[llvm] [RISCV][GlobalISel] Legalize Scalable Vector Loads and Stores (PR #84965)
Jiahan Xie via llvm-commits
llvm-commits at lists.llvm.org
Sun Jul 21 17:43:03 PDT 2024
================
@@ -0,0 +1,1040 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=riscv32 -mattr=+v -run-pass=legalizer %s -o - | FileCheck %s
+# RUN: llc -mtriple=riscv64 -mattr=+v -run-pass=legalizer %s -o - | FileCheck %s
+--- |
+
+ define <vscale x 1 x i8> @vload_nxv1i8(ptr %pa) #0 {
+ %va = load <vscale x 1 x i8>, ptr %pa, align 1
+ ret <vscale x 1 x i8> %va
+ }
+
+ define <vscale x 2 x i8> @vload_nxv2i8(ptr %pa) #0 {
+ %va = load <vscale x 2 x i8>, ptr %pa, align 2
+ ret <vscale x 2 x i8> %va
+ }
+
+ define <vscale x 4 x i8> @vload_nxv4i8(ptr %pa) #0 {
+ %va = load <vscale x 4 x i8>, ptr %pa, align 4
+ ret <vscale x 4 x i8> %va
+ }
+
+ define <vscale x 8 x i8> @vload_nxv8i8(ptr %pa) #0 {
+ %va = load <vscale x 8 x i8>, ptr %pa, align 8
+ ret <vscale x 8 x i8> %va
+ }
+
+ define <vscale x 16 x i8> @vload_nxv16i8(ptr %pa) #0 {
+ %va = load <vscale x 16 x i8>, ptr %pa, align 16
+ ret <vscale x 16 x i8> %va
+ }
+
+ define <vscale x 32 x i8> @vload_nxv32i8(ptr %pa) #0 {
+ %va = load <vscale x 32 x i8>, ptr %pa, align 32
+ ret <vscale x 32 x i8> %va
+ }
+
+ define <vscale x 64 x i8> @vload_nxv64i8(ptr %pa) #0 {
+ %va = load <vscale x 64 x i8>, ptr %pa, align 64
+ ret <vscale x 64 x i8> %va
+ }
+
+ define <vscale x 1 x i16> @vload_nxv1i16(ptr %pa) #0 {
+ %va = load <vscale x 1 x i16>, ptr %pa, align 2
+ ret <vscale x 1 x i16> %va
+ }
+
+ define <vscale x 2 x i16> @vload_nxv2i16(ptr %pa) #0 {
+ %va = load <vscale x 2 x i16>, ptr %pa, align 4
+ ret <vscale x 2 x i16> %va
+ }
+
+ define <vscale x 4 x i16> @vload_nxv4i16(ptr %pa) #0 {
+ %va = load <vscale x 4 x i16>, ptr %pa, align 8
+ ret <vscale x 4 x i16> %va
+ }
+
+ define <vscale x 8 x i16> @vload_nxv8i16(ptr %pa) #0 {
+ %va = load <vscale x 8 x i16>, ptr %pa, align 16
+ ret <vscale x 8 x i16> %va
+ }
+
+ define <vscale x 16 x i16> @vload_nxv16i16(ptr %pa) #0 {
+ %va = load <vscale x 16 x i16>, ptr %pa, align 32
+ ret <vscale x 16 x i16> %va
+ }
+
+ define <vscale x 32 x i16> @vload_nxv32i16(ptr %pa) #0 {
+ %va = load <vscale x 32 x i16>, ptr %pa, align 64
+ ret <vscale x 32 x i16> %va
+ }
+
+ define <vscale x 1 x i32> @vload_nxv1i32(ptr %pa) #0 {
+ %va = load <vscale x 1 x i32>, ptr %pa, align 4
+ ret <vscale x 1 x i32> %va
+ }
+
+ define <vscale x 2 x i32> @vload_nxv2i32(ptr %pa) #0 {
+ %va = load <vscale x 2 x i32>, ptr %pa, align 8
+ ret <vscale x 2 x i32> %va
+ }
+
+ define <vscale x 4 x i32> @vload_nxv4i32(ptr %pa) #0 {
+ %va = load <vscale x 4 x i32>, ptr %pa, align 16
+ ret <vscale x 4 x i32> %va
+ }
+
+ define <vscale x 8 x i32> @vload_nxv8i32(ptr %pa) #0 {
+ %va = load <vscale x 8 x i32>, ptr %pa, align 32
+ ret <vscale x 8 x i32> %va
+ }
+
+ define <vscale x 16 x i32> @vload_nxv16i32(ptr %pa) #0 {
+ %va = load <vscale x 16 x i32>, ptr %pa, align 64
+ ret <vscale x 16 x i32> %va
+ }
+
+ define <vscale x 1 x i64> @vload_nxv1i64(ptr %pa) #0 {
+ %va = load <vscale x 1 x i64>, ptr %pa, align 8
+ ret <vscale x 1 x i64> %va
+ }
+
+ define <vscale x 2 x i64> @vload_nxv2i64(ptr %pa) #0 {
+ %va = load <vscale x 2 x i64>, ptr %pa, align 16
+ ret <vscale x 2 x i64> %va
+ }
+
+ define <vscale x 4 x i64> @vload_nxv4i64(ptr %pa) #0 {
+ %va = load <vscale x 4 x i64>, ptr %pa, align 32
+ ret <vscale x 4 x i64> %va
+ }
+
+ define <vscale x 8 x i64> @vload_nxv8i64(ptr %pa) #0 {
+ %va = load <vscale x 8 x i64>, ptr %pa, align 64
+ ret <vscale x 8 x i64> %va
+ }
+
+ define <vscale x 16 x i8> @vload_nxv16i8_align1(ptr %pa) #0 {
+ %va = load <vscale x 16 x i8>, ptr %pa, align 1
+ ret <vscale x 16 x i8> %va
+ }
+
+ define <vscale x 16 x i8> @vload_nxv16i8_align2(ptr %pa) #0 {
+ %va = load <vscale x 16 x i8>, ptr %pa, align 2
+ ret <vscale x 16 x i8> %va
+ }
+
+ define <vscale x 16 x i8> @vload_nxv16i8_align16(ptr %pa) #0 {
+ %va = load <vscale x 16 x i8>, ptr %pa, align 16
+ ret <vscale x 16 x i8> %va
+ }
+
+ define <vscale x 16 x i8> @vload_nxv16i8_align64(ptr %pa) #0 {
+ %va = load <vscale x 16 x i8>, ptr %pa, align 64
+ ret <vscale x 16 x i8> %va
+ }
+
+ define <vscale x 4 x i16> @vload_nxv4i16_align1(ptr %pa) #0 {
+ %va = load <vscale x 4 x i16>, ptr %pa, align 1
+ ret <vscale x 4 x i16> %va
+ }
+
+ define <vscale x 4 x i16> @vload_nxv4i16_align2(ptr %pa) #0 {
+ %va = load <vscale x 4 x i16>, ptr %pa, align 2
+ ret <vscale x 4 x i16> %va
+ }
+
+ define <vscale x 4 x i16> @vload_nxv4i16_align4(ptr %pa) #0 {
+ %va = load <vscale x 4 x i16>, ptr %pa, align 4
+ ret <vscale x 4 x i16> %va
+ }
+
+ define <vscale x 4 x i16> @vload_nxv4i16_align8(ptr %pa) #0 {
+ %va = load <vscale x 4 x i16>, ptr %pa, align 8
+ ret <vscale x 4 x i16> %va
+ }
+
+ define <vscale x 4 x i16> @vload_nxv4i16_align16(ptr %pa) #0 {
+ %va = load <vscale x 4 x i16>, ptr %pa, align 16
+ ret <vscale x 4 x i16> %va
+ }
+
+ define <vscale x 2 x i32> @vload_nxv2i32_align2(ptr %pa) #0 {
+ %va = load <vscale x 2 x i32>, ptr %pa, align 2
+ ret <vscale x 2 x i32> %va
+ }
+
+ define <vscale x 2 x i32> @vload_nxv2i32_align4(ptr %pa) #0 {
+ %va = load <vscale x 2 x i32>, ptr %pa, align 4
+ ret <vscale x 2 x i32> %va
+ }
+
+ define <vscale x 2 x i32> @vload_nxv2i32_align8(ptr %pa) #0 {
+ %va = load <vscale x 2 x i32>, ptr %pa, align 8
+ ret <vscale x 2 x i32> %va
+ }
+
+ define <vscale x 2 x i32> @vload_nxv2i32_align16(ptr %pa) #0 {
+ %va = load <vscale x 2 x i32>, ptr %pa, align 16
+ ret <vscale x 2 x i32> %va
+ }
+
+ define <vscale x 2 x i32> @vload_nxv2i32_align256(ptr %pa) #0 {
+ %va = load <vscale x 2 x i32>, ptr %pa, align 256
+ ret <vscale x 2 x i32> %va
+ }
+
+ define <vscale x 2 x i64> @vload_nxv2i64_align4(ptr %pa) #0 {
+ %va = load <vscale x 2 x i64>, ptr %pa, align 4
+ ret <vscale x 2 x i64> %va
+ }
+
+ define <vscale x 2 x i64> @vload_nxv2i64_align8(ptr %pa) #0 {
+ %va = load <vscale x 2 x i64>, ptr %pa, align 8
+ ret <vscale x 2 x i64> %va
+ }
+
+ define <vscale x 2 x i64> @vload_nxv2i64_align16(ptr %pa) #0 {
+ %va = load <vscale x 2 x i64>, ptr %pa, align 16
+ ret <vscale x 2 x i64> %va
+ }
+
+ define <vscale x 2 x i64> @vload_nxv2i64_align32(ptr %pa) #0 {
+ %va = load <vscale x 2 x i64>, ptr %pa, align 32
+ ret <vscale x 2 x i64> %va
+ }
+
+ define <vscale x 1 x ptr> @vload_nxv1ptr(ptr %pa) #0 {
+ %va = load <vscale x 1 x ptr>, ptr %pa, align 4
+ ret <vscale x 1 x ptr> %va
+ }
+
+ define <vscale x 2 x ptr> @vload_nxv2ptr(ptr %pa) #0 {
+ %va = load <vscale x 2 x ptr>, ptr %pa, align 8
+ ret <vscale x 2 x ptr> %va
+ }
+
+ define <vscale x 8 x ptr> @vload_nxv8ptr(ptr %pa) #0 {
+ %va = load <vscale x 8 x ptr>, ptr %pa, align 32
+ ret <vscale x 8 x ptr> %va
+ }
+
+ attributes #0 = { "target-features"="+v" }
+
+...
+---
+name: vload_nxv1i8
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv1i8
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 1 x s8>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 1 x s8>) from %ir.pa)
+ ; CHECK-NEXT: $v8 = COPY [[LOAD]](<vscale x 1 x s8>)
+ ; CHECK-NEXT: PseudoRET implicit $v8
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 1 x s8>) = G_LOAD %0(p0) :: (load (<vscale x 1 x s8>) from %ir.pa)
+ $v8 = COPY %1(<vscale x 1 x s8>)
+ PseudoRET implicit $v8
+
+...
+---
+name: vload_nxv2i8
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv2i8
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 2 x s8>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 2 x s8>) from %ir.pa)
+ ; CHECK-NEXT: $v8 = COPY [[LOAD]](<vscale x 2 x s8>)
+ ; CHECK-NEXT: PseudoRET implicit $v8
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 2 x s8>) = G_LOAD %0(p0) :: (load (<vscale x 2 x s8>) from %ir.pa)
+ $v8 = COPY %1(<vscale x 2 x s8>)
+ PseudoRET implicit $v8
+
+...
+---
+name: vload_nxv4i8
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv4i8
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 4 x s8>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 4 x s8>) from %ir.pa)
+ ; CHECK-NEXT: $v8 = COPY [[LOAD]](<vscale x 4 x s8>)
+ ; CHECK-NEXT: PseudoRET implicit $v8
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 4 x s8>) = G_LOAD %0(p0) :: (load (<vscale x 4 x s8>) from %ir.pa)
+ $v8 = COPY %1(<vscale x 4 x s8>)
+ PseudoRET implicit $v8
+
+...
+---
+name: vload_nxv8i8
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv8i8
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 8 x s8>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 8 x s8>) from %ir.pa)
+ ; CHECK-NEXT: $v8 = COPY [[LOAD]](<vscale x 8 x s8>)
+ ; CHECK-NEXT: PseudoRET implicit $v8
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 8 x s8>) = G_LOAD %0(p0) :: (load (<vscale x 8 x s8>) from %ir.pa)
+ $v8 = COPY %1(<vscale x 8 x s8>)
+ PseudoRET implicit $v8
+
+...
+---
+name: vload_nxv16i8
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv16i8
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 16 x s8>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 16 x s8>) from %ir.pa)
+ ; CHECK-NEXT: $v8m2 = COPY [[LOAD]](<vscale x 16 x s8>)
+ ; CHECK-NEXT: PseudoRET implicit $v8m2
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 16 x s8>) = G_LOAD %0(p0) :: (load (<vscale x 16 x s8>) from %ir.pa)
+ $v8m2 = COPY %1(<vscale x 16 x s8>)
+ PseudoRET implicit $v8m2
+
+...
+---
+name: vload_nxv32i8
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv32i8
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 32 x s8>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 32 x s8>) from %ir.pa)
+ ; CHECK-NEXT: $v8m4 = COPY [[LOAD]](<vscale x 32 x s8>)
+ ; CHECK-NEXT: PseudoRET implicit $v8m4
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 32 x s8>) = G_LOAD %0(p0) :: (load (<vscale x 32 x s8>) from %ir.pa)
+ $v8m4 = COPY %1(<vscale x 32 x s8>)
+ PseudoRET implicit $v8m4
+
+...
+---
+name: vload_nxv64i8
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv64i8
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 64 x s8>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 64 x s8>) from %ir.pa)
+ ; CHECK-NEXT: $v8m8 = COPY [[LOAD]](<vscale x 64 x s8>)
+ ; CHECK-NEXT: PseudoRET implicit $v8m8
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 64 x s8>) = G_LOAD %0(p0) :: (load (<vscale x 64 x s8>) from %ir.pa)
+ $v8m8 = COPY %1(<vscale x 64 x s8>)
+ PseudoRET implicit $v8m8
+
+...
+---
+name: vload_nxv1i16
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv1i16
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 1 x s16>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 1 x s16>) from %ir.pa)
+ ; CHECK-NEXT: $v8 = COPY [[LOAD]](<vscale x 1 x s16>)
+ ; CHECK-NEXT: PseudoRET implicit $v8
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 1 x s16>) = G_LOAD %0(p0) :: (load (<vscale x 1 x s16>) from %ir.pa)
+ $v8 = COPY %1(<vscale x 1 x s16>)
+ PseudoRET implicit $v8
+
+...
+---
+name: vload_nxv2i16
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv2i16
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 2 x s16>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 2 x s16>) from %ir.pa)
+ ; CHECK-NEXT: $v8 = COPY [[LOAD]](<vscale x 2 x s16>)
+ ; CHECK-NEXT: PseudoRET implicit $v8
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 2 x s16>) = G_LOAD %0(p0) :: (load (<vscale x 2 x s16>) from %ir.pa)
+ $v8 = COPY %1(<vscale x 2 x s16>)
+ PseudoRET implicit $v8
+
+...
+---
+name: vload_nxv4i16
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv4i16
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 4 x s16>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 4 x s16>) from %ir.pa)
+ ; CHECK-NEXT: $v8 = COPY [[LOAD]](<vscale x 4 x s16>)
+ ; CHECK-NEXT: PseudoRET implicit $v8
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 4 x s16>) = G_LOAD %0(p0) :: (load (<vscale x 4 x s16>) from %ir.pa)
+ $v8 = COPY %1(<vscale x 4 x s16>)
+ PseudoRET implicit $v8
+
+...
+---
+name: vload_nxv8i16
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv8i16
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 8 x s16>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 8 x s16>) from %ir.pa)
+ ; CHECK-NEXT: $v8m2 = COPY [[LOAD]](<vscale x 8 x s16>)
+ ; CHECK-NEXT: PseudoRET implicit $v8m2
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 8 x s16>) = G_LOAD %0(p0) :: (load (<vscale x 8 x s16>) from %ir.pa)
+ $v8m2 = COPY %1(<vscale x 8 x s16>)
+ PseudoRET implicit $v8m2
+
+...
+---
+name: vload_nxv16i16
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv16i16
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 16 x s16>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 16 x s16>) from %ir.pa)
+ ; CHECK-NEXT: $v8m4 = COPY [[LOAD]](<vscale x 16 x s16>)
+ ; CHECK-NEXT: PseudoRET implicit $v8m4
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 16 x s16>) = G_LOAD %0(p0) :: (load (<vscale x 16 x s16>) from %ir.pa)
+ $v8m4 = COPY %1(<vscale x 16 x s16>)
+ PseudoRET implicit $v8m4
+
+...
+---
+name: vload_nxv32i16
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv32i16
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 32 x s16>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 32 x s16>) from %ir.pa)
+ ; CHECK-NEXT: $v8m8 = COPY [[LOAD]](<vscale x 32 x s16>)
+ ; CHECK-NEXT: PseudoRET implicit $v8m8
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 32 x s16>) = G_LOAD %0(p0) :: (load (<vscale x 32 x s16>) from %ir.pa)
+ $v8m8 = COPY %1(<vscale x 32 x s16>)
+ PseudoRET implicit $v8m8
+
+...
+---
+name: vload_nxv1i32
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv1i32
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 1 x s32>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 1 x s32>) from %ir.pa)
+ ; CHECK-NEXT: $v8 = COPY [[LOAD]](<vscale x 1 x s32>)
+ ; CHECK-NEXT: PseudoRET implicit $v8
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 1 x s32>) = G_LOAD %0(p0) :: (load (<vscale x 1 x s32>) from %ir.pa)
+ $v8 = COPY %1(<vscale x 1 x s32>)
+ PseudoRET implicit $v8
+
+...
+---
+name: vload_nxv2i32
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv2i32
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 2 x s32>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 2 x s32>) from %ir.pa)
+ ; CHECK-NEXT: $v8 = COPY [[LOAD]](<vscale x 2 x s32>)
+ ; CHECK-NEXT: PseudoRET implicit $v8
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 2 x s32>) = G_LOAD %0(p0) :: (load (<vscale x 2 x s32>) from %ir.pa)
+ $v8 = COPY %1(<vscale x 2 x s32>)
+ PseudoRET implicit $v8
+
+...
+---
+name: vload_nxv4i32
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv4i32
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 4 x s32>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 4 x s32>) from %ir.pa)
+ ; CHECK-NEXT: $v8m2 = COPY [[LOAD]](<vscale x 4 x s32>)
+ ; CHECK-NEXT: PseudoRET implicit $v8m2
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 4 x s32>) = G_LOAD %0(p0) :: (load (<vscale x 4 x s32>) from %ir.pa)
+ $v8m2 = COPY %1(<vscale x 4 x s32>)
+ PseudoRET implicit $v8m2
+
+...
+---
+name: vload_nxv8i32
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv8i32
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 8 x s32>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 8 x s32>) from %ir.pa)
+ ; CHECK-NEXT: $v8m4 = COPY [[LOAD]](<vscale x 8 x s32>)
+ ; CHECK-NEXT: PseudoRET implicit $v8m4
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 8 x s32>) = G_LOAD %0(p0) :: (load (<vscale x 8 x s32>) from %ir.pa)
+ $v8m4 = COPY %1(<vscale x 8 x s32>)
+ PseudoRET implicit $v8m4
+
+...
+---
+name: vload_nxv16i32
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv16i32
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 16 x s32>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 16 x s32>) from %ir.pa)
+ ; CHECK-NEXT: $v8m8 = COPY [[LOAD]](<vscale x 16 x s32>)
+ ; CHECK-NEXT: PseudoRET implicit $v8m8
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 16 x s32>) = G_LOAD %0(p0) :: (load (<vscale x 16 x s32>) from %ir.pa)
+ $v8m8 = COPY %1(<vscale x 16 x s32>)
+ PseudoRET implicit $v8m8
+
+...
+---
+name: vload_nxv1i64
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv1i64
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 1 x s64>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 1 x s64>) from %ir.pa)
+ ; CHECK-NEXT: $v8 = COPY [[LOAD]](<vscale x 1 x s64>)
+ ; CHECK-NEXT: PseudoRET implicit $v8
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 1 x s64>) = G_LOAD %0(p0) :: (load (<vscale x 1 x s64>) from %ir.pa)
+ $v8 = COPY %1(<vscale x 1 x s64>)
+ PseudoRET implicit $v8
+
+...
+---
+name: vload_nxv2i64
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv2i64
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 2 x s64>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 2 x s64>) from %ir.pa)
+ ; CHECK-NEXT: $v8m2 = COPY [[LOAD]](<vscale x 2 x s64>)
+ ; CHECK-NEXT: PseudoRET implicit $v8m2
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 2 x s64>) = G_LOAD %0(p0) :: (load (<vscale x 2 x s64>) from %ir.pa)
+ $v8m2 = COPY %1(<vscale x 2 x s64>)
+ PseudoRET implicit $v8m2
+
+...
+---
+name: vload_nxv4i64
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv4i64
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 4 x s64>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 4 x s64>) from %ir.pa)
+ ; CHECK-NEXT: $v8m4 = COPY [[LOAD]](<vscale x 4 x s64>)
+ ; CHECK-NEXT: PseudoRET implicit $v8m4
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 4 x s64>) = G_LOAD %0(p0) :: (load (<vscale x 4 x s64>) from %ir.pa)
+ $v8m4 = COPY %1(<vscale x 4 x s64>)
+ PseudoRET implicit $v8m4
+
+...
+---
+name: vload_nxv8i64
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv8i64
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 8 x s64>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 8 x s64>) from %ir.pa)
+ ; CHECK-NEXT: $v8m8 = COPY [[LOAD]](<vscale x 8 x s64>)
+ ; CHECK-NEXT: PseudoRET implicit $v8m8
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 8 x s64>) = G_LOAD %0(p0) :: (load (<vscale x 8 x s64>) from %ir.pa)
+ $v8m8 = COPY %1(<vscale x 8 x s64>)
+ PseudoRET implicit $v8m8
+
+...
+---
+name: vload_nxv16i8_align1
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv16i8_align1
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 16 x s8>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 16 x s8>) from %ir.pa, align 1)
+ ; CHECK-NEXT: $v8m2 = COPY [[LOAD]](<vscale x 16 x s8>)
+ ; CHECK-NEXT: PseudoRET implicit $v8m2
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 16 x s8>) = G_LOAD %0(p0) :: (load (<vscale x 16 x s8>) from %ir.pa, align 1)
+ $v8m2 = COPY %1(<vscale x 16 x s8>)
+ PseudoRET implicit $v8m2
+
+...
+---
+name: vload_nxv16i8_align2
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv16i8_align2
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 16 x s8>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 16 x s8>) from %ir.pa, align 2)
+ ; CHECK-NEXT: $v8m2 = COPY [[LOAD]](<vscale x 16 x s8>)
+ ; CHECK-NEXT: PseudoRET implicit $v8m2
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 16 x s8>) = G_LOAD %0(p0) :: (load (<vscale x 16 x s8>) from %ir.pa, align 2)
+ $v8m2 = COPY %1(<vscale x 16 x s8>)
+ PseudoRET implicit $v8m2
+
+...
+---
+name: vload_nxv16i8_align16
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv16i8_align16
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 16 x s8>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 16 x s8>) from %ir.pa)
+ ; CHECK-NEXT: $v8m2 = COPY [[LOAD]](<vscale x 16 x s8>)
+ ; CHECK-NEXT: PseudoRET implicit $v8m2
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 16 x s8>) = G_LOAD %0(p0) :: (load (<vscale x 16 x s8>) from %ir.pa)
+ $v8m2 = COPY %1(<vscale x 16 x s8>)
+ PseudoRET implicit $v8m2
+
+...
+---
+name: vload_nxv16i8_align64
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv16i8_align64
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<vscale x 16 x s8>) = G_LOAD [[COPY]](p0) :: (load (<vscale x 16 x s8>) from %ir.pa, align 64)
+ ; CHECK-NEXT: $v8m2 = COPY [[LOAD]](<vscale x 16 x s8>)
+ ; CHECK-NEXT: PseudoRET implicit $v8m2
+ %0:_(p0) = COPY $x10
+ %1:_(<vscale x 16 x s8>) = G_LOAD %0(p0) :: (load (<vscale x 16 x s8>) from %ir.pa, align 64)
+ $v8m2 = COPY %1(<vscale x 16 x s8>)
+ PseudoRET implicit $v8m2
+
+...
+---
+name: vload_nxv4i16_align1
+body: |
+ bb.1 (%ir-block.0):
+ liveins: $x10
+
+ ; CHECK-LABEL: name: vload_nxv4i16_align1
+ ; CHECK: liveins: $x10
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x10
+ ; CHECK-NEXT: [[BITCAST:%[0-9]+]]:_(<vscale x 4 x s16>) = G_BITCAST %2:_(<vscale x 8 x s8>)
----------------
jiahanxie353 wrote:
Curious why we have a `bitcast` here but the instructions below are not changed in-place
https://github.com/llvm/llvm-project/pull/84965
More information about the llvm-commits
mailing list