/rewrite-vgpr-mfma-to-agpr-subreg-insert-extract.mir b/llvm/test/CodeGen/AMDGPU/rewrite-vgpr-mfma-to-agpr-subreg-insert-extract.mir
index d7b713aa53b86..0b4e6622b9418 100644
--- a/llvm/test/CodeGen/AMDGPU/rewrite-vgpr-mfma-to-agpr-subreg-insert-extract.mir
+++ b/llvm/test/CodeGen/AMDGPU/rewrite-vgpr-mfma-to-agpr-subreg-insert-extract.mir
@@ -19,7 +19,7 @@ body: |
; CHECK-NEXT: [[V_MFMA_F64_4X4X4F64_e64_:%[0-9]+]]:areg_64_align2 = V_MFMA_F64_4X4X4F64_e64 [[COPY1]], [[COPY2]], [[GLOBAL_LOAD_DWORDX2_]], 0, 0, 0, implicit $mode, implicit $exec
; CHECK-NEXT: undef [[COPY3:%[0-9]+]].sub0_sub1:areg_128_align2 = COPY [[V_MFMA_F64_4X4X4F64_e64_]]
; CHECK-NEXT: [[COPY3:%[0-9]+]].sub2_sub3:areg_128_align2 = IMPLICIT_DEF
- ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8650761 /* reguse:AReg_128_Align2 */, [[COPY3]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 9568265 /* reguse:AReg_128_Align2 */, [[COPY3]]
; CHECK-NEXT: GLOBAL_STORE_DWORDX4 [[COPY]], [[COPY3]], 0, 0, implicit $exec :: (store (s128), addrspace 1)
; CHECK-NEXT: GLOBAL_STORE_DWORDX2 [[COPY]], [[COPY3]].sub2_sub3, 0, 0, implicit $exec :: (store (s128), addrspace 1)
; CHECK-NEXT: SI_RETURN
@@ -30,7 +30,7 @@ body: |
%4:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %3, 0, 0, 0, implicit $mode, implicit $exec
undef %5.sub0_sub1:areg_128_align2 = COPY %4
%5.sub2_sub3 = IMPLICIT_DEF
- INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8650761 /* reguse:AReg_128_Align2 */, %5
+ INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 9568265 /* reguse:AReg_128_Align2 */, %5
GLOBAL_STORE_DWORDX4 %0, %5, 0, 0, implicit $exec :: (store (s128), addrspace 1)
GLOBAL_STORE_DWORDX2 %0, %5.sub2_sub3, 0, 0, implicit $exec :: (store (s128), addrspace 1)
SI_RETURN
@@ -172,7 +172,7 @@ body: |
; CHECK-NEXT: undef [[V_MFMA_F64_4X4X4F64_e64_:%[0-9]+]].sub2_sub3:areg_128_align2 = V_MFMA_F64_4X4X4F64_e64 [[COPY1]], [[COPY2]], [[GLOBAL_LOAD_DWORDX2_]], 0, 0, 0, implicit $mode, implicit $exec
; CHECK-NEXT: undef [[COPY3:%[0-9]+]].sub0_sub1:areg_128_align2 = COPY [[V_MFMA_F64_4X4X4F64_e64_]].sub2_sub3
; CHECK-NEXT: [[COPY3:%[0-9]+]].sub2_sub3:areg_128_align2 = IMPLICIT_DEF
- ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8650761 /* reguse:AReg_128_Align2 */, [[COPY3]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 9568265 /* reguse:AReg_128_Align2 */, [[COPY3]]
; CHECK-NEXT: GLOBAL_STORE_DWORDX4 [[COPY]], [[COPY3]], 0, 0, implicit $exec :: (store (s128), addrspace 1)
; CHECK-NEXT: GLOBAL_STORE_DWORDX2 [[COPY]], [[COPY3]].sub2_sub3, 0, 0, implicit $exec :: (store (s128), addrspace 1)
; CHECK-NEXT: SI_RETURN
@@ -183,7 +183,7 @@ body: |
undef %4.sub2_sub3:vreg_128_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %3, 0, 0, 0, implicit $mode, implicit $exec
undef %5.sub0_sub1:areg_128_align2 = COPY %4.sub2_sub3
%5.sub2_sub3 = IMPLICIT_DEF
- INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8650761 /* reguse:AReg_128_Align2 */, %5
+ INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 9568265 /* reguse:AReg_128_Align2 */, %5
GLOBAL_STORE_DWORDX4 %0, %5, 0, 0, implicit $exec :: (store (s128), addrspace 1)
GLOBAL_STORE_DWORDX2 %0, %5.sub2_sub3, 0, 0, implicit $exec :: (store (s128), addrspace 1)
SI_RETURN
@@ -208,7 +208,7 @@ body: |
; CHECK-NEXT: undef [[V_MFMA_F64_4X4X4F64_vgprcd_e64_:%[0-9]+]].sub2_sub3:vreg_128_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 [[COPY1]], [[COPY2]], [[GLOBAL_LOAD_DWORDX2_]], 0, 0, 0, implicit $mode, implicit $exec
; CHECK-NEXT: undef [[COPY3:%[0-9]+]].sub1:areg_128_align2 = COPY [[V_MFMA_F64_4X4X4F64_vgprcd_e64_]].sub2
; CHECK-NEXT: [[COPY3:%[0-9]+]].sub2_sub3:areg_128_align2 = IMPLICIT_DEF
- ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8650761 /* reguse:AReg_128_Align2 */, [[COPY3]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 9568265 /* reguse:AReg_128_Align2 */, [[COPY3]]
; CHECK-NEXT: GLOBAL_STORE_DWORDX4 [[COPY]], [[COPY3]], 0, 0, implicit $exec :: (store (s128), addrspace 1)
; CHECK-NEXT: GLOBAL_STORE_DWORDX2 [[COPY]], [[COPY3]].sub2_sub3, 0, 0, implicit $exec :: (store (s128), addrspace 1)
; CHECK-NEXT: SI_RETURN
@@ -219,7 +219,7 @@ body: |
undef %4.sub2_sub3:vreg_128_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %3, 0, 0, 0, implicit $mode, implicit $exec
undef %5.sub1:areg_128_align2 = COPY %4.sub2
%5.sub2_sub3 = IMPLICIT_DEF
- INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8650761 /* reguse:AReg_128_Align2 */, %5
+ INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 9568265 /* reguse:AReg_128_Align2 */, %5
GLOBAL_STORE_DWORDX4 %0, %5, 0, 0, implicit $exec :: (store (s128), addrspace 1)
GLOBAL_STORE_DWORDX2 %0, %5.sub2_sub3, 0, 0, implicit $exec :: (store (s128), addrspace 1)
SI_RETURN
diff --git a/llvm/test/CodeGen/AMDGPU/rewrite-vgpr-mfma-to-agpr-subreg-src2-chain.mir b/llvm/test/CodeGen/AMDGPU/rewrite-vgpr-mfma-to-agpr-subreg-src2-chain.mir
index 57f611b4a033e..4c2ea2f3b814a 100644
--- a/llvm/test/CodeGen/AMDGPU/rewrite-vgpr-mfma-to-agpr-subreg-src2-chain.mir
+++ b/llvm/test/CodeGen/AMDGPU/rewrite-vgpr-mfma-to-agpr-subreg-src2-chain.mir
@@ -17,7 +17,7 @@ body: |
; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_:%[0-9]+]]:areg_128_align2 = GLOBAL_LOAD_DWORDX4 [[COPY]], 0, 0, implicit $exec :: (load (s128), addrspace 1)
; CHECK-NEXT: [[V_MFMA_F64_4X4X4F64_e64_:%[0-9]+]]:areg_64_align2 = V_MFMA_F64_4X4X4F64_e64 [[COPY1]], [[COPY2]], [[GLOBAL_LOAD_DWORDX4_]].sub0_sub1, 0, 0, 0, implicit $mode, implicit $exec
; CHECK-NEXT: undef [[COPY3:%[0-9]+]].sub0_sub1:areg_128_align2 = COPY [[V_MFMA_F64_4X4X4F64_e64_]]
- ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8650761 /* reguse:AReg_128_Align2 */, [[COPY3]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 9568265 /* reguse:AReg_128_Align2 */, [[COPY3]]
; CHECK-NEXT: GLOBAL_STORE_DWORDX4 [[COPY]], [[COPY3]], 0, 0, implicit $exec :: (store (s128), addrspace 1)
; CHECK-NEXT: SI_RETURN
%0:vreg_64_align2 = COPY $vgpr4_vgpr5
@@ -26,7 +26,7 @@ body: |
%3:vreg_128_align2 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec :: (load (s128), addrspace 1)
%4:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %3.sub0_sub1, 0, 0, 0, implicit $mode, implicit $exec
undef %5.sub0_sub1:areg_128_align2 = COPY %4
- INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8650761 /* reguse:AReg_128_Align2 */, %5
+ INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 9568265 /* reguse:AReg_128_Align2 */, %5
GLOBAL_STORE_DWORDX4 %0, %5, 0, 0, implicit $exec :: (store (s128), addrspace 1)
SI_RETURN
...
@@ -47,7 +47,7 @@ body: |
; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX4_:%[0-9]+]]:areg_128_align2 = GLOBAL_LOAD_DWORDX4 [[COPY]], 0, 0, implicit $exec :: (load (s128), addrspace 1)
; CHECK-NEXT: [[V_MFMA_F64_4X4X4F64_e64_:%[0-9]+]]:areg_64_align2 = V_MFMA_F64_4X4X4F64_e64 [[COPY1]], [[COPY2]], [[GLOBAL_LOAD_DWORDX4_]].sub2_sub3, 0, 0, 0, implicit $mode, implicit $exec
; CHECK-NEXT: undef [[COPY3:%[0-9]+]].sub0_sub1:areg_128_align2 = COPY [[V_MFMA_F64_4X4X4F64_e64_]]
- ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8650761 /* reguse:AReg_128_Align2 */, [[COPY3]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 9568265 /* reguse:AReg_128_Align2 */, [[COPY3]]
; CHECK-NEXT: GLOBAL_STORE_DWORDX4 [[COPY]], [[COPY3]], 0, 0, implicit $exec :: (store (s128), addrspace 1)
; CHECK-NEXT: SI_RETURN
%0:vreg_64_align2 = COPY $vgpr4_vgpr5
@@ -56,7 +56,7 @@ body: |
%3:vreg_128_align2 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec :: (load (s128), addrspace 1)
%4:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %3.sub2_sub3, 0, 0, 0, implicit $mode, implicit $exec
undef %5.sub0_sub1:areg_128_align2 = COPY %4
- INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8650761 /* reguse:AReg_128_Align2 */, %5
+ INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 9568265 /* reguse:AReg_128_Align2 */, %5
GLOBAL_STORE_DWORDX4 %0, %5, 0, 0, implicit $exec :: (store (s128), addrspace 1)
SI_RETURN
...
@@ -151,7 +151,7 @@ body: |
; CHECK-NEXT: dead %other_use:vreg_64_align2 = COPY [[V_MFMA_F64_4X4X4F64_e64_1]].sub0_sub1
; CHECK-NEXT: [[V_MFMA_F64_4X4X4F64_e64_2:%[0-9]+]]:areg_64_align2 = V_MFMA_F64_4X4X4F64_e64 [[COPY1]], [[COPY2]], [[V_MFMA_F64_4X4X4F64_e64_1]].sub0_sub1, 0, 0, 0, implicit $mode, implicit $exec
; CHECK-NEXT: undef [[COPY3:%[0-9]+]].sub0_sub1:areg_128_align2 = COPY [[V_MFMA_F64_4X4X4F64_e64_2]]
- ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8650761 /* reguse:AReg_128_Align2 */, [[COPY3]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 9568265 /* reguse:AReg_128_Align2 */, [[COPY3]]
; CHECK-NEXT: GLOBAL_STORE_DWORDX4 [[COPY]], [[COPY3]], 0, 0, implicit $exec :: (store (s128), addrspace 1)
; CHECK-NEXT: SI_RETURN
%0:vreg_64_align2 = COPY $vgpr4_vgpr5
@@ -163,7 +163,7 @@ body: |
%other_use:vreg_64_align2 = COPY %5.sub0_sub1
%6:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %5.sub0_sub1, 0, 0, 0, implicit $mode, implicit $exec
undef %8.sub0_sub1:areg_128_align2 = COPY %6
- INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8650761 /* reguse:AReg_128_Align2 */, %8:areg_128_align2
+ INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 9568265 /* reguse:AReg_128_Align2 */, %8:areg_128_align2
GLOBAL_STORE_DWORDX4 %0, %8, 0, 0, implicit $exec :: (store (s128), addrspace 1)
SI_RETURN
@@ -231,7 +231,7 @@ body: |
; CHECK-NEXT: dead %other_use1:vreg_64_align2 = COPY [[V_MFMA_F64_4X4X4F64_e64_]].sub2_sub3
; CHECK-NEXT: dead %other_use2:vreg_64 = COPY [[V_MFMA_F64_4X4X4F64_e64_]].sub1_sub2
; CHECK-NEXT: [[COPY3:%[0-9]+]]:areg_128_align2 = COPY [[V_MFMA_F64_4X4X4F64_e64_]]
- ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8650761 /* reguse:AReg_128_Align2 */, [[COPY3]]
+ ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 9568265 /* reguse:AReg_128_Align2 */, [[COPY3]]
; CHECK-NEXT: GLOBAL_STORE_DWORDX4 [[COPY]], [[COPY3]], 0, 0, implicit $exec :: (store (s128), addrspace 1)
; CHECK-NEXT: SI_RETURN
%0:vreg_64_align2 = COPY $vgpr4_vgpr5
@@ -245,7 +245,7 @@ body: |
%other_use1:vreg_64_align2 = COPY %4.sub2_sub3
%other_use2:vreg_64 = COPY %4.sub1_sub2
%6:areg_128_align2 = COPY %4
- INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 8650761 /* reguse:AReg_128_Align2 */, %6:areg_128_align2
+ INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 9568265 /* reguse:AReg_128_Align2 */, %6:areg_128_align2
GLOBAL_STORE_DWORDX4 %0, %6, 0, 0, implicit $exec :: (store (s128), addrspace 1)
SI_RETURN
...
More information about the llvm-commits
mailing list