[PATCH] D40254: [MI scheduler] Fix VADD and VSUB in cortex-a57 model

[Eugene Leviant via Phabricator via llvm-commits]

evgeny777 updated this revision to Diff 123740.
evgeny777 retitled this revision from "[MI scheduler] Fix VADD in cortex-a57 model" to "[MI scheduler] Fix VADD and VSUB in cortex-a57 model".
evgeny777 added a comment.

Addressed review comments. Also added fix for VSUB, which was also broken.


https://reviews.llvm.org/D40254

Files:
  lib/Target/ARM/ARMScheduleA57.td
  test/CodeGen/ARM/cortex-a57-misched-vadd.ll
  test/CodeGen/ARM/cortex-a57-misched-vsub.ll


Index: test/CodeGen/ARM/cortex-a57-misched-vsub.ll
===================================================================
--- test/CodeGen/ARM/cortex-a57-misched-vsub.ll
+++ test/CodeGen/ARM/cortex-a57-misched-vsub.ll
@@ -0,0 +1,26 @@
+; REQUIRES: asserts
+; RUN: llc < %s -mtriple=armv8r-eabi -mcpu=cortex-a57 -misched-postra -enable-misched -verify-misched -debug-only=machine-scheduler -o - 2>&1 > /dev/null | FileCheck %s
+
+; CHECK-LABEL:  subv_i32:BB#0
+; CHECK:        SU(8): {{.*}} VSUBv4i32
+; CHECK-NEXT:   # preds left
+; CHECK-NEXT:   # succs left
+; CHECK-NEXT:   # rdefs left
+; CHECK-NEXT:   Latency : 3
+
+define <4 x i32> @subv_i32(<4 x i32>, <4 x i32>) {
+  %3 = sub <4 x i32> %1, %0
+  ret <4 x i32> %3
+}
+
+; CHECK-LABEL:  subv_f32:BB#0
+; CHECK:        SU(8): {{.*}} VSUBfq
+; CHECK-NEXT:   # preds left
+; CHECK-NEXT:   # succs left
+; CHECK-NEXT:   # rdefs left
+; CHECK-NEXT:   Latency : 5
+
+define <4 x float> @subv_f32(<4 x float>, <4 x float>) {
+  %3 = fsub <4 x float> %0, %1
+  ret <4 x float> %3
+}
Index: test/CodeGen/ARM/cortex-a57-misched-vadd.ll
===================================================================
--- test/CodeGen/ARM/cortex-a57-misched-vadd.ll
+++ test/CodeGen/ARM/cortex-a57-misched-vadd.ll
@@ -0,0 +1,26 @@
+; REQUIRES: asserts
+; RUN: llc < %s -mtriple=armv8r-eabi -mcpu=cortex-a57 -misched-postra -enable-misched -verify-misched -debug-only=machine-scheduler -o - 2>&1 > /dev/null | FileCheck %s
+
+; CHECK-LABEL:  addv_i32:BB#0
+; CHECK:        SU(8): {{.*}} VADDv4i32
+; CHECK-NEXT:   # preds left
+; CHECK-NEXT:   # succs left
+; CHECK-NEXT:   # rdefs left
+; CHECK-NEXT:   Latency : 3
+
+define <4 x i32> @addv_i32(<4 x i32>, <4 x i32>) {
+  %3 = add <4 x i32> %1, %0
+  ret <4 x i32> %3
+}
+
+; CHECK-LABEL:  addv_f32:BB#0
+; CHECK:        SU(8): {{.*}} VADDfq
+; CHECK-NEXT:   # preds left
+; CHECK-NEXT:   # succs left
+; CHECK-NEXT:   # rdefs left
+; CHECK-NEXT:   Latency : 5
+
+define <4 x float> @addv_f32(<4 x float>, <4 x float>) {
+  %3 = fadd <4 x float> %0, %1
+  ret <4 x float> %3
+}
Index: lib/Target/ARM/ARMScheduleA57.td
===================================================================
--- lib/Target/ARM/ARMScheduleA57.td
+++ lib/Target/ARM/ARMScheduleA57.td
@@ -971,9 +971,9 @@
 def : InstRW<[A57Write_3cyc_1V], (instregex "VABDL(s|u)")>;
 
 // ASIMD arith, basic
-def : InstRW<[A57Write_3cyc_1V], (instregex "VADD", "VADDL", "VADDW",
+def : InstRW<[A57Write_3cyc_1V], (instregex "VADDv", "VADDL", "VADDW",
   "VNEG(s8d|s16d|s32d|s8q|s16q|s32q|d|q)",
-  "VPADDi", "VPADDL", "VSUB", "VSUBL", "VSUBW")>;
+  "VPADDi", "VPADDL", "VSUBv", "VSUBL", "VSUBW")>;
 
 // ASIMD arith, complex
 def : InstRW<[A57Write_3cyc_1V], (instregex "VABS", "VADDHN", "VHADD", "VHSUB",


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D40254.123740.patch
Type: text/x-patch
Size: 2744 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20171121/34762034/attachment.bin>