[clang] [llvm] [LLVM][AArch64] Add new feature +sme-mop4 and +sme-tmop (PR #121935)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Jan 7 05:58:39 PST 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-clang
Author: None (CarolineConcatto)
<details>
<summary>Changes</summary>
The 2024-12 ISA spec release[1] add these features:
FEAT_SME_MOP4(sme-mop4) to enable SME Quarter-tile outer product instructions
and
FEAT_SME_TMOP(sme-tmop) to enable SME Structured sparsity outer product instructions
to allow these instructions to be available outside Armv9.6/sme2p2
[1] https://developer.arm.com/Architectures/A-Profile%20Architecture#Downloads
---
Patch is 181.12 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/121935.diff
41 Files Affected:
- (modified) clang/test/Driver/print-supported-extensions-aarch64.c (+2)
- (modified) llvm/lib/Target/AArch64/AArch64.td (+2-1)
- (modified) llvm/lib/Target/AArch64/AArch64Features.td (+6)
- (modified) llvm/lib/Target/AArch64/AArch64InstrInfo.td (+8)
- (modified) llvm/lib/Target/AArch64/AArch64SMEInstrInfo.td (+32-21)
- (modified) llvm/lib/Target/AArch64/AsmParser/AArch64AsmParser.cpp (+2)
- (modified) llvm/test/MC/AArch64/SME2p2/bfmop4as-non-widening.s (+26-24)
- (modified) llvm/test/MC/AArch64/SME2p2/bfmop4as-widening.s (+26-24)
- (modified) llvm/test/MC/AArch64/SME2p2/bftmopa.s (+8-6)
- (modified) llvm/test/MC/AArch64/SME2p2/directive-arch.s (+8)
- (modified) llvm/test/MC/AArch64/SME2p2/fmop4a-fp8-fp16-widening.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/fmop4a-fp8-fp32-widening.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/fmop4as-fp16-fp32-widening.s (+26-24)
- (modified) llvm/test/MC/AArch64/SME2p2/fmop4as-fp16-non-widening.s (+26-24)
- (modified) llvm/test/MC/AArch64/SME2p2/fmop4as-fp32-non-widening.s (+26-24)
- (modified) llvm/test/MC/AArch64/SME2p2/fmop4as-fp64-non-widening.s (+26-24)
- (modified) llvm/test/MC/AArch64/SME2p2/ftmopa.s (+18-16)
- (modified) llvm/test/MC/AArch64/SME2p2/smop4a-16to32.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/smop4a-64.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/smop4a-8to32.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/smop4s-16to32.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/smop4s-64.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/smop4s-8to32.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/stmopa.s (+8-6)
- (modified) llvm/test/MC/AArch64/SME2p2/sumop4a-32.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/sumop4a-64.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/sumop4s-32.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/sumop4s-64.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/sutmopa.s (+5-3)
- (modified) llvm/test/MC/AArch64/SME2p2/umop4a-16to32.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/umop4a-64.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/umop4a-8to32.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/umop4s-64.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/umop4s-8to32.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/usmop4a-32.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/usmop4a-64.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/usmop4s-32.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/usmop4s-64.s (+14-12)
- (modified) llvm/test/MC/AArch64/SME2p2/ustmopa.s (+5-3)
- (modified) llvm/test/MC/AArch64/SME2p2/utmopa.s (+8-6)
- (modified) llvm/unittests/TargetParser/TargetParserTest.cpp (+8-2)
``````````diff
diff --git a/clang/test/Driver/print-supported-extensions-aarch64.c b/clang/test/Driver/print-supported-extensions-aarch64.c
index 09d499548aa565..77812189f12d0d 100644
--- a/clang/test/Driver/print-supported-extensions-aarch64.c
+++ b/clang/test/Driver/print-supported-extensions-aarch64.c
@@ -51,6 +51,8 @@
// CHECK-NEXT: pcdphint FEAT_PCDPHINT Enable Armv9.6-A Producer Consumer Data Placement hints
// CHECK-NEXT: pmuv3 FEAT_PMUv3 Enable Armv8.0-A PMUv3 Performance Monitors extension
// CHECK-NEXT: pops FEAT_PoPS Enable Armv9.6-A Point Of Physical Storage (PoPS) DC instructions
+// CHECK-NEXT: sme-mop4 FEAT_SME_MOP4 Enable SME Quarter-tile outer product instructions
+// CHECK-NEXT: sme-tmop FEAT_SME_TMOP Enable SME Structured sparsity outer product instructions
// CHECK-NEXT: predres FEAT_SPECRES Enable Armv8.5-A execution and data prediction invalidation instructions
// CHECK-NEXT: rng FEAT_RNG Enable Random Number generation instructions
// CHECK-NEXT: ras FEAT_RAS, FEAT_RASv1p1 Enable Armv8.0-A Reliability, Availability and Serviceability Extensions
diff --git a/llvm/lib/Target/AArch64/AArch64.td b/llvm/lib/Target/AArch64/AArch64.td
index e3dd334e7b098b..67cc98965b5799 100644
--- a/llvm/lib/Target/AArch64/AArch64.td
+++ b/llvm/lib/Target/AArch64/AArch64.td
@@ -74,7 +74,8 @@ def SVEUnsupported : AArch64Unsupported {
}
let F = [HasSME2p2, HasSVE2p2orSME2p2, HasNonStreamingSVEorSME2p2,
- HasNonStreamingSVE2p2orSME2p2] in
+ HasNonStreamingSVE2p2orSME2p2, HasSME2p2orSME_MOP4,
+ HasSME2p2orSME_TMOP] in
def SME2p2Unsupported : AArch64Unsupported;
def SME2p1Unsupported : AArch64Unsupported {
diff --git a/llvm/lib/Target/AArch64/AArch64Features.td b/llvm/lib/Target/AArch64/AArch64Features.td
index 41eb9a73bd013d..e9606c2db60673 100644
--- a/llvm/lib/Target/AArch64/AArch64Features.td
+++ b/llvm/lib/Target/AArch64/AArch64Features.td
@@ -565,6 +565,12 @@ def FeaturePCDPHINT: ExtensionWithMArch<"pcdphint", "PCDPHINT", "FEAT_PCDPHINT",
def FeaturePoPS: ExtensionWithMArch<"pops", "PoPS", "FEAT_PoPS",
"Enable Armv9.6-A Point Of Physical Storage (PoPS) DC instructions">;
+def FeatureSME_MOP4: ExtensionWithMArch<"sme-mop4", "SME_MOP4", "FEAT_SME_MOP4",
+ "Enable SME Quarter-tile outer product instructions", [FeatureSME2]>;
+
+def FeatureSME_TMOP: ExtensionWithMArch<"sme-tmop", "SME_TMOP", "FEAT_SME_TMOP",
+ "Enable SME Structured sparsity outer product instructions.", [FeatureSME2]>;
+
//===----------------------------------------------------------------------===//
// Other Features
//===----------------------------------------------------------------------===//
diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.td b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
index c6f5cdcd1d5fe7..3983665c69b2cb 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
@@ -286,6 +286,14 @@ def HasNonStreamingSVE2p2orSME2p2
"(Subtarget->isSVEorStreamingSVEAvailable() && Subtarget->hasSME2p2())">,
AssemblerPredicateWithAll<(any_of FeatureSVE2p2, FeatureSME2p2),
"sme2p2 or sve2p2">;
+def HasSME2p2orSME_MOP4
+ : Predicate<"(Subtarget->isStreaming() &&"
+ "(Subtarget->hasSME2p2() || Subtarget->hasSME_MOP4()))">,
+ AssemblerPredicateWithAll<(any_of FeatureSME2p2, FeatureSME_MOP4), "sme2p2 or sme-mop4">;
+def HasSME2p2orSME_TMOP
+ : Predicate<"(Subtarget->isStreaming() &&"
+ "(Subtarget->hasSME2p2()) || Subtarget->hasSME_TMOP()))">,
+ AssemblerPredicateWithAll<(any_of FeatureSME2p2, FeatureSME_TMOP), "sme2p2 or sme-tmop">;
// A subset of NEON instructions are legal in Streaming SVE execution mode,
// so don't need the additional check for 'isNeonAvailable'.
diff --git a/llvm/lib/Target/AArch64/AArch64SMEInstrInfo.td b/llvm/lib/Target/AArch64/AArch64SMEInstrInfo.td
index aee54ed47a3ab4..33a032974c4594 100644
--- a/llvm/lib/Target/AArch64/AArch64SMEInstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64SMEInstrInfo.td
@@ -147,7 +147,7 @@ defm USMOPA_MPPZZ_D : sme_int_outer_product_i64<0b100, "usmopa", int_aarch64_sme
defm USMOPS_MPPZZ_D : sme_int_outer_product_i64<0b101, "usmops", int_aarch64_sme_usmops_wide>;
}
-let Predicates = [HasSME2p2] in {
+let Predicates = [HasSME2p2orSME_MOP4] in {
defm SMOP4A : sme_quarter_outer_product_i8_i32<0b0, 0b0, 0b0, "smop4a">;
defm SMOP4S : sme_quarter_outer_product_i8_i32<0b0, 0b0, 0b1, "smop4s">;
defm SUMOP4A : sme_quarter_outer_product_i8_i32<0b0, 0b1, 0b0, "sumop4a">;
@@ -163,7 +163,7 @@ let Predicates = [HasSME2p2] in {
defm UMOP4S : sme_quarter_outer_product_i16_i32<0b1, 0b1, "umop4s">;
}
-let Predicates = [HasSME2p2, HasSMEI16I64] in {
+let Predicates = [HasSME2p2orSME_MOP4, HasSMEI16I64] in {
defm SMOP4A : sme_quarter_outer_product_i64<0b0, 0b0, 0b0, "smop4a">;
defm SMOP4S : sme_quarter_outer_product_i64<0b0, 0b0, 0b1, "smop4s">;
defm SUMOP4A : sme_quarter_outer_product_i64<0b0, 0b1, 0b0, "sumop4a">;
@@ -174,7 +174,7 @@ let Predicates = [HasSME2p2, HasSMEI16I64] in {
defm USMOP4S : sme_quarter_outer_product_i64<0b1, 0b0, 0b1, "usmop4s">;
}
-let Predicates = [HasSME2p2] in {
+let Predicates = [HasSME2p2orSME_TMOP] in {
def STMOPA_M2ZZZI_BtoS : sme_int_sparse_outer_product_i32<0b00100, ZZ_b_mul_r, ZPR8, "stmopa">;
def STMOPA_M2ZZZI_HtoS : sme_int_sparse_outer_product_i32<0b00101, ZZ_h_mul_r, ZPR16, "stmopa">;
def UTMOPA_M2ZZZI_BtoS : sme_int_sparse_outer_product_i32<0b11100, ZZ_b_mul_r, ZPR8, "utmopa">;
@@ -1053,41 +1053,52 @@ let Predicates = [HasSME2, HasSVEBFSCALE] in {
defm BFSCALE : sme2_bfscale_multi<"bfscale">;
}
-let Predicates = [HasSME2p2] in {
+let Predicates = [HasSME2p2orSME_MOP4] in {
+ defm BFMOP4A : sme2_bfmop4as_widening<0, "bfmop4a">;
+ defm BFMOP4S : sme2_bfmop4as_widening<1, "bfmop4s">;
+
+ defm FMOP4A : sme2_fmop4as_fp16_fp32_widening<0, "fmop4a">;
+ defm FMOP4S : sme2_fmop4as_fp16_fp32_widening<1, "fmop4s">;
+
+ defm FMOP4A : sme2_fmop4as_fp32_non_widening<0, "fmop4a">;
+ defm FMOP4S : sme2_fmop4as_fp32_non_widening<1, "fmop4s">;
+}
+
+let Predicates = [HasSME2p2orSME_TMOP] in {
def FTMOPA_M2ZZZI_HtoS : sme_tmopa_32b<0b11000, ZZ_h_mul_r, ZPR16, "ftmopa">;
def FTMOPA_M2ZZZI_StoS : sme_tmopa_32b<0b00000, ZZ_s_mul_r, ZPR32, "ftmopa">;
def BFTMOPA_M2ZZZI_HtoS : sme_tmopa_32b<0b10000, ZZ_h_mul_r, ZPR16, "bftmopa">;
+}
- defm BFMOP4A : sme2_bfmop4as_widening<0, "bfmop4a">;
- defm BFMOP4S : sme2_bfmop4as_widening<1, "bfmop4s">;
-
+let Predicates = [HasSME2p2] in {
defm FMUL_2ZZ : sme2_multi2_fmul_sm<"fmul">;
defm FMUL_2Z2Z : sme2_multi2_fmul_mm< "fmul">;
defm FMUL_4ZZ : sme2_multi4_fmul_sm<"fmul">;
defm FMUL_4Z4Z : sme2_multi4_fmul_mm< "fmul">;
- defm FMOP4A : sme2_fmop4as_fp32_non_widening<0, "fmop4a">;
- defm FMOP4S : sme2_fmop4as_fp32_non_widening<1, "fmop4s">;
-
- defm FMOP4A : sme2_fmop4as_fp16_fp32_widening<0, "fmop4a">;
- defm FMOP4S : sme2_fmop4as_fp16_fp32_widening<1, "fmop4s">;
-}
+} // [HasSME2p2]
-let Predicates = [HasSME2p2, HasSMEB16B16] in {
+let Predicates = [HasSME2p2orSME_TMOP, HasSMEB16B16] in {
def BFTMOPA_M2ZZZI_HtoH : sme_tmopa_16b<0b11001, ZZ_h_mul_r, ZPR16, "bftmopa">;
}
-let Predicates = [HasSME2p2, HasSMEF8F32], Uses = [FPMR, FPCR] in {
+let Predicates = [HasSME2p2orSME_TMOP, HasSMEF8F32], Uses = [FPMR, FPCR] in {
def FTMOPA_M2ZZZI_BtoS : sme_tmopa_32b<0b01000, ZZ_b_mul_r, ZPR8, "ftmopa">;
-}
+}
-let Predicates = [HasSME2p2, HasSMEF8F16], Uses = [FPMR, FPCR] in {
+let Predicates = [HasSME2p2orSME_TMOP, HasSMEF8F16], Uses = [FPMR, FPCR] in {
def FTMOPA_M2ZZZI_BtoH : sme_tmopa_16b<0b01001, ZZ_b_mul_r, ZPR8, "ftmopa">;
+}
+
+let Predicates = [HasSME2p2orSME_MOP4, HasSMEF8F16], Uses = [FPMR, FPCR] in {
defm FMOP4A : sme2_fmop4a_fp8_fp16_2way<"fmop4a">;
}
-let Predicates = [HasSME2p2, HasSMEF16F16] in {
+let Predicates = [HasSME2p2orSME_TMOP, HasSMEF16F16] in {
def FTMOPA_M2ZZZI_HtoH : sme_tmopa_16b<0b10001, ZZ_h_mul_r, ZPR16, "ftmopa">;
+}
+
+let Predicates = [HasSME2p2orSME_MOP4, HasSMEF16F16] in {
defm FMOP4A : sme2_fmop4as_fp16_non_widening<0, "fmop4a">;
defm FMOP4S : sme2_fmop4as_fp16_non_widening<1, "fmop4s">;
}
@@ -1098,17 +1109,17 @@ let Predicates = [HasSME2, HasSVEBFSCALE] in {
}
let Uses = [FPMR, FPCR] in {
-let Predicates = [HasSME2p2, HasSMEF8F32] in {
+let Predicates = [HasSME2p2orSME_MOP4, HasSMEF8F32] in {
defm FMOP4A : sme2_fmop4a_fp8_fp32_4way<"fmop4a">;
}
}
-let Predicates = [HasSME2p2, HasSMEB16B16] in {
+let Predicates = [HasSME2p2orSME_MOP4, HasSMEB16B16] in {
defm BFMOP4A : sme2_bfmop4as_non_widening<0, "bfmop4a">;
defm BFMOP4S : sme2_bfmop4as_non_widening<1, "bfmop4s">;
}
-let Predicates = [HasSME2p2, HasSMEF64F64] in {
+let Predicates = [HasSME2p2orSME_MOP4, HasSMEF64F64] in {
defm FMOP4A : sme2_fmop4as_fp64_non_widening<0, "fmop4a">;
defm FMOP4S : sme2_fmop4as_fp64_non_widening<1, "fmop4s">;
}
diff --git a/llvm/lib/Target/AArch64/AsmParser/AArch64AsmParser.cpp b/llvm/lib/Target/AArch64/AsmParser/AArch64AsmParser.cpp
index f44afd804c2bde..8b0296f7c788e9 100644
--- a/llvm/lib/Target/AArch64/AsmParser/AArch64AsmParser.cpp
+++ b/llvm/lib/Target/AArch64/AsmParser/AArch64AsmParser.cpp
@@ -3827,6 +3827,8 @@ static const struct Extension {
{"lsui", {AArch64::FeatureLSUI}},
{"occmo", {AArch64::FeatureOCCMO}},
{"pcdphint", {AArch64::FeaturePCDPHINT}},
+ {"sme-mop4", {AArch64::FeatureSME_MOP4}},
+ {"sme-tmop", {AArch64::FeatureSME_TMOP}},
};
static void setRequiredFeatureString(FeatureBitset FBS, std::string &Str) {
diff --git a/llvm/test/MC/AArch64/SME2p2/bfmop4as-non-widening.s b/llvm/test/MC/AArch64/SME2p2/bfmop4as-non-widening.s
index b98bb99def0569..eb3382b67e9cfd 100644
--- a/llvm/test/MC/AArch64/SME2p2/bfmop4as-non-widening.s
+++ b/llvm/test/MC/AArch64/SME2p2/bfmop4as-non-widening.s
@@ -1,5 +1,7 @@
// RUN: llvm-mc -triple=aarch64 -show-encoding -mattr=+sme2p2,+sme-b16b16 < %s \
// RUN: | FileCheck %s --check-prefixes=CHECK-ENCODING,CHECK-INST
+// RUN: llvm-mc -triple=aarch64 -show-encoding -mattr=+sme-mop4,+sme-b16b16 < %s \
+// RUN: | FileCheck %s --check-prefixes=CHECK-ENCODING,CHECK-INST
// RUN: not llvm-mc -triple=aarch64 -show-encoding < %s 2>&1 \
// RUN: | FileCheck %s --check-prefix=CHECK-ERROR
// RUN: llvm-mc -triple=aarch64 -filetype=obj -mattr=+sme2p2,+sme-b16b16 < %s \
@@ -19,19 +21,19 @@
bfmop4a za0.h, z0.h, z16.h // 10000001-00100000-00000000-00001000
// CHECK-INST: bfmop4a za0.h, z0.h, z16.h
// CHECK-ENCODING: [0x08,0x00,0x20,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 81200008 <unknown>
bfmop4a za1.h, z12.h, z24.h // 10000001-00101000-00000001-10001001
// CHECK-INST: bfmop4a za1.h, z12.h, z24.h
// CHECK-ENCODING: [0x89,0x01,0x28,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 81280189 <unknown>
bfmop4a za1.h, z14.h, z30.h // 10000001-00101110-00000001-11001001
// CHECK-INST: bfmop4a za1.h, z14.h, z30.h
// CHECK-ENCODING: [0xc9,0x01,0x2e,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 812e01c9 <unknown>
// Single and multiple vectors
@@ -39,19 +41,19 @@ bfmop4a za1.h, z14.h, z30.h // 10000001-00101110-00000001-11001001
bfmop4a za0.h, z0.h, {z16.h-z17.h} // 10000001-00110000-00000000-00001000
// CHECK-INST: bfmop4a za0.h, z0.h, { z16.h, z17.h }
// CHECK-ENCODING: [0x08,0x00,0x30,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 81300008 <unknown>
bfmop4a za1.h, z12.h, {z24.h-z25.h} // 10000001-00111000-00000001-10001001
// CHECK-INST: bfmop4a za1.h, z12.h, { z24.h, z25.h }
// CHECK-ENCODING: [0x89,0x01,0x38,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 81380189 <unknown>
bfmop4a za1.h, z14.h, {z30.h-z31.h} // 10000001-00111110-00000001-11001001
// CHECK-INST: bfmop4a za1.h, z14.h, { z30.h, z31.h }
// CHECK-ENCODING: [0xc9,0x01,0x3e,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 813e01c9 <unknown>
// Multiple and single vectors
@@ -59,19 +61,19 @@ bfmop4a za1.h, z14.h, {z30.h-z31.h} // 10000001-00111110-00000001-11001001
bfmop4a za0.h, {z0.h-z1.h}, z16.h // 10000001-00100000-00000010-00001000
// CHECK-INST: bfmop4a za0.h, { z0.h, z1.h }, z16.h
// CHECK-ENCODING: [0x08,0x02,0x20,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 81200208 <unknown>
bfmop4a za1.h, {z12.h-z13.h}, z24.h // 10000001-00101000-00000011-10001001
// CHECK-INST: bfmop4a za1.h, { z12.h, z13.h }, z24.h
// CHECK-ENCODING: [0x89,0x03,0x28,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 81280389 <unknown>
bfmop4a za1.h, {z14.h-z15.h}, z30.h // 10000001-00101110-00000011-11001001
// CHECK-INST: bfmop4a za1.h, { z14.h, z15.h }, z30.h
// CHECK-ENCODING: [0xc9,0x03,0x2e,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 812e03c9 <unknown>
// Multiple vectors
@@ -79,19 +81,19 @@ bfmop4a za1.h, {z14.h-z15.h}, z30.h // 10000001-00101110-00000011-11001001
bfmop4a za0.h, {z0.h-z1.h}, {z16.h-z17.h} // 10000001-00110000-00000010-00001000
// CHECK-INST: bfmop4a za0.h, { z0.h, z1.h }, { z16.h, z17.h }
// CHECK-ENCODING: [0x08,0x02,0x30,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 81300208 <unknown>
bfmop4a za1.h, {z12.h-z13.h}, {z24.h-z25.h} // 10000001-00111000-00000011-10001001
// CHECK-INST: bfmop4a za1.h, { z12.h, z13.h }, { z24.h, z25.h }
// CHECK-ENCODING: [0x89,0x03,0x38,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 81380389 <unknown>
bfmop4a za1.h, {z14.h-z15.h}, {z30.h-z31.h} // 10000001-00111110-00000011-11001001
// CHECK-INST: bfmop4a za1.h, { z14.h, z15.h }, { z30.h, z31.h }
// CHECK-ENCODING: [0xc9,0x03,0x3e,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 813e03c9 <unknown>
@@ -102,19 +104,19 @@ bfmop4a za1.h, {z14.h-z15.h}, {z30.h-z31.h} // 10000001-00111110-00000011-11001
bfmop4s za0.h, z0.h, z16.h // 10000001-00100000-00000000-00011000
// CHECK-INST: bfmop4s za0.h, z0.h, z16.h
// CHECK-ENCODING: [0x18,0x00,0x20,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 81200018 <unknown>
bfmop4s za1.h, z12.h, z24.h // 10000001-00101000-00000001-10011001
// CHECK-INST: bfmop4s za1.h, z12.h, z24.h
// CHECK-ENCODING: [0x99,0x01,0x28,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 81280199 <unknown>
bfmop4s za1.h, z14.h, z30.h // 10000001-00101110-00000001-11011001
// CHECK-INST: bfmop4s za1.h, z14.h, z30.h
// CHECK-ENCODING: [0xd9,0x01,0x2e,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 812e01d9 <unknown>
// Single and multiple vectors
@@ -122,19 +124,19 @@ bfmop4s za1.h, z14.h, z30.h // 10000001-00101110-00000001-11011001
bfmop4s za0.h, z0.h, {z16.h-z17.h} // 10000001-00110000-00000000-00011000
// CHECK-INST: bfmop4s za0.h, z0.h, { z16.h, z17.h }
// CHECK-ENCODING: [0x18,0x00,0x30,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 81300018 <unknown>
bfmop4s za1.h, z12.h, {z24.h-z25.h} // 10000001-00111000-00000001-10011001
// CHECK-INST: bfmop4s za1.h, z12.h, { z24.h, z25.h }
// CHECK-ENCODING: [0x99,0x01,0x38,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 81380199 <unknown>
bfmop4s za1.h, z14.h, {z30.h-z31.h} // 10000001-00111110-00000001-11011001
// CHECK-INST: bfmop4s za1.h, z14.h, { z30.h, z31.h }
// CHECK-ENCODING: [0xd9,0x01,0x3e,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 813e01d9 <unknown>
// Multiple and single vectors
@@ -142,19 +144,19 @@ bfmop4s za1.h, z14.h, {z30.h-z31.h} // 10000001-00111110-00000001-11011001
bfmop4s za0.h, {z0.h-z1.h}, z16.h // 10000001-00100000-00000010-00011000
// CHECK-INST: bfmop4s za0.h, { z0.h, z1.h }, z16.h
// CHECK-ENCODING: [0x18,0x02,0x20,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 81200218 <unknown>
bfmop4s za1.h, {z12.h-z13.h}, z24.h // 10000001-00101000-00000011-10011001
// CHECK-INST: bfmop4s za1.h, { z12.h, z13.h }, z24.h
// CHECK-ENCODING: [0x99,0x03,0x28,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 81280399 <unknown>
bfmop4s za1.h, {z14.h-z15.h}, z30.h // 10000001-00101110-00000011-11011001
// CHECK-INST: bfmop4s za1.h, { z14.h, z15.h }, z30.h
// CHECK-ENCODING: [0xd9,0x03,0x2e,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 812e03d9 <unknown>
// Multiple vectors
@@ -162,17 +164,17 @@ bfmop4s za1.h, {z14.h-z15.h}, z30.h // 10000001-00101110-00000011-11011001
bfmop4s za0.h, {z0.h-z1.h}, {z16.h-z17.h} // 10000001-00110000-00000010-00011000
// CHECK-INST: bfmop4s za0.h, { z0.h, z1.h }, { z16.h, z17.h }
// CHECK-ENCODING: [0x18,0x02,0x30,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 81300218 <unknown>
bfmop4s za1.h, {z12.h-z13.h}, {z24.h-z25.h} // 10000001-00111000-00000011-10011001
// CHECK-INST: bfmop4s za1.h, { z12.h, z13.h }, { z24.h, z25.h }
// CHECK-ENCODING: [0x99,0x03,0x38,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 81380399 <unknown>
bfmop4s za1.h, {z14.h-z15.h}, {z30.h-z31.h} // 10000001-00111110-00000011-11011001
// CHECK-INST: bfmop4s za1.h, { z14.h, z15.h }, { z30.h, z31.h }
// CHECK-ENCODING: [0xd9,0x03,0x3e,0x81]
-// CHECK-ERROR: instruction requires: sme2p2 sme-b16b16
+// CHECK-ERROR: instruction requires: sme2p2 or sme-mop4 sme-b16b16
// CHECK-UNKNOWN: 813e03d9 <unknown>
diff --git a/llvm/test/MC/AArch64/SME2p2/bfmop4as-widening.s b/llvm/test/MC/AArch64/SME2p2/bfmop4as-widening.s
index 40d08e503c8bb3..b550342a71c77a 100644
--- a/llvm/test/MC/AArch64/SME2p2/bfmop4as-widening.s
+++ b/llvm/test/MC/AArch64/SME2p2/bfmop4as-widening.s
@@ -1,5 +1,7 @@
// RUN: llvm-mc -triple=aarch64 -show-encoding -mattr=+sme2p2 < %s \
// RUN: | FileCheck %s --check-prefixes=CHECK-ENCODING,CHECK-INST
+// RUN: llvm-mc -triple=aarch64 -show-encoding -mattr=+sme-mop4 < %s \
+// RUN: | FileCheck %s --check-prefixes=CHECK-ENCODING,CHECK-...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/121935
More information about the llvm-commits
mailing list