[llvm] [AArch64] Update predicate for FEXPA (PR #116613)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Nov 18 05:37:49 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-mc
Author: None (Lukacma)
<details>
<summary>Changes</summary>
This patch updates predicate and backend tests for FEXPA instructions to match [latest spec](https://developer.arm.com/documentation/ddi0602/2024-09/SVE-Instructions/FEXPA--Floating-point-exponential-accelerator-).
---
Full diff: https://github.com/llvm/llvm-project/pull/116613.diff
4 Files Affected:
- (modified) llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td (+1-1)
- (added) llvm/test/CodeGen/AArch64/sve-intrinsics-fexpa.ll (+30)
- (modified) llvm/test/CodeGen/AArch64/sve-intrinsics-fp-arith.ll (-35)
- (modified) llvm/test/MC/AArch64/SVE/fexpa.s (+5-3)
``````````diff
diff --git a/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td b/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
index 8791ce6266c86c..8ea9d62f6e1c47 100644
--- a/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
@@ -971,7 +971,7 @@ let Predicates = [HasSVEorSME] in {
def MOVPRFX_ZZ : sve_int_bin_cons_misc_0_c<0b00000001, "movprfx", ZPRAny>;
} // End HasSVEorSME
-let Predicates = [HasSVE] in {
+let Predicates = [HasNonStreamingSVEorSME2p2] in {
defm FEXPA_ZZ : sve_int_bin_cons_misc_0_c_fexpa<"fexpa", int_aarch64_sve_fexpa_x>;
} // End HasSVE
diff --git a/llvm/test/CodeGen/AArch64/sve-intrinsics-fexpa.ll b/llvm/test/CodeGen/AArch64/sve-intrinsics-fexpa.ll
new file mode 100644
index 00000000000000..00e000f6423776
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/sve-intrinsics-fexpa.ll
@@ -0,0 +1,30 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnu -force-streaming -mattr=+sme2p2 < %s | FileCheck %s
+
+define <vscale x 8 x half> @fexpa_h(<vscale x 8 x i16> %a) {
+; CHECK-LABEL: fexpa_h:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fexpa z0.h, z0.h
+; CHECK-NEXT: ret
+ %out = call <vscale x 8 x half> @llvm.aarch64.sve.fexpa.x.nxv8f16(<vscale x 8 x i16> %a)
+ ret <vscale x 8 x half> %out
+}
+
+define <vscale x 4 x float> @fexpa_s(<vscale x 4 x i32> %a) {
+; CHECK-LABEL: fexpa_s:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fexpa z0.s, z0.s
+; CHECK-NEXT: ret
+ %out = call <vscale x 4 x float> @llvm.aarch64.sve.fexpa.x.nxv4f32(<vscale x 4 x i32> %a)
+ ret <vscale x 4 x float> %out
+}
+
+define <vscale x 2 x double> @fexpa_d(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a) {
+; CHECK-LABEL: fexpa_d:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fexpa z0.d, z0.d
+; CHECK-NEXT: ret
+ %out = call <vscale x 2 x double> @llvm.aarch64.sve.fexpa.x.nxv2f64(<vscale x 2 x i64> %a)
+ ret <vscale x 2 x double> %out
+}
\ No newline at end of file
diff --git a/llvm/test/CodeGen/AArch64/sve-intrinsics-fp-arith.ll b/llvm/test/CodeGen/AArch64/sve-intrinsics-fp-arith.ll
index a16f230cf8bbbc..0aeab72096caa9 100644
--- a/llvm/test/CodeGen/AArch64/sve-intrinsics-fp-arith.ll
+++ b/llvm/test/CodeGen/AArch64/sve-intrinsics-fp-arith.ll
@@ -299,37 +299,6 @@ define <vscale x 2 x double> @fdivr_d(<vscale x 2 x i1> %pg, <vscale x 2 x doubl
ret <vscale x 2 x double> %out
}
-;
-; FEXPA
-;
-
-define <vscale x 8 x half> @fexpa_h(<vscale x 8 x i16> %a) {
-; CHECK-LABEL: fexpa_h:
-; CHECK: // %bb.0:
-; CHECK-NEXT: fexpa z0.h, z0.h
-; CHECK-NEXT: ret
- %out = call <vscale x 8 x half> @llvm.aarch64.sve.fexpa.x.nxv8f16(<vscale x 8 x i16> %a)
- ret <vscale x 8 x half> %out
-}
-
-define <vscale x 4 x float> @fexpa_s(<vscale x 4 x i32> %a) {
-; CHECK-LABEL: fexpa_s:
-; CHECK: // %bb.0:
-; CHECK-NEXT: fexpa z0.s, z0.s
-; CHECK-NEXT: ret
- %out = call <vscale x 4 x float> @llvm.aarch64.sve.fexpa.x.nxv4f32(<vscale x 4 x i32> %a)
- ret <vscale x 4 x float> %out
-}
-
-define <vscale x 2 x double> @fexpa_d(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a) {
-; CHECK-LABEL: fexpa_d:
-; CHECK: // %bb.0:
-; CHECK-NEXT: fexpa z0.d, z0.d
-; CHECK-NEXT: ret
- %out = call <vscale x 2 x double> @llvm.aarch64.sve.fexpa.x.nxv2f64(<vscale x 2 x i64> %a)
- ret <vscale x 2 x double> %out
-}
-
;
; FMAD
;
@@ -1668,10 +1637,6 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.fdivr.nxv8f16(<vscale x 8 x i1>, <
declare <vscale x 4 x float> @llvm.aarch64.sve.fdivr.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fdivr.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
-declare <vscale x 8 x half> @llvm.aarch64.sve.fexpa.x.nxv8f16(<vscale x 8 x i16>)
-declare <vscale x 4 x float> @llvm.aarch64.sve.fexpa.x.nxv4f32(<vscale x 4 x i32>)
-declare <vscale x 2 x double> @llvm.aarch64.sve.fexpa.x.nxv2f64(<vscale x 2 x i64>)
-
declare <vscale x 8 x half> @llvm.aarch64.sve.fmad.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmad.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmad.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
diff --git a/llvm/test/MC/AArch64/SVE/fexpa.s b/llvm/test/MC/AArch64/SVE/fexpa.s
index 1171efc2d64668..c51b1e2b1d3e57 100644
--- a/llvm/test/MC/AArch64/SVE/fexpa.s
+++ b/llvm/test/MC/AArch64/SVE/fexpa.s
@@ -1,5 +1,7 @@
// RUN: llvm-mc -triple=aarch64 -show-encoding -mattr=+sve < %s \
// RUN: | FileCheck %s --check-prefixes=CHECK-ENCODING,CHECK-INST
+// RUN: llvm-mc -triple=aarch64 -show-encoding -mattr=+sme2p2 < %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: not llvm-mc -triple=aarch64 -show-encoding -mattr=+sme < %s 2>&1 \
@@ -12,17 +14,17 @@
fexpa z0.h, z31.h
// CHECK-INST: fexpa z0.h, z31.h
// CHECK-ENCODING: [0xe0,0xbb,0x60,0x04]
-// CHECK-ERROR: instruction requires: sve
+// CHECK-ERROR: instruction requires: sve or sme2p2
// CHECK-UNKNOWN: 0460bbe0 <unknown>
fexpa z0.s, z31.s
// CHECK-INST: fexpa z0.s, z31.s
// CHECK-ENCODING: [0xe0,0xbb,0xa0,0x04]
-// CHECK-ERROR: instruction requires: sve
+// CHECK-ERROR: instruction requires: sve or sme2p2
// CHECK-UNKNOWN: 04a0bbe0 <unknown>
fexpa z0.d, z31.d
// CHECK-INST: fexpa z0.d, z31.d
// CHECK-ENCODING: [0xe0,0xbb,0xe0,0x04]
-// CHECK-ERROR: instruction requires: sve
+// CHECK-ERROR: instruction requires: sve or sme2p2
// CHECK-UNKNOWN: 04e0bbe0 <unknown>
``````````
</details>
https://github.com/llvm/llvm-project/pull/116613
More information about the llvm-commits
mailing list