[llvm] update_mir_test_checks.py: match undef vreg subreg definitions (PR #66627)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Sep 18 03:33:28 PDT 2023
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-x86
<details>
<summary>Changes</summary>
Following on from D139466 which added support for dead vreg defs, this
patch adds support for "undef" defs of subregs.
Use this to regenerate checks for amx-greedy-ra-spill-shape.ll which
previously required manual tweaks to the autogenerated checks to fix an
EXPENSIVE_CHECKS failure; see commit
8b7c1fbd9647a5a6ef246a6b5b2543ea0f5a2337
---
Patch is 25.84 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/66627.diff
4 Files Affected:
- (modified) llvm/test/CodeGen/X86/AMX/amx-greedy-ra-spill-shape.ll (+92-92)
- (modified) llvm/test/tools/UpdateTestChecks/update_mir_test_checks/Inputs/x86-dead-def.mir (+3-5)
- (modified) llvm/test/tools/UpdateTestChecks/update_mir_test_checks/Inputs/x86-dead-def.mir.expected (+6-6)
- (modified) llvm/utils/update_mir_test_checks.py (+2-2)
``````````diff
diff --git a/llvm/test/CodeGen/X86/AMX/amx-greedy-ra-spill-shape.ll b/llvm/test/CodeGen/X86/AMX/amx-greedy-ra-spill-shape.ll
index 044ab0111fd0cad..6d6f9aca7188da3 100644
--- a/llvm/test/CodeGen/X86/AMX/amx-greedy-ra-spill-shape.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-greedy-ra-spill-shape.ll
@@ -1,8 +1,8 @@
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx512f -verify-machineinstrs -stop-before virtregrewriter | FileCheck %s
+; Check LEA64_32r register is split to COPY10
define void @foo(i32 %M, i32 %N, i32 %K, ptr %A, ptr %B_rcr4, ptr %C, i32 %c_row_from, i32 %c_row_to, i32 %c_row_tile, i32 %c_col_from, i32 %c_col_to, i32 %c_col_tile) {
- ; Check LEA64_32r register is split to COPY10
; CHECK-LABEL: name: foo
; CHECK: bb.0.entry:
; CHECK-NEXT: successors: %bb.1(0x40000000), %bb.4(0x40000000)
@@ -11,16 +11,16 @@ define void @foo(i32 %M, i32 %N, i32 %K, ptr %A, ptr %B_rcr4, ptr %C, i32 %c_row
; CHECK-NEXT: [[COPY:%[0-9]+]]:gr64 = COPY $r9
; CHECK-NEXT: [[COPY1:%[0-9]+]]:gr64 = COPY $r8
; CHECK-NEXT: MOV64mr %stack.1, 1, $noreg, 0, $noreg, $rcx :: (store (s64) into %stack.1)
- ; CHECK-NEXT: undef [[COPY83:%[0-9]+]].sub_32bit:gr64_with_sub_8bit = COPY $edx
- ; CHECK-NEXT: undef [[COPY85:%[0-9]+]].sub_32bit:gr64_nosp = COPY $esi
+ ; CHECK-NEXT: undef [[COPY2:%[0-9]+]].sub_32bit:gr64_with_sub_8bit = COPY $edx
+ ; CHECK-NEXT: undef [[COPY3:%[0-9]+]].sub_32bit:gr64_nosp = COPY $esi
; CHECK-NEXT: [[AVX512_512_SET0_:%[0-9]+]]:vr512 = AVX512_512_SET0
; CHECK-NEXT: VMOVUPSZmr %stack.0, 1, $noreg, 0, $noreg, [[AVX512_512_SET0_]] :: (store (s512) into %stack.0, align 4)
; CHECK-NEXT: MOV8mi %stack.0, 1, $noreg, 0, $noreg, 1 :: (store (s512) into %stack.0, align 4)
; CHECK-NEXT: [[MOV32rm:%[0-9]+]]:gr32 = MOV32rm %fixed-stack.4, 1, $noreg, 0, $noreg :: (load (s32) from %fixed-stack.4, align 8)
; CHECK-NEXT: [[MOV32rm1:%[0-9]+]]:gr32 = MOV32rm %fixed-stack.5, 1, $noreg, 0, $noreg :: (load (s32) from %fixed-stack.5, align 16)
- ; CHECK-NEXT: [[LEA64_32r:%[0-9]+]]:gr32 = LEA64_32r [[COPY83]], 1, $noreg, 63, $noreg
- ; CHECK-NEXT: TEST32rr [[COPY83]].sub_32bit, [[COPY83]].sub_32bit, implicit-def $eflags
- ; CHECK-NEXT: [[CMOV32rr:%[0-9]+]]:gr32 = CMOV32rr [[CMOV32rr]], [[COPY83]].sub_32bit, 9, implicit $eflags
+ ; CHECK-NEXT: [[LEA64_32r:%[0-9]+]]:gr32 = LEA64_32r [[COPY2]], 1, $noreg, 63, $noreg
+ ; CHECK-NEXT: TEST32rr [[COPY2]].sub_32bit, [[COPY2]].sub_32bit, implicit-def $eflags
+ ; CHECK-NEXT: [[LEA64_32r:%[0-9]+]]:gr32 = CMOV32rr [[LEA64_32r]], [[COPY2]].sub_32bit, 9, implicit $eflags
; CHECK-NEXT: CMP32rr [[MOV32rm1]], [[MOV32rm]], implicit-def $eflags
; CHECK-NEXT: JCC_1 %bb.4, 13, implicit $eflags
; CHECK-NEXT: JMP_1 %bb.1
@@ -28,64 +28,64 @@ define void @foo(i32 %M, i32 %N, i32 %K, ptr %A, ptr %B_rcr4, ptr %C, i32 %c_row
; CHECK-NEXT: bb.1.for.cond14.preheader.lr.ph:
; CHECK-NEXT: successors: %bb.2(0x80000000)
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: undef [[MOV89:%[0-9]+]].sub_32bit:gr64_nosp = MOV32rm %fixed-stack.0, 1, $noreg, 0, $noreg :: (load (s32) from %fixed-stack.0, align 8)
- ; CHECK-NEXT: MOV16mr %stack.0, 1, $noreg, 16, $noreg, [[MOV89]].sub_16bit :: (store (s512) into %stack.0 + 16, align 4)
- ; CHECK-NEXT: [[MOV32rm2:%[0-9]+]]:gr32 = MOV32rm %fixed-stack.3, 1, $noreg, 0, $noreg :: (load (s32) from %fixed-stack.3, align 16)
- ; CHECK-NEXT: MOV8mr %stack.0, 1, $noreg, 49, $noreg, [[MOV32rm2]].sub_8bit :: (store (s512) into %stack.0 + 49, align 1, basealign 4)
- ; CHECK-NEXT: MOV8mr %stack.0, 1, $noreg, 48, $noreg, [[MOV32rm2]].sub_8bit :: (store (s512) into %stack.0 + 48, align 4)
- ; CHECK-NEXT: [[AND32ri_:%[0-9]+]]:gr32 = AND32ri [[AND32ri_]], -64, implicit-def dead $eflags
- ; CHECK-NEXT: [[COPY2:%[0-9]+]]:gr32 = COPY [[COPY83]].sub_32bit
- ; CHECK-NEXT: MOV16mr %stack.0, 1, $noreg, 18, $noreg, [[COPY2]].sub_16bit :: (store (s512) into %stack.0 + 18, align 2, basealign 4)
- ; CHECK-NEXT: [[SUB32rr:%[0-9]+]]:gr32 = SUB32rr [[SUB32rr]], [[AND32ri_]], implicit-def dead $eflags
- ; CHECK-NEXT: MOV16mr %stack.0, 1, $noreg, 18, $noreg, [[SUB32rr]].sub_16bit :: (store (s512) into %stack.0 + 18, align 2, basealign 4)
- ; CHECK-NEXT: [[MOVZX32rr16_:%[0-9]+]]:gr32 = MOVZX32rr16 [[SUB32rr]].sub_16bit
+ ; CHECK-NEXT: undef [[MOV32rm2:%[0-9]+]].sub_32bit:gr64_nosp = MOV32rm %fixed-stack.0, 1, $noreg, 0, $noreg :: (load (s32) from %fixed-stack.0, align 8)
+ ; CHECK-NEXT: MOV16mr %stack.0, 1, $noreg, 16, $noreg, [[MOV32rm2]].sub_16bit :: (store (s512) into %stack.0 + 16, align 4)
+ ; CHECK-NEXT: [[MOV32rm3:%[0-9]+]]:gr32 = MOV32rm %fixed-stack.3, 1, $noreg, 0, $noreg :: (load (s32) from %fixed-stack.3, align 16)
+ ; CHECK-NEXT: MOV8mr %stack.0, 1, $noreg, 49, $noreg, [[MOV32rm3]].sub_8bit :: (store (s512) into %stack.0 + 49, align 1, basealign 4)
+ ; CHECK-NEXT: MOV8mr %stack.0, 1, $noreg, 48, $noreg, [[MOV32rm3]].sub_8bit :: (store (s512) into %stack.0 + 48, align 4)
+ ; CHECK-NEXT: [[LEA64_32r:%[0-9]+]]:gr32 = AND32ri [[LEA64_32r]], -64, implicit-def dead $eflags
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:gr32 = COPY [[COPY2]].sub_32bit
+ ; CHECK-NEXT: MOV16mr %stack.0, 1, $noreg, 18, $noreg, [[COPY4]].sub_16bit :: (store (s512) into %stack.0 + 18, align 2, basealign 4)
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:gr32 = SUB32rr [[COPY4]], [[LEA64_32r]], implicit-def dead $eflags
+ ; CHECK-NEXT: MOV16mr %stack.0, 1, $noreg, 18, $noreg, [[COPY4]].sub_16bit :: (store (s512) into %stack.0 + 18, align 2, basealign 4)
+ ; CHECK-NEXT: [[MOVZX32rr16_:%[0-9]+]]:gr32 = MOVZX32rr16 [[COPY4]].sub_16bit
; CHECK-NEXT: MOV8mr %stack.0, 1, $noreg, 50, $noreg, [[MOVZX32rr16_]].sub_8bit :: (store (s512) into %stack.0 + 50, align 2, basealign 4)
- ; CHECK-NEXT: [[SHR32ri:%[0-9]+]]:gr32 = SHR32ri [[SHR32ri]], 2, implicit-def dead $eflags
- ; CHECK-NEXT: MOV32mr %stack.2, 1, $noreg, 0, $noreg, [[SHR32ri]] :: (store (s32) into %stack.2)
- ; CHECK-NEXT: MOV8mr %stack.0, 1, $noreg, 50, $noreg, [[SHR32ri]].sub_8bit :: (store (s512) into %stack.0 + 50, align 2, basealign 4)
- ; CHECK-NEXT: [[LEA64_32r:%[0-9]+]]:gr32 = LEA64_32r $noreg, 4, [[MOV89]], 0, $noreg
- ; CHECK-NEXT: MOV16mr %stack.0, 1, $noreg, 20, $noreg, [[LEA64_32r]].sub_16bit :: (store (s512) into %stack.0 + 20, align 4)
+ ; CHECK-NEXT: [[MOVZX32rr16_:%[0-9]+]]:gr32 = SHR32ri [[MOVZX32rr16_]], 2, implicit-def dead $eflags
+ ; CHECK-NEXT: MOV32mr %stack.2, 1, $noreg, 0, $noreg, [[MOVZX32rr16_]] :: (store (s32) into %stack.2)
+ ; CHECK-NEXT: MOV8mr %stack.0, 1, $noreg, 50, $noreg, [[MOVZX32rr16_]].sub_8bit :: (store (s512) into %stack.0 + 50, align 2, basealign 4)
+ ; CHECK-NEXT: [[LEA64_32r1:%[0-9]+]]:gr32 = LEA64_32r $noreg, 4, [[MOV32rm2]], 0, $noreg
+ ; CHECK-NEXT: MOV16mr %stack.0, 1, $noreg, 20, $noreg, [[LEA64_32r1]].sub_16bit :: (store (s512) into %stack.0 + 20, align 4)
; CHECK-NEXT: PLDTILECFGV %stack.0, 1, $noreg, 0, $noreg, implicit-def dead $tmm0, implicit-def dead $tmm1, implicit-def dead $tmm2, implicit-def dead $tmm3, implicit-def dead $tmm4, implicit-def dead $tmm5, implicit-def dead $tmm6, implicit-def dead $tmm7 :: (load (s512) from %stack.0, align 4)
- ; CHECK-NEXT: [[MOVSX64rr32_:%[0-9]+]]:gr64_nosp = MOVSX64rr32 [[COPY83]].sub_32bit
- ; CHECK-NEXT: [[COPY83]].sub_32bit:gr64_with_sub_8bit = SUB32rr [[COPY83]].sub_32bit, [[SUB32rr]], implicit-def dead $eflags
- ; CHECK-NEXT: undef %14.sub_32bit:gr64_with_sub_8bit = MOVZX32rr16 [[COPY83]].sub_16bit
- ; CHECK-NEXT: ADD64mr %stack.1, 1, $noreg, 0, $noreg, %14, implicit-def dead $eflags :: (store (s64) into %stack.1)
- ; CHECK-NEXT: undef %61.sub_32bit:gr64_with_sub_8bit = COPY %14.sub_32bit
- ; CHECK-NEXT: %61.sub_32bit:gr64_with_sub_8bit = IMUL32rr %61.sub_32bit, [[COPY85]].sub_32bit, implicit-def dead $eflags
- ; CHECK-NEXT: [[LEA64_32r1:%[0-9]+]]:gr32 = LEA64_32r $noreg, 4, [[COPY85]], 0, $noreg
- ; CHECK-NEXT: [[MOVSX64rr32_1:%[0-9]+]]:gr64 = MOVSX64rr32 [[LEA64_32r1]]
+ ; CHECK-NEXT: [[MOVSX64rr32_:%[0-9]+]]:gr64_nosp = MOVSX64rr32 [[COPY2]].sub_32bit
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]].sub_32bit:gr64_with_sub_8bit = SUB32rr [[COPY2]].sub_32bit, [[COPY4]], implicit-def dead $eflags
+ ; CHECK-NEXT: undef [[MOVZX32rr16_1:%[0-9]+]].sub_32bit:gr64_with_sub_8bit = MOVZX32rr16 [[COPY2]].sub_16bit
+ ; CHECK-NEXT: ADD64mr %stack.1, 1, $noreg, 0, $noreg, [[MOVZX32rr16_1]], implicit-def dead $eflags :: (store (s64) into %stack.1)
+ ; CHECK-NEXT: undef [[COPY5:%[0-9]+]].sub_32bit:gr64_with_sub_8bit = COPY [[MOVZX32rr16_1]].sub_32bit
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]].sub_32bit:gr64_with_sub_8bit = IMUL32rr [[COPY5]].sub_32bit, [[COPY3]].sub_32bit, implicit-def dead $eflags
+ ; CHECK-NEXT: [[LEA64_32r2:%[0-9]+]]:gr32 = LEA64_32r $noreg, 4, [[COPY3]], 0, $noreg
+ ; CHECK-NEXT: [[MOVSX64rr32_1:%[0-9]+]]:gr64 = MOVSX64rr32 [[LEA64_32r2]]
; CHECK-NEXT: MOV64mr %stack.3, 1, $noreg, 0, $noreg, [[MOVSX64rr32_1]] :: (store (s64) into %stack.3)
- ; CHECK-NEXT: [[MOVSX64rr32_2:%[0-9]+]]:gr64_nosp = MOVSX64rr32 [[COPY85]].sub_32bit
+ ; CHECK-NEXT: [[MOVSX64rr32_2:%[0-9]+]]:gr64_nosp = MOVSX64rr32 [[COPY3]].sub_32bit
; CHECK-NEXT: [[MOVSX64rm32_:%[0-9]+]]:gr64_nosp = MOVSX64rm32 %fixed-stack.2, 1, $noreg, 0, $noreg :: (load (s32) from %fixed-stack.2, align 8)
- ; CHECK-NEXT: [[MOVSX64rr32_3:%[0-9]+]]:gr64_nosp = MOVSX64rr32 [[MOV89]].sub_32bit
+ ; CHECK-NEXT: [[MOVSX64rr32_3:%[0-9]+]]:gr64_nosp = MOVSX64rr32 [[MOV32rm2]].sub_32bit
; CHECK-NEXT: [[MOVSX64rm32_1:%[0-9]+]]:gr64 = MOVSX64rm32 %fixed-stack.1, 1, $noreg, 0, $noreg :: (load (s32) from %fixed-stack.1, align 16)
; CHECK-NEXT: MOV64mr %stack.5, 1, $noreg, 0, $noreg, [[MOVSX64rm32_1]] :: (store (s64) into %stack.5)
; CHECK-NEXT: [[MOVSX64rr32_4:%[0-9]+]]:gr64 = MOVSX64rr32 [[MOV32rm1]]
- ; CHECK-NEXT: [[COPY2:%[0-9]+]]:gr32 = COPY [[MOV32rm2]]
- ; CHECK-NEXT: [[MOVSX64rr32_5:%[0-9]+]]:gr64 = MOVSX64rr32 [[COPY2]]
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:gr32 = COPY [[MOV32rm3]]
+ ; CHECK-NEXT: [[MOVSX64rr32_5:%[0-9]+]]:gr64 = MOVSX64rr32 [[COPY6]]
; CHECK-NEXT: [[MOVSX64rr32_6:%[0-9]+]]:gr64 = MOVSX64rr32 [[MOV32rm]]
; CHECK-NEXT: MOV64mr %stack.8, 1, $noreg, 0, $noreg, [[MOVSX64rr32_6]] :: (store (s64) into %stack.8)
; CHECK-NEXT: MOV64mr %stack.6, 1, $noreg, 0, $noreg, [[MOVSX64rr32_4]] :: (store (s64) into %stack.6)
- ; CHECK-NEXT: [[COPY3:%[0-9]+]]:gr64_nosp = COPY [[MOVSX64rr32_4]]
- ; CHECK-NEXT: [[IMUL64rr:%[0-9]+]]:gr64_nosp = IMUL64rr [[IMUL64rr]], [[MOVSX64rr32_2]], implicit-def dead $eflags
- ; CHECK-NEXT: [[ADD64rr:%[0-9]+]]:gr64_nosp = ADD64rr [[ADD64rr]], [[MOVSX64rm32_]], implicit-def dead $eflags
- ; CHECK-NEXT: [[LEA64r:%[0-9]+]]:gr64 = LEA64r [[COPY]], 4, [[ADD64rr]], 0, $noreg
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:gr64_nosp = COPY [[MOVSX64rr32_4]]
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:gr64_nosp = IMUL64rr [[COPY7]], [[MOVSX64rr32_2]], implicit-def dead $eflags
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:gr64_nosp = ADD64rr [[COPY7]], [[MOVSX64rm32_]], implicit-def dead $eflags
+ ; CHECK-NEXT: [[LEA64r:%[0-9]+]]:gr64 = LEA64r [[COPY]], 4, [[COPY7]], 0, $noreg
; CHECK-NEXT: MOV64mr %stack.9, 1, $noreg, 0, $noreg, [[LEA64r]] :: (store (s64) into %stack.9)
; CHECK-NEXT: MOV64mr %stack.7, 1, $noreg, 0, $noreg, [[MOVSX64rr32_5]] :: (store (s64) into %stack.7)
- ; CHECK-NEXT: [[COPY3:%[0-9]+]]:gr64 = COPY [[MOVSX64rr32_5]]
- ; CHECK-NEXT: [[IMUL64rr:%[0-9]+]]:gr64 = IMUL64rr [[IMUL64rr]], [[MOVSX64rr32_2]], implicit-def dead $eflags
- ; CHECK-NEXT: [[SHL64ri:%[0-9]+]]:gr64 = SHL64ri [[SHL64ri]], 2, implicit-def dead $eflags
- ; CHECK-NEXT: MOV64mr %stack.10, 1, $noreg, 0, $noreg, [[SHL64ri]] :: (store (s64) into %stack.10)
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:gr64 = COPY [[MOVSX64rr32_5]]
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:gr64 = IMUL64rr [[COPY8]], [[MOVSX64rr32_2]], implicit-def dead $eflags
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:gr64 = SHL64ri [[COPY8]], 2, implicit-def dead $eflags
+ ; CHECK-NEXT: MOV64mr %stack.10, 1, $noreg, 0, $noreg, [[COPY8]] :: (store (s64) into %stack.10)
; CHECK-NEXT: [[LEA64r1:%[0-9]+]]:gr64 = LEA64r $noreg, 4, [[MOVSX64rr32_3]], 0, $noreg
; CHECK-NEXT: MOV64mr %stack.4, 1, $noreg, 0, $noreg, [[MOVSX64rm32_]] :: (store (s64) into %stack.4)
- ; CHECK-NEXT: [[LEA64_32r2:%[0-9]+]]:gr32 = LEA64_32r %61, 4, [[MOVSX64rm32_]], 0, $noreg
- ; CHECK-NEXT: MOV32mr %stack.11, 1, $noreg, 0, $noreg, [[LEA64_32r2]] :: (store (s32) into %stack.11)
+ ; CHECK-NEXT: [[LEA64_32r3:%[0-9]+]]:gr32 = LEA64_32r [[COPY5]], 4, [[MOVSX64rm32_]], 0, $noreg
+ ; CHECK-NEXT: MOV32mr %stack.11, 1, $noreg, 0, $noreg, [[LEA64_32r3]] :: (store (s32) into %stack.11)
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.2.for.cond14.preheader:
; CHECK-NEXT: successors: %bb.3(0x40000000), %bb.5(0x40000000)
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: [[MOV32rm3:%[0-9]+]]:gr32 = MOV32rm %fixed-stack.2, 1, $noreg, 0, $noreg :: (load (s32) from %fixed-stack.2, align 8)
- ; CHECK-NEXT: CMP32rm [[MOV32rm3]], %fixed-stack.1, 1, $noreg, 0, $noreg, implicit-def $eflags :: (load (s32) from %fixed-stack.1, align 16)
+ ; CHECK-NEXT: [[MOV32rm4:%[0-9]+]]:gr32 = MOV32rm %fixed-stack.2, 1, $noreg, 0, $noreg :: (load (s32) from %fixed-stack.2, align 8)
+ ; CHECK-NEXT: CMP32rm [[MOV32rm4]], %fixed-stack.1, 1, $noreg, 0, $noreg, implicit-def $eflags :: (load (s32) from %fixed-stack.1, align 16)
; CHECK-NEXT: JCC_1 %bb.5, 13, implicit $eflags
; CHECK-NEXT: JMP_1 %bb.3
; CHECK-NEXT: {{ $}}
@@ -93,13 +93,13 @@ define void @foo(i32 %M, i32 %N, i32 %K, ptr %A, ptr %B_rcr4, ptr %C, i32 %c_row
; CHECK-NEXT: successors: %bb.6(0x80000000)
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[MOV64rm:%[0-9]+]]:gr64 = MOV64rm %stack.6, 1, $noreg, 0, $noreg :: (load (s64) from %stack.6)
- ; CHECK-NEXT: [[IMUL64rr:%[0-9]+]]:gr64 = nsw IMUL64rr [[IMUL64rr]], [[MOVSX64rr32_]], implicit-def dead $eflags
- ; CHECK-NEXT: [[ADD64rm:%[0-9]+]]:gr64 = ADD64rm [[ADD64rm]], %stack.1, 1, $noreg, 0, $noreg, implicit-def dead $eflags :: (load (s64) from %stack.1)
- ; CHECK-NEXT: MOV64mr %stack.12, 1, $noreg, 0, $noreg, [[ADD64rm]] :: (store (s64) into %stack.12)
- ; CHECK-NEXT: [[MOV32rm4:%[0-9]+]]:gr32 = MOV32rm %stack.11, 1, $noreg, 0, $noreg :: (load (s32) from %stack.11)
- ; CHECK-NEXT: undef %68.sub_32bit:gr64_nosp = COPY [[MOV32rm4]]
- ; CHECK-NEXT: [[MOV64rm:%[0-9]+]]:gr64 = MOV64rm %stack.9, 1, $noreg, 0, $noreg :: (load (s64) from %stack.9)
- ; CHECK-NEXT: [[MOV64rm1:%[0-9]+]]:gr64 = MOV64rm %stack.4, 1, $noreg, 0, $noreg :: (load (s64) from %stack.4)
+ ; CHECK-NEXT: [[MOV64rm:%[0-9]+]]:gr64 = nsw IMUL64rr [[MOV64rm]], [[MOVSX64rr32_]], implicit-def dead $eflags
+ ; CHECK-NEXT: [[MOV64rm:%[0-9]+]]:gr64 = ADD64rm [[MOV64rm]], %stack.1, 1, $noreg, 0, $noreg, implicit-def dead $eflags :: (load (s64) from %stack.1)
+ ; CHECK-NEXT: MOV64mr %stack.12, 1, $noreg, 0, $noreg, [[MOV64rm]] :: (store (s64) into %stack.12)
+ ; CHECK-NEXT: [[MOV32rm5:%[0-9]+]]:gr32 = MOV32rm %stack.11, 1, $noreg, 0, $noreg :: (load (s32) from %stack.11)
+ ; CHECK-NEXT: undef [[COPY9:%[0-9]+]].sub_32bit:gr64_nosp = COPY [[MOV32rm5]]
+ ; CHECK-NEXT: [[MOV64rm1:%[0-9]+]]:gr64 = MOV64rm %stack.9, 1, $noreg, 0, $noreg :: (load (s64) from %stack.9)
+ ; CHECK-NEXT: [[MOV64rm2:%[0-9]+]]:gr64 = MOV64rm %stack.4, 1, $noreg, 0, $noreg :: (load (s64) from %stack.4)
; CHECK-NEXT: JMP_1 %bb.6
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.4.for.cond.cleanup:
@@ -108,51 +108,51 @@ define void @foo(i32 %M, i32 %N, i32 %K, ptr %A, ptr %B_rcr4, ptr %C, i32 %c_row
; CHECK-NEXT: bb.5.for.cond.cleanup16:
; CHECK-NEXT: successors: %bb.2(0x7c000000), %bb.4(0x04000000)
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: [[MOV64rm2:%[0-9]+]]:gr64 = MOV64rm %stack.6, 1, $noreg, 0, $noreg :: (load (s64) from %stack.6)
- ; CHECK-NEXT: [[ADD64rm1:%[0-9]+]]:gr64 = ADD64rm [[ADD64rm1]], %stack.7, 1, $noreg, 0, $noreg, implicit-def dead $eflags :: (load (s64) from %stack.7)
- ; CHECK-NEXT: [[MOV64rm2:%[0-9]+]]:gr64 = MOV64rm %stack.10, 1, $noreg, 0, $noreg :: (load (s64) from %stack.10)
- ; CHECK-NEXT: ADD64mr %stack.9, 1, $noreg, 0, $noreg, [[MOV64rm2]], implicit-def dead $eflags :: (store (s64) into %stack.9)
- ; CHECK-NEXT: MOV64mr %stack.6, 1, $noreg, 0, $noreg, [[ADD64rm1]] :: (store (s64) into %stack.6)
- ; CHECK-NEXT: CMP64rm [[ADD64rm1]], %stack.8, 1, $noreg, 0, $noreg, implicit-def $eflags :: (load (s64) from %stack.8)
+ ; CHECK-NEXT: [[MOV64rm3:%[0-9]+]]:gr64 = MOV64rm %stack.6, 1, $noreg, 0, $noreg :: (load (s64) from %stack.6)
+ ; CHECK-NEXT: [[MOV64rm3:%[0-9]+]]:gr64 = ADD64rm [[MOV64rm3]], %stack.7, 1, $noreg, 0, $noreg, implicit-def dead $eflags :: (load (s64) from %stack.7)
+ ; CHECK-NEXT: [[MOV64rm4:%[0-9]+]]:gr64 = MOV64rm %stack.10, 1, $noreg, 0, $noreg :: (load (s64) from %stack.10)
+ ; CHECK-NEXT: ADD64mr %stack.9, 1, $noreg, 0, $noreg, [[MOV64rm4]], implicit-def dead $eflags :: (store (s64) into %stack.9)
+ ; CHECK-NEXT: MOV64mr %stack.6, 1, $noreg, 0, $noreg, [[MOV64rm3]] :: (store (s64) into %stack.6)
+ ; CHECK-NEXT: CMP64rm [[MOV64rm3]], %stack.8, 1, $noreg, 0, $noreg, implicit-def $eflags :: (load (s64) from %stack.8)
; CHECK-NEXT: JCC_1 %bb.2, 12, implicit $eflags
; CHECK-NEXT: JMP_1 %bb.4
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.6.for.body17:
; CHECK-NEXT: successors: %bb.6(0x7c000000), %bb.5(0x04000000)
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: [[PTILEZEROV:%[0-9]+]]:tile = PTILEZEROV [[COPY2]].sub_16bit, [[MOV89]].sub_16bit
- ; CHECK-NEXT: [[MOV64rm3:%[0-9]+]]:gr64 = MOV64rm %stack.12, 1, $noreg, 0, $noreg :: (load (s64) from %stack.12)
- ; CHECK-NEXT: [[PTILELOADDV:%[0-9]+]]:tile = PTILELOADDV [[COPY2]].sub_16bit, [[SUB32rr]].sub_16bit, [[MOV64rm3]], 1, [[MOVSX64rr32_]], 0, $noreg
- ; CHECK-NEXT: [[MOVSX64rr32_7:%[0-9]+]]:gr64_nosp = MOVSX64rr32 [[MOVSX64rr32_7]].sub_32bit
- ; CHECK-NEXT: [[COPY3:%[0-9]+]]:gr32 = COPY [[LEA64_32r]]
- ; CHECK-NEXT: [[COPY4:%[0-9]+]]:gr64 = COPY [[LEA64r1]]
- ; CHECK-NEXT: [[COPY5:%[0-9]+]]:gr32 = COPY [[SUB32rr]]
- ; CHECK-NEXT: [[COPY6:%[0-9]+]]:gr32 = COPY [[COPY2]]
- ; CHECK-NEXT: [[COPY7:%[0-9]+]]:gr64 = COPY [[MOVSX64rr32_3]]
- ; CHECK-NEXT: [[COPY8:%[0-9]+]]:gr64 = COPY [[MOVSX64rr32_2]]
- ; CHECK-NEXT: [[COPY9:%[0-9]+]]:gr64 = COPY [[MOVSX64rr32_]]
- ; CHECK-NEXT: [[COPY10:%[0-9]+]]:gr64 = COPY [[MOV89]]
- ; CHECK-NEXT: [[COPY11:%[0-9]+]]:gr64 = COPY [[COPY1]]
- ; CHECK-NEXT: [[LEA64r2:%[0-9]+]]:gr64 = LEA64r [[COPY11]], 1, [[MOVSX64rr32_7]], 0, $noreg
- ; CHECK-NEXT: [[MOV32rm5:%[0-9]+]]:gr32 = MOV32rm %stack.2, 1, $noreg, 0, $noreg :: (load (s32) from %stack.2)
- ; CHECK-NEXT: [[MOV64rm4:%[0-9]+]]:gr64_nosp = MOV64rm %stack.3, 1, $noreg, 0, $noreg :: (load (s64) from %stack.3)
- ; CHECK-NEXT: [[PTILELOADDV1:%[0-9]+]]:tile = PTILELOADDV [[MOV32rm5]].sub_16bit, [[COPY3]].sub_16bit, [[LEA64r2]], 1, [[MOV64rm4]], 0, $noreg
- ; CHECK-NEXT: [[COPY12:%[0-9]+]]:gr64 = COPY [[COPY11]]
- ; CHECK-NEXT: [[COPY12:%[0-9]+]]:gr64_nosp = COPY [[COPY10]]
- ; CHECK-NEXT: [[COPY13:%[0-9]+]]:gr64_nosp = COPY [[COPY9]]
- ; CHECK-NEXT: [[COPY14:%[0-9]+]]:gr64_nosp = COPY [[COPY8]]
- ; CHECK-NEXT: [[COPY15:%[0-9]+]]:gr64_nosp = COPY [[COPY7]]
- ; CHECK-NEXT: [[COPY16:%[0-9]+]]:gr32 = COPY [[COPY6]]
- ; CHECK-NEXT: [[COPY19:%[0-9]+]]:gr32 = COPY [[COPY5]]
- ; CHECK-NEXT: [[COPY17:%[0-9]+]]:gr64 = COPY [[COPY4]]
- ; CHECK-NEXT: [[MOV64rm5:%[0-9]+]]:gr64 = MOV64rm %stack.5, 1, $noreg, 0, $noreg :: (load (s64) from %stack.5)
- ; CHECK-NEXT: [[COPY18:%[0-9]+]]:gr32 = COPY [[COPY3]]
- ; CHECK-NEXT: [[PTDPBSSDV:%[0-9]+]]:tile = PTDPBSSDV [[COPY16]].sub_16bit, [[COPY18]].sub_16bit, [[COPY19]].sub_16bit, [[PTDPBSSDV]], [[PTILELOADDV]], [[PTILELOADDV1]]
- ; CHECK-NEXT: PTILESTOREDV [[COPY16]].sub_16bit, [[COPY12]].sub_16bit, [[MOV64rm]], 1, [[COPY14]], 0, $noreg, [[PTDPBSSDV]]
- ; CHECK-NEXT: [[ADD64rr1:%[0-9]+]]:gr64 = ADD64rr [[ADD64rr1]], [[COPY15]], implicit-def dead $eflags
- ; CHECK-NEXT: [[ADD64rr2:%[0-9]+]]:gr64 = ADD64rr [[ADD64rr2]], [[COPY17]], implicit-def dead $eflags
- ; CHECK-NEXT: [[MOVSX64rr32_7]].sub_32bit:gr64_nosp = ADD32rr [[MOVSX64...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/66627
More information about the llvm-commits
mailing list