[llvm] [AArch64][SME2][SVE2p1] Add PNR_3b regclass (PR #67785)
Matthew Devereau via llvm-commits
llvm-commits at lists.llvm.org
Fri Sep 29 03:59:26 PDT 2023
https://github.com/MDevereau updated https://github.com/llvm/llvm-project/pull/67785
>From c0c983a6ad708327ebcd2482e20f61055e5496ee Mon Sep 17 00:00:00 2001
From: Matt Devereau <matthew.devereau at arm.com>
Date: Fri, 29 Sep 2023 10:39:08 +0000
Subject: [PATCH 1/2] [AArch64][SME2][SVE2p1] Add PNR_3b regclass
This patch adds the PNR_3b regclass for predicate-as-counter registers
0-7 and allows the Upl ASM constraint to use this register class.
---
.../Target/AArch64/AArch64ISelLowering.cpp | 3 ++-
.../lib/Target/AArch64/AArch64RegisterInfo.td | 1 +
.../GlobalISel/irtranslator-inline-asm.ll | 22 ++++++++--------
.../irtranslator-unwind-inline-asm.ll | 2 +-
.../AArch64/GlobalISel/regbank-inlineasm.mir | 4 +--
llvm/test/CodeGen/AArch64/aarch64-sme2-asm.ll | 22 +++++++++++++---
.../callbr-asm-outputs-indirect-isel.ll | 26 +++++++++----------
.../emit_fneg_with_non_register_operand.mir | 4 +--
.../CodeGen/AArch64/peephole-insvigpr.mir | 2 +-
9 files changed, 51 insertions(+), 35 deletions(-)
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index 662306c0dadf0d4..06fe64d10a1c13e 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -10063,7 +10063,8 @@ getPredicateRegisterClass(PredicateConstraint Constraint, EVT VT) {
return VT == MVT::aarch64svcount ? &AArch64::PNR_p8to15RegClass
: &AArch64::PPR_p8to15RegClass;
case PredicateConstraint::Upl:
- return VT == MVT::aarch64svcount ? nullptr : &AArch64::PPR_3bRegClass;
+ return VT == MVT::aarch64svcount ? &AArch64::PNR_3bRegClass
+ : &AArch64::PPR_3bRegClass;
case PredicateConstraint::Upa:
return VT == MVT::aarch64svcount ? &AArch64::PNRRegClass
: &AArch64::PPRRegClass;
diff --git a/llvm/lib/Target/AArch64/AArch64RegisterInfo.td b/llvm/lib/Target/AArch64/AArch64RegisterInfo.td
index e3d77ef37a8ac02..eb26591908fd79c 100644
--- a/llvm/lib/Target/AArch64/AArch64RegisterInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64RegisterInfo.td
@@ -915,6 +915,7 @@ class PNRClass<int firstreg, int lastreg> : RegisterClass<
}
def PNR : PNRClass<0, 15>;
+def PNR_3b : PNRClass<0, 7>;
def PNR_p8to15 : PNRClass<8, 15>;
// SVE predicate-as-counter operand
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/irtranslator-inline-asm.ll b/llvm/test/CodeGen/AArch64/GlobalISel/irtranslator-inline-asm.ll
index d531c29da7551a9..ef8e46653640862 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/irtranslator-inline-asm.ll
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/irtranslator-inline-asm.ll
@@ -26,7 +26,7 @@ define void @asm_simple_register_clobber() {
define i64 @asm_register_early_clobber() {
; CHECK-LABEL: name: asm_register_early_clobber
; CHECK: bb.1 (%ir-block.0):
- ; CHECK-NEXT: INLINEASM &"mov $0, 7; mov $1, 7", 1 /* sideeffect attdialect */, 2686987 /* regdef-ec:GPR64common */, def early-clobber %0, 2686987 /* regdef-ec:GPR64common */, def early-clobber %1, !0
+ ; CHECK-NEXT: INLINEASM &"mov $0, 7; mov $1, 7", 1 /* sideeffect attdialect */, 2752523 /* regdef-ec:GPR64common */, def early-clobber %0, 2752523 /* regdef-ec:GPR64common */, def early-clobber %1, !0
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY %0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY %1
; CHECK-NEXT: [[ADD:%[0-9]+]]:_(s64) = G_ADD [[COPY]], [[COPY1]]
@@ -54,7 +54,7 @@ entry:
define i32 @test_single_register_output() nounwind ssp {
; CHECK-LABEL: name: test_single_register_output
; CHECK: bb.1.entry:
- ; CHECK-NEXT: INLINEASM &"mov ${0:w}, 7", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %0
+ ; CHECK-NEXT: INLINEASM &"mov ${0:w}, 7", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %0
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY %0
; CHECK-NEXT: $w0 = COPY [[COPY]](s32)
; CHECK-NEXT: RET_ReallyLR implicit $w0
@@ -66,7 +66,7 @@ entry:
define i64 @test_single_register_output_s64() nounwind ssp {
; CHECK-LABEL: name: test_single_register_output_s64
; CHECK: bb.1.entry:
- ; CHECK-NEXT: INLINEASM &"mov $0, 7", 0 /* attdialect */, 2686986 /* regdef:GPR64common */, def %0
+ ; CHECK-NEXT: INLINEASM &"mov $0, 7", 0 /* attdialect */, 2752522 /* regdef:GPR64common */, def %0
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY %0
; CHECK-NEXT: $x0 = COPY [[COPY]](s64)
; CHECK-NEXT: RET_ReallyLR implicit $x0
@@ -79,7 +79,7 @@ entry:
define float @test_multiple_register_outputs_same() #0 {
; CHECK-LABEL: name: test_multiple_register_outputs_same
; CHECK: bb.1 (%ir-block.0):
- ; CHECK-NEXT: INLINEASM &"mov $0, #0; mov $1, #0", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %0, 1638410 /* regdef:GPR32common */, def %1
+ ; CHECK-NEXT: INLINEASM &"mov $0, #0; mov $1, #0", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %0, 1703946 /* regdef:GPR32common */, def %1
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY %0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY %1
; CHECK-NEXT: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[COPY]], [[COPY1]]
@@ -96,7 +96,7 @@ define float @test_multiple_register_outputs_same() #0 {
define double @test_multiple_register_outputs_mixed() #0 {
; CHECK-LABEL: name: test_multiple_register_outputs_mixed
; CHECK: bb.1 (%ir-block.0):
- ; CHECK-NEXT: INLINEASM &"mov $0, #0; mov $1, #0", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %0, 2490378 /* regdef:FPR64 */, def %1
+ ; CHECK-NEXT: INLINEASM &"mov $0, #0; mov $1, #0", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %0, 2555914 /* regdef:FPR64 */, def %1
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY %0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY %1
; CHECK-NEXT: $d0 = COPY [[COPY1]](s64)
@@ -125,7 +125,7 @@ define zeroext i8 @test_register_output_trunc(ptr %src) nounwind {
; CHECK-NEXT: liveins: $x0
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
- ; CHECK-NEXT: INLINEASM &"mov ${0:w}, 32", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %1
+ ; CHECK-NEXT: INLINEASM &"mov ${0:w}, 32", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %1
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY %1
; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY1]](s32)
; CHECK-NEXT: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[TRUNC]](s8)
@@ -155,7 +155,7 @@ define void @test_input_register_imm() {
; CHECK: bb.1 (%ir-block.0):
; CHECK-NEXT: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 42
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr64common = COPY [[C]](s64)
- ; CHECK-NEXT: INLINEASM &"mov x0, $0", 1 /* sideeffect attdialect */, 2686985 /* reguse:GPR64common */, [[COPY]]
+ ; CHECK-NEXT: INLINEASM &"mov x0, $0", 1 /* sideeffect attdialect */, 2752521 /* reguse:GPR64common */, [[COPY]]
; CHECK-NEXT: RET_ReallyLR
call void asm sideeffect "mov x0, $0", "r"(i64 42)
ret void
@@ -190,7 +190,7 @@ define zeroext i8 @test_input_register(ptr %src) nounwind {
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:gpr64common = COPY [[COPY]](p0)
- ; CHECK-NEXT: INLINEASM &"ldtrb ${0:w}, [$1]", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %1, 2686985 /* reguse:GPR64common */, [[COPY1]]
+ ; CHECK-NEXT: INLINEASM &"ldtrb ${0:w}, [$1]", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %1, 2752521 /* reguse:GPR64common */, [[COPY1]]
; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY %1
; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[COPY2]](s32)
; CHECK-NEXT: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[TRUNC]](s8)
@@ -207,7 +207,7 @@ define i32 @test_memory_constraint(ptr %a) nounwind {
; CHECK-NEXT: liveins: $x0
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
- ; CHECK-NEXT: INLINEASM &"ldr $0, $1", 8 /* mayload attdialect */, 1638410 /* regdef:GPR32common */, def %1, 262158 /* mem:m */, [[COPY]](p0)
+ ; CHECK-NEXT: INLINEASM &"ldr $0, $1", 8 /* mayload attdialect */, 1703946 /* regdef:GPR32common */, def %1, 262158 /* mem:m */, [[COPY]](p0)
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY %1
; CHECK-NEXT: $w0 = COPY [[COPY1]](s32)
; CHECK-NEXT: RET_ReallyLR implicit $w0
@@ -221,7 +221,7 @@ define i16 @test_anyext_input() {
; CHECK-NEXT: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 1
; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[C]](s16)
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr32common = COPY [[ANYEXT]](s32)
- ; CHECK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, 1638410 /* regdef:GPR32common */, def %0, 1638409 /* reguse:GPR32common */, [[COPY]]
+ ; CHECK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, 1703946 /* regdef:GPR32common */, def %0, 1703945 /* reguse:GPR32common */, [[COPY]]
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY %0
; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
; CHECK-NEXT: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC]](s16)
@@ -237,7 +237,7 @@ define i16 @test_anyext_input_with_matching_constraint() {
; CHECK-NEXT: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 1
; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[C]](s16)
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr32common = COPY [[ANYEXT]](s32)
- ; CHECK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, 1638410 /* regdef:GPR32common */, def %0, 2147483657 /* reguse tiedto:$0 */, [[COPY]](tied-def 3)
+ ; CHECK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, 1703946 /* regdef:GPR32common */, def %0, 2147483657 /* reguse tiedto:$0 */, [[COPY]](tied-def 3)
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY %0
; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
; CHECK-NEXT: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC]](s16)
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/irtranslator-unwind-inline-asm.ll b/llvm/test/CodeGen/AArch64/GlobalISel/irtranslator-unwind-inline-asm.ll
index c224b0a259fcd18..59eb80ae6146b3f 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/irtranslator-unwind-inline-asm.ll
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/irtranslator-unwind-inline-asm.ll
@@ -71,7 +71,7 @@ define void @test2() #0 personality ptr @__gcc_personality_v0 {
; CHECK-NEXT: G_INVOKE_REGION_START
; CHECK-NEXT: EH_LABEL <mcsymbol >
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr64common = COPY [[DEF]](p0)
- ; CHECK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, 2686985 /* reguse:GPR64common */, [[COPY]]
+ ; CHECK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, 2752521 /* reguse:GPR64common */, [[COPY]]
; CHECK-NEXT: EH_LABEL <mcsymbol >
; CHECK-NEXT: G_BR %bb.2
; CHECK-NEXT: {{ $}}
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/regbank-inlineasm.mir b/llvm/test/CodeGen/AArch64/GlobalISel/regbank-inlineasm.mir
index f75731e351c7826..e77fac19e0a78a5 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/regbank-inlineasm.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/regbank-inlineasm.mir
@@ -57,7 +57,7 @@ tracksRegLiveness: true
body: |
bb.1:
; CHECK-LABEL: name: inlineasm_virt_reg_output
- ; CHECK: INLINEASM &"mov ${0:w}, 7", 0 /* attdialect */, 1310730 /* regdef:PPR2_with_psub_in_PNR_p8to15_and_PPR2_with_psub1_in_PPR_3b */, def %0
+ ; CHECK: INLINEASM &"mov ${0:w}, 7", 0 /* attdialect */, 1310730 /* regdef:PPR2_with_psub_in_PNR_3b_and_PPR2_with_psub1_in_PPR_p8to15 */, def %0
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr(s32) = COPY %0
; CHECK-NEXT: $w0 = COPY [[COPY]](s32)
; CHECK-NEXT: RET_ReallyLR implicit $w0
@@ -75,7 +75,7 @@ tracksRegLiveness: true
body: |
bb.1:
; CHECK-LABEL: name: inlineasm_virt_mixed_types
- ; CHECK: INLINEASM &"mov $0, #0; mov $1, #0", 0 /* attdialect */, 1310730 /* regdef:PPR2_with_psub_in_PNR_p8to15_and_PPR2_with_psub1_in_PPR_3b */, def %0, 2162698 /* regdef:WSeqPairsClass_with_subo32_in_GPR32common */, def %1
+ ; CHECK: INLINEASM &"mov $0, #0; mov $1, #0", 0 /* attdialect */, 1310730 /* regdef:PPR2_with_psub_in_PNR_3b_and_PPR2_with_psub1_in_PPR_p8to15 */, def %0, 2162698 /* regdef:WSeqPairsClass */, def %1
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr(s32) = COPY %0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:fpr(s64) = COPY %1
; CHECK-NEXT: $d0 = COPY [[COPY1]](s64)
diff --git a/llvm/test/CodeGen/AArch64/aarch64-sme2-asm.ll b/llvm/test/CodeGen/AArch64/aarch64-sme2-asm.ll
index 98e7ad740681e68..604e00b2cce7fd6 100644
--- a/llvm/test/CodeGen/AArch64/aarch64-sme2-asm.ll
+++ b/llvm/test/CodeGen/AArch64/aarch64-sme2-asm.ll
@@ -1,11 +1,11 @@
; RUN: llc < %s -mtriple aarch64-none-linux-gnu -mattr=+sme2 -stop-after=finalize-isel | FileCheck %s
-define dso_local void @UphPNR(target("aarch64.svcount") %predcnt) {
+define void @UphPNR(target("aarch64.svcount") %predcnt) {
entry:
; CHECK: %0:ppr = COPY $p0
; CHECK: STR_PXI %0, %stack.0.predcnt.addr, 0 :: (store unknown-size into %ir.predcnt.addr, align 2)
; CHECK: %1:pnr_p8to15 = COPY %0
-; CHECK: INLINEASM &"ld1w {z0.s,z1.s,z2.s,z3.s}, $0/z, [x10]", 1 /* sideeffect attdialect */, 393225 /* reguse:PNR_p8to15 */, %1
+; CHECK: INLINEASM &"ld1w {z0.s,z1.s,z2.s,z3.s}, $0/z, [x10]", 1 /* sideeffect attdialect */, 458761 /* reguse:PNR_p8to15 */, %1
; CHECK: RET_ReallyLR
%predcnt.addr = alloca target("aarch64.svcount"), align 2
store target("aarch64.svcount") %predcnt, ptr %predcnt.addr, align 2
@@ -14,7 +14,7 @@ entry:
ret void
}
-define dso_local void @UpaPNR(target("aarch64.svcount") %predcnt) {
+define void @UpaPNR(target("aarch64.svcount") %predcnt) {
entry:
; CHECK: %0:ppr = COPY $p0
; CHECK: STR_PXI %0, %stack.0.predcnt.addr, 0 :: (store unknown-size into %ir.predcnt.addr, align 2)
@@ -26,4 +26,18 @@ entry:
%0 = load target("aarch64.svcount"), ptr %predcnt.addr, align 2
call void asm sideeffect "ld1w {z0.s,z1.s,z2.s,z3.s}, $0/z, [x10]", "@3Upa"(target("aarch64.svcount") %0)
ret void
-}
\ No newline at end of file
+}
+
+define void @UplPNR(target("aarch64.svcount") %predcnt) {
+entry:
+; CHECK: %0:ppr = COPY $p0
+; CHECK: STR_PXI %0, %stack.0.predcnt.addr, 0 :: (store unknown-size into %ir.predcnt.addr, align 2)
+; CHECK: %1:pnr_3b = COPY %0
+; CHECK: INLINEASM &"fadd z0.h, p0/m, z0.h, #0.5", 1 /* sideeffect attdialect */, 393225 /* reguse:PNR_3b */, %1
+; CHECK: RET_ReallyLR
+ %predcnt.addr = alloca target("aarch64.svcount"), align 2
+ store target("aarch64.svcount") %predcnt, ptr %predcnt.addr, align 2
+ %0 = load target("aarch64.svcount"), ptr %predcnt.addr, align 2
+ call void asm sideeffect "fadd z0.h, p0/m, z0.h, #0.5", "@3Upl"(target("aarch64.svcount") %0)
+ ret void
+}
diff --git a/llvm/test/CodeGen/AArch64/callbr-asm-outputs-indirect-isel.ll b/llvm/test/CodeGen/AArch64/callbr-asm-outputs-indirect-isel.ll
index ed02fdfc996a433..89745f4df4cde40 100644
--- a/llvm/test/CodeGen/AArch64/callbr-asm-outputs-indirect-isel.ll
+++ b/llvm/test/CodeGen/AArch64/callbr-asm-outputs-indirect-isel.ll
@@ -18,7 +18,7 @@ define i32 @test0() {
; CHECK: bb.0.entry:
; CHECK-NEXT: successors: %bb.2(0x80000000), %bb.1(0x00000000)
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: INLINEASM_BR &"# $0", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %5, 13 /* imm */, %bb.1
+ ; CHECK-NEXT: INLINEASM_BR &"# $0", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %5, 13 /* imm */, %bb.1
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr32all = COPY %5
; CHECK-NEXT: B %bb.2
; CHECK-NEXT: {{ $}}
@@ -31,7 +31,7 @@ define i32 @test0() {
; CHECK-NEXT: bb.2.direct:
; CHECK-NEXT: successors: %bb.4(0x80000000), %bb.3(0x00000000)
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: INLINEASM_BR &"# $0", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %7, 13 /* imm */, %bb.3
+ ; CHECK-NEXT: INLINEASM_BR &"# $0", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %7, 13 /* imm */, %bb.3
; CHECK-NEXT: [[COPY2:%[0-9]+]]:gpr32all = COPY %7
; CHECK-NEXT: B %bb.4
; CHECK-NEXT: {{ $}}
@@ -107,7 +107,7 @@ define i32 @dont_split1() {
; CHECK: bb.0.entry:
; CHECK-NEXT: successors: %bb.1(0x80000000), %bb.2(0x00000000)
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %1, 13 /* imm */, %bb.2
+ ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %1, 13 /* imm */, %bb.2
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr32all = COPY %1
; CHECK-NEXT: B %bb.1
; CHECK-NEXT: {{ $}}
@@ -168,7 +168,7 @@ define i32 @dont_split3() {
; CHECK: bb.0.entry:
; CHECK-NEXT: successors: %bb.1(0x80000000), %bb.2(0x00000000)
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %0, 13 /* imm */, %bb.2
+ ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %0, 13 /* imm */, %bb.2
; CHECK-NEXT: B %bb.1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.1.x:
@@ -195,7 +195,7 @@ define i32 @split_me0() {
; CHECK: bb.0.entry:
; CHECK-NEXT: successors: %bb.2(0x80000000), %bb.1(0x00000000)
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %3, 13 /* imm */, %bb.1
+ ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %3, 13 /* imm */, %bb.1
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr32all = COPY %3
; CHECK-NEXT: B %bb.2
; CHECK-NEXT: {{ $}}
@@ -245,7 +245,7 @@ define i32 @split_me1(i1 %z) {
; CHECK-NEXT: bb.1.w:
; CHECK-NEXT: successors: %bb.3(0x80000000), %bb.2(0x00000000)
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %5, 13 /* imm */, %bb.2, 13 /* imm */, %bb.2
+ ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %5, 13 /* imm */, %bb.2, 13 /* imm */, %bb.2
; CHECK-NEXT: [[COPY1:%[0-9]+]]:gpr32all = COPY %5
; CHECK-NEXT: B %bb.3
; CHECK-NEXT: {{ $}}
@@ -298,7 +298,7 @@ define i32 @split_me2(i1 %z) {
; CHECK-NEXT: bb.1.w:
; CHECK-NEXT: successors: %bb.3(0x80000000), %bb.2(0x00000000)
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %6, 13 /* imm */, %bb.2, 13 /* imm */, %bb.2
+ ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %6, 13 /* imm */, %bb.2, 13 /* imm */, %bb.2
; CHECK-NEXT: [[COPY2:%[0-9]+]]:gpr32all = COPY %6
; CHECK-NEXT: B %bb.3
; CHECK-NEXT: {{ $}}
@@ -341,7 +341,7 @@ define i32 @dont_split4() {
; CHECK: bb.0.entry:
; CHECK-NEXT: successors: %bb.1(0x80000000), %bb.2(0x00000000)
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %3, 13 /* imm */, %bb.2
+ ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %3, 13 /* imm */, %bb.2
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr32all = COPY %3
; CHECK-NEXT: B %bb.1
; CHECK-NEXT: {{ $}}
@@ -380,7 +380,7 @@ define i32 @dont_split5() {
; CHECK: bb.0.entry:
; CHECK-NEXT: successors: %bb.2(0x80000000), %bb.1(0x00000000)
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %3, 13 /* imm */, %bb.1
+ ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %3, 13 /* imm */, %bb.1
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr32all = COPY %3
; CHECK-NEXT: B %bb.2
; CHECK-NEXT: {{ $}}
@@ -411,7 +411,7 @@ define i32 @split_me3() {
; CHECK: bb.0.entry:
; CHECK-NEXT: successors: %bb.2(0x80000000), %bb.1(0x00000000)
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %3, 13 /* imm */, %bb.1
+ ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %3, 13 /* imm */, %bb.1
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr32all = COPY %3
; CHECK-NEXT: B %bb.2
; CHECK-NEXT: {{ $}}
@@ -458,7 +458,7 @@ define i32 @dont_split6(i32 %0) {
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[PHI:%[0-9]+]]:gpr32all = PHI [[COPY]], %bb.0, %2, %bb.2
; CHECK-NEXT: [[COPY1:%[0-9]+]]:gpr32common = COPY [[PHI]]
- ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %4, 2147483657 /* reguse tiedto:$0 */, [[COPY1]](tied-def 3), 13 /* imm */, %bb.2
+ ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %4, 2147483657 /* reguse tiedto:$0 */, [[COPY1]](tied-def 3), 13 /* imm */, %bb.2
; CHECK-NEXT: [[COPY2:%[0-9]+]]:gpr32all = COPY %4
; CHECK-NEXT: B %bb.3
; CHECK-NEXT: {{ $}}
@@ -493,7 +493,7 @@ define i32 @split_me4() {
; CHECK: bb.0.entry:
; CHECK-NEXT: successors: %bb.2(0x80000000), %bb.1(0x00000000)
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %3, 13 /* imm */, %bb.1
+ ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %3, 13 /* imm */, %bb.1
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr32all = COPY %3
; CHECK-NEXT: B %bb.2
; CHECK-NEXT: {{ $}}
@@ -524,7 +524,7 @@ define i32 @split_me5() {
; CHECK: bb.0.entry:
; CHECK-NEXT: successors: %bb.2(0x80000000), %bb.1(0x00000000)
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1638410 /* regdef:GPR32common */, def %3, 13 /* imm */, %bb.1
+ ; CHECK-NEXT: INLINEASM_BR &"", 0 /* attdialect */, 1703946 /* regdef:GPR32common */, def %3, 13 /* imm */, %bb.1
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr32all = COPY %3
; CHECK-NEXT: B %bb.2
; CHECK-NEXT: {{ $}}
diff --git a/llvm/test/CodeGen/AArch64/emit_fneg_with_non_register_operand.mir b/llvm/test/CodeGen/AArch64/emit_fneg_with_non_register_operand.mir
index 8255c7dd6f1e4d9..483dbd2f14d556d 100644
--- a/llvm/test/CodeGen/AArch64/emit_fneg_with_non_register_operand.mir
+++ b/llvm/test/CodeGen/AArch64/emit_fneg_with_non_register_operand.mir
@@ -91,10 +91,10 @@ body: |
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[LOADgot:%[0-9]+]]:gpr64common = LOADgot target-flags(aarch64-got) @c
; CHECK-NEXT: [[LDRDui:%[0-9]+]]:fpr64 = LDRDui [[LOADgot]], 0 :: (dereferenceable load (s64) from @c)
- ; CHECK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, 2359306 /* regdef:WSeqPairsClass_with_sube32_in_MatrixIndexGPR32_8_11 */, def %2, 2147483657 /* reguse tiedto:$0 */, [[LDRDui]](tied-def 3)
+ ; CHECK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, 2359306 /* regdef:WSeqPairsClass_with_sube32_in_MatrixIndexGPR32_12_15 */, def %2, 2147483657 /* reguse tiedto:$0 */, [[LDRDui]](tied-def 3)
; CHECK-NEXT: [[COPY:%[0-9]+]]:fpr64 = COPY %2
; CHECK-NEXT: [[LDRDui1:%[0-9]+]]:fpr64 = LDRDui [[LOADgot]], 0 :: (dereferenceable load (s64) from @c)
- ; CHECK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, 2359306 /* regdef:WSeqPairsClass_with_sube32_in_MatrixIndexGPR32_8_11 */, def %4, 2147483657 /* reguse tiedto:$0 */, [[LDRDui1]](tied-def 3)
+ ; CHECK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, 2359306 /* regdef:WSeqPairsClass_with_sube32_in_MatrixIndexGPR32_12_15 */, def %4, 2147483657 /* reguse tiedto:$0 */, [[LDRDui1]](tied-def 3)
; CHECK-NEXT: [[FNEGDr:%[0-9]+]]:fpr64 = FNEGDr %2
; CHECK-NEXT: nofpexcept FCMPDrr %4, killed [[FNEGDr]], implicit-def $nzcv, implicit $fpcr
; CHECK-NEXT: Bcc 1, %bb.2, implicit $nzcv
diff --git a/llvm/test/CodeGen/AArch64/peephole-insvigpr.mir b/llvm/test/CodeGen/AArch64/peephole-insvigpr.mir
index 546f2ec0c417152..041b2dc6af12779 100644
--- a/llvm/test/CodeGen/AArch64/peephole-insvigpr.mir
+++ b/llvm/test/CodeGen/AArch64/peephole-insvigpr.mir
@@ -487,7 +487,7 @@ body: |
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr64common = COPY $x0
; CHECK-NEXT: [[DEF:%[0-9]+]]:gpr64all = IMPLICIT_DEF
; CHECK-NEXT: [[COPY1:%[0-9]+]]:gpr64sp = COPY [[DEF]]
- ; CHECK-NEXT: INLINEASM &"ldr ${0:s}, $1", 8 /* mayload attdialect */, 2359306 /* regdef:WSeqPairsClass_with_sube32_in_MatrixIndexGPR32_8_11 */, def %1, 262158 /* mem:m */, killed [[COPY1]]
+ ; CHECK-NEXT: INLINEASM &"ldr ${0:s}, $1", 8 /* mayload attdialect */, 2359306 /* regdef:WSeqPairsClass_with_sube32_in_MatrixIndexGPR32_12_15 */, def %1, 262158 /* mem:m */, killed [[COPY1]]
; CHECK-NEXT: [[MOVIv2d_ns:%[0-9]+]]:fpr128 = MOVIv2d_ns 0
; CHECK-NEXT: [[COPY2:%[0-9]+]]:fpr64 = COPY [[MOVIv2d_ns]].dsub
; CHECK-NEXT: [[DEF1:%[0-9]+]]:fpr128 = IMPLICIT_DEF
>From 08bfb831d69f15282d9380fce85a406385de9f61 Mon Sep 17 00:00:00 2001
From: Matt Devereau <matthew.devereau at arm.com>
Date: Fri, 29 Sep 2023 10:59:00 +0000
Subject: [PATCH 2/2] Fix ASM parameter
---
llvm/test/CodeGen/AArch64/aarch64-sme2-asm.ll | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/llvm/test/CodeGen/AArch64/aarch64-sme2-asm.ll b/llvm/test/CodeGen/AArch64/aarch64-sme2-asm.ll
index 604e00b2cce7fd6..8ed7059d2e754c4 100644
--- a/llvm/test/CodeGen/AArch64/aarch64-sme2-asm.ll
+++ b/llvm/test/CodeGen/AArch64/aarch64-sme2-asm.ll
@@ -33,11 +33,11 @@ entry:
; CHECK: %0:ppr = COPY $p0
; CHECK: STR_PXI %0, %stack.0.predcnt.addr, 0 :: (store unknown-size into %ir.predcnt.addr, align 2)
; CHECK: %1:pnr_3b = COPY %0
-; CHECK: INLINEASM &"fadd z0.h, p0/m, z0.h, #0.5", 1 /* sideeffect attdialect */, 393225 /* reguse:PNR_3b */, %1
+; CHECK: INLINEASM &"fadd z0.h, $0/m, z0.h, #0.5", 1 /* sideeffect attdialect */, 393225 /* reguse:PNR_3b */, %1
; CHECK: RET_ReallyLR
%predcnt.addr = alloca target("aarch64.svcount"), align 2
store target("aarch64.svcount") %predcnt, ptr %predcnt.addr, align 2
%0 = load target("aarch64.svcount"), ptr %predcnt.addr, align 2
- call void asm sideeffect "fadd z0.h, p0/m, z0.h, #0.5", "@3Upl"(target("aarch64.svcount") %0)
+ call void asm sideeffect "fadd z0.h, $0/m, z0.h, #0.5", "@3Upl"(target("aarch64.svcount") %0)
ret void
}
More information about the llvm-commits
mailing list