[llvm] [llvm][ScheduleDAG] SUnit::biasCriticalPath() does not find the critical path consistently (PR #93001)
via llvm-commits
llvm-commits at lists.llvm.org
Wed May 22 00:59:05 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
@llvm/pr-subscribers-backend-x86
Author: None (csstormq)
<details>
<summary>Changes</summary>
Patch co-authored by AtariDreams (gfunni234@<!-- -->gmail.com).
Fixes #<!-- -->38037.
[AMDGPU] Update test results to fix build (#<!-- -->92982)
---
Patch is 255.78 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/93001.diff
7 Files Affected:
- (modified) llvm/lib/CodeGen/ScheduleDAG.cpp (+3-1)
- (modified) llvm/test/CodeGen/AMDGPU/fp_to_sint.ll (+196-199)
- (modified) llvm/test/CodeGen/AMDGPU/fp_to_uint.ll (+196-199)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.exp.ll (+788-804)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.exp10.ll (+788-804)
- (modified) llvm/test/CodeGen/AMDGPU/shl.ll (+109-107)
- (added) llvm/test/CodeGen/X86/misched-critical-path.ll (+240)
``````````diff
diff --git a/llvm/lib/CodeGen/ScheduleDAG.cpp b/llvm/lib/CodeGen/ScheduleDAG.cpp
index de8e6f63794dc..8d9a5041fc2fe 100644
--- a/llvm/lib/CodeGen/ScheduleDAG.cpp
+++ b/llvm/lib/CodeGen/ScheduleDAG.cpp
@@ -331,8 +331,10 @@ void SUnit::biasCriticalPath() {
unsigned MaxDepth = BestI->getSUnit()->getDepth();
for (SUnit::pred_iterator I = std::next(BestI), E = Preds.end(); I != E;
++I) {
- if (I->getKind() == SDep::Data && I->getSUnit()->getDepth() > MaxDepth)
+ if (I->getKind() == SDep::Data && I->getSUnit()->getDepth() > MaxDepth) {
+ MaxDepth = I->getSUnit()->getDepth();
BestI = I;
+ }
}
if (BestI != Preds.begin())
std::swap(*Preds.begin(), *BestI);
diff --git a/llvm/test/CodeGen/AMDGPU/fp_to_sint.ll b/llvm/test/CodeGen/AMDGPU/fp_to_sint.ll
index 64063f65e288f..04ef30bd26aa5 100644
--- a/llvm/test/CodeGen/AMDGPU/fp_to_sint.ll
+++ b/llvm/test/CodeGen/AMDGPU/fp_to_sint.ll
@@ -253,25 +253,25 @@ define amdgpu_kernel void @fp_to_sint_i64 (ptr addrspace(1) %out, float %in) {
; EG-NEXT: ADD_INT * T2.W, PV.W, literal.y,
; EG-NEXT: 8388608(1.175494e-38), -150(nan)
; EG-NEXT: ADD_INT T0.X, T0.W, literal.x,
-; EG-NEXT: SUB_INT T0.Y, literal.y, T0.W,
-; EG-NEXT: AND_INT T0.Z, PS, literal.z,
+; EG-NEXT: AND_INT T0.Y, PS, literal.y,
+; EG-NEXT: SUB_INT T0.Z, literal.z, T0.W,
; EG-NEXT: NOT_INT T0.W, PS,
; EG-NEXT: LSHR * T3.W, PV.W, 1,
-; EG-NEXT: -127(nan), 150(2.101948e-43)
-; EG-NEXT: 31(4.344025e-44), 0(0.000000e+00)
+; EG-NEXT: -127(nan), 31(4.344025e-44)
+; EG-NEXT: 150(2.101948e-43), 0(0.000000e+00)
; EG-NEXT: BIT_ALIGN_INT T1.X, 0.0, PS, PV.W,
-; EG-NEXT: LSHL T1.Y, T1.W, PV.Z,
-; EG-NEXT: AND_INT T0.Z, T2.W, literal.x, BS:VEC_120/SCL_212
-; EG-NEXT: BIT_ALIGN_INT T0.W, 0.0, T1.W, PV.Y, BS:VEC_021/SCL_122
-; EG-NEXT: AND_INT * T1.W, PV.Y, literal.x,
+; EG-NEXT: AND_INT T1.Y, PV.Z, literal.x,
+; EG-NEXT: BIT_ALIGN_INT T0.Z, 0.0, T1.W, PV.Z,
+; EG-NEXT: LSHL T0.W, T1.W, PV.Y,
+; EG-NEXT: AND_INT * T1.W, T2.W, literal.x,
; EG-NEXT: 32(4.484155e-44), 0(0.000000e+00)
; EG-NEXT: CNDE_INT T0.Y, PS, PV.W, 0.0,
-; EG-NEXT: CNDE_INT T1.Z, PV.Z, PV.Y, 0.0,
-; EG-NEXT: CNDE_INT T0.W, PV.Z, PV.X, PV.Y,
+; EG-NEXT: CNDE_INT T0.Z, PV.Y, PV.Z, 0.0,
+; EG-NEXT: CNDE_INT T0.W, PS, PV.X, PV.W,
; EG-NEXT: SETGT_INT * T1.W, T0.X, literal.x,
; EG-NEXT: 23(3.222986e-44), 0(0.000000e+00)
-; EG-NEXT: CNDE_INT T0.Z, PS, 0.0, PV.W,
-; EG-NEXT: CNDE_INT T0.W, PS, PV.Y, PV.Z,
+; EG-NEXT: CNDE_INT T1.Z, PS, 0.0, PV.W,
+; EG-NEXT: CNDE_INT T0.W, PS, PV.Z, PV.Y,
; EG-NEXT: ASHR * T1.W, KC0[2].Z, literal.x,
; EG-NEXT: 31(4.344025e-44), 0(0.000000e+00)
; EG-NEXT: XOR_INT T0.W, PV.W, PS,
@@ -364,79 +364,78 @@ define amdgpu_kernel void @fp_to_sint_v2i64(ptr addrspace(1) %out, <2 x float> %
;
; EG-LABEL: fp_to_sint_v2i64:
; EG: ; %bb.0:
-; EG-NEXT: ALU 75, @4, KC0[CB0:0-32], KC1[]
+; EG-NEXT: ALU 74, @4, KC0[CB0:0-32], KC1[]
; EG-NEXT: MEM_RAT_CACHELESS STORE_RAW T1.XYZW, T0.X, 1
; EG-NEXT: CF_END
; EG-NEXT: PAD
; EG-NEXT: ALU clause starting at 4:
; EG-NEXT: MOV * T0.W, literal.x,
; EG-NEXT: 8(1.121039e-44), 0(0.000000e+00)
-; EG-NEXT: BFE_UINT * T1.W, KC0[2].W, literal.x, PV.W,
-; EG-NEXT: 23(3.222986e-44), 0(0.000000e+00)
-; EG-NEXT: AND_INT T0.Z, KC0[2].W, literal.x,
-; EG-NEXT: BFE_UINT T0.W, KC0[3].X, literal.y, T0.W,
-; EG-NEXT: ADD_INT * T2.W, PV.W, literal.z,
-; EG-NEXT: 8388607(1.175494e-38), 23(3.222986e-44)
+; EG-NEXT: BFE_UINT T0.Z, KC0[3].X, literal.x, PV.W,
+; EG-NEXT: BFE_UINT T0.W, KC0[2].W, literal.x, PV.W,
+; EG-NEXT: AND_INT * T1.Z, KC0[2].W, literal.y,
+; EG-NEXT: 23(3.222986e-44), 8388607(1.175494e-38)
+; EG-NEXT: ADD_INT T1.W, PV.W, literal.x,
+; EG-NEXT: ADD_INT * T2.W, PV.Z, literal.x,
; EG-NEXT: -150(nan), 0(0.000000e+00)
-; EG-NEXT: SUB_INT T0.X, literal.x, PV.W,
-; EG-NEXT: SUB_INT T0.Y, literal.x, T1.W,
-; EG-NEXT: AND_INT T1.Z, PS, literal.y,
-; EG-NEXT: OR_INT T3.W, PV.Z, literal.z,
+; EG-NEXT: AND_INT T0.X, PS, literal.x,
+; EG-NEXT: AND_INT T0.Y, PV.W, literal.x,
+; EG-NEXT: OR_INT T1.Z, T1.Z, literal.y,
+; EG-NEXT: SUB_INT T3.W, literal.z, T0.W,
; EG-NEXT: AND_INT * T4.W, KC0[3].X, literal.w,
-; EG-NEXT: 150(2.101948e-43), 31(4.344025e-44)
-; EG-NEXT: 8388608(1.175494e-38), 8388607(1.175494e-38)
+; EG-NEXT: 31(4.344025e-44), 8388608(1.175494e-38)
+; EG-NEXT: 150(2.101948e-43), 8388607(1.175494e-38)
; EG-NEXT: OR_INT T1.X, PS, literal.x,
-; EG-NEXT: LSHL T1.Y, PV.W, PV.Z,
-; EG-NEXT: AND_INT T0.Z, T2.W, literal.y,
-; EG-NEXT: BIT_ALIGN_INT T4.W, 0.0, PV.W, PV.Y,
-; EG-NEXT: AND_INT * T5.W, PV.Y, literal.y,
+; EG-NEXT: AND_INT T1.Y, PV.W, literal.y,
+; EG-NEXT: BIT_ALIGN_INT T2.Z, 0.0, PV.Z, PV.W,
+; EG-NEXT: LSHL T3.W, PV.Z, PV.Y,
+; EG-NEXT: AND_INT * T4.W, T1.W, literal.y,
; EG-NEXT: 8388608(1.175494e-38), 32(4.484155e-44)
-; EG-NEXT: CNDE_INT T2.X, PS, PV.W, 0.0,
-; EG-NEXT: CNDE_INT T0.Y, PV.Z, PV.Y, 0.0,
-; EG-NEXT: ADD_INT T1.Z, T0.W, literal.x,
-; EG-NEXT: BIT_ALIGN_INT T4.W, 0.0, PV.X, T0.X,
-; EG-NEXT: AND_INT * T5.W, T0.X, literal.y,
-; EG-NEXT: -150(nan), 32(4.484155e-44)
+; EG-NEXT: CNDE_INT T0.Y, PS, PV.W, 0.0,
+; EG-NEXT: CNDE_INT T2.Z, PV.Y, PV.Z, 0.0,
+; EG-NEXT: LSHL T5.W, PV.X, T0.X,
+; EG-NEXT: AND_INT * T6.W, T2.W, literal.x,
+; EG-NEXT: 32(4.484155e-44), 0(0.000000e+00)
; EG-NEXT: CNDE_INT T0.X, PS, PV.W, 0.0,
-; EG-NEXT: NOT_INT T2.Y, T2.W,
-; EG-NEXT: AND_INT T2.Z, PV.Z, literal.x,
-; EG-NEXT: NOT_INT T2.W, PV.Z,
-; EG-NEXT: LSHR * T4.W, T1.X, 1,
-; EG-NEXT: 31(4.344025e-44), 0(0.000000e+00)
-; EG-NEXT: LSHR T3.X, T3.W, 1,
-; EG-NEXT: ADD_INT T3.Y, T0.W, literal.x, BS:VEC_120/SCL_212
-; EG-NEXT: BIT_ALIGN_INT T3.Z, 0.0, PS, PV.W,
-; EG-NEXT: LSHL T0.W, T1.X, PV.Z,
-; EG-NEXT: AND_INT * T2.W, T1.Z, literal.y,
+; EG-NEXT: NOT_INT T1.Y, T1.W,
+; EG-NEXT: SUB_INT T3.Z, literal.x, T0.Z,
+; EG-NEXT: NOT_INT T1.W, T2.W, BS:VEC_120/SCL_212
+; EG-NEXT: LSHR * T2.W, T1.X, 1,
+; EG-NEXT: 150(2.101948e-43), 0(0.000000e+00)
+; EG-NEXT: LSHR T2.X, T1.Z, 1,
+; EG-NEXT: ADD_INT T2.Y, T0.Z, literal.x, BS:VEC_120/SCL_212
+; EG-NEXT: BIT_ALIGN_INT T0.Z, 0.0, PS, PV.W,
+; EG-NEXT: BIT_ALIGN_INT T1.W, 0.0, T1.X, PV.Z,
+; EG-NEXT: AND_INT * T2.W, PV.Z, literal.y,
; EG-NEXT: -127(nan), 32(4.484155e-44)
; EG-NEXT: CNDE_INT T1.X, PS, PV.W, 0.0,
-; EG-NEXT: CNDE_INT T4.Y, PS, PV.Z, PV.W,
-; EG-NEXT: SETGT_INT T1.Z, PV.Y, literal.x,
-; EG-NEXT: BIT_ALIGN_INT T0.W, 0.0, PV.X, T2.Y,
-; EG-NEXT: ADD_INT * T1.W, T1.W, literal.y,
+; EG-NEXT: CNDE_INT T3.Y, T6.W, PV.Z, T5.W, BS:VEC_021/SCL_122
+; EG-NEXT: SETGT_INT T0.Z, PV.Y, literal.x,
+; EG-NEXT: BIT_ALIGN_INT T1.W, 0.0, PV.X, T1.Y,
+; EG-NEXT: ADD_INT * T0.W, T0.W, literal.y,
; EG-NEXT: 23(3.222986e-44), -127(nan)
-; EG-NEXT: CNDE_INT T3.X, T0.Z, PV.W, T1.Y,
+; EG-NEXT: CNDE_INT T2.X, T4.W, PV.W, T3.W,
; EG-NEXT: SETGT_INT T1.Y, PS, literal.x,
-; EG-NEXT: CNDE_INT T0.Z, PV.Z, 0.0, PV.Y,
-; EG-NEXT: CNDE_INT T0.W, PV.Z, T0.X, PV.X,
+; EG-NEXT: CNDE_INT T1.Z, PV.Z, 0.0, PV.Y,
+; EG-NEXT: CNDE_INT T1.W, PV.Z, PV.X, T0.X,
; EG-NEXT: ASHR * T2.W, KC0[3].X, literal.y,
; EG-NEXT: 23(3.222986e-44), 31(4.344025e-44)
; EG-NEXT: XOR_INT T0.X, PV.W, PS,
-; EG-NEXT: XOR_INT T2.Y, PV.Z, PS,
+; EG-NEXT: XOR_INT T3.Y, PV.Z, PS,
; EG-NEXT: CNDE_INT T0.Z, PV.Y, 0.0, PV.X,
-; EG-NEXT: CNDE_INT T0.W, PV.Y, T2.X, T0.Y,
+; EG-NEXT: CNDE_INT T1.W, PV.Y, T2.Z, T0.Y,
; EG-NEXT: ASHR * T3.W, KC0[2].W, literal.x,
; EG-NEXT: 31(4.344025e-44), 0(0.000000e+00)
; EG-NEXT: XOR_INT T0.Y, PV.W, PS,
; EG-NEXT: XOR_INT T0.Z, PV.Z, PS,
-; EG-NEXT: SUB_INT T0.W, PV.Y, T2.W,
+; EG-NEXT: SUB_INT T1.W, PV.Y, T2.W,
; EG-NEXT: SUBB_UINT * T4.W, PV.X, T2.W,
; EG-NEXT: SUB_INT T1.Y, PV.W, PS,
-; EG-NEXT: SETGT_INT T1.Z, 0.0, T3.Y,
-; EG-NEXT: SUB_INT T0.W, PV.Z, T3.W,
+; EG-NEXT: SETGT_INT T1.Z, 0.0, T2.Y,
+; EG-NEXT: SUB_INT T1.W, PV.Z, T3.W,
; EG-NEXT: SUBB_UINT * T4.W, PV.Y, T3.W,
; EG-NEXT: SUB_INT T0.Z, PV.W, PS,
-; EG-NEXT: SETGT_INT T0.W, 0.0, T1.W,
+; EG-NEXT: SETGT_INT T0.W, 0.0, T0.W,
; EG-NEXT: CNDE_INT * T1.W, PV.Z, PV.Y, 0.0,
; EG-NEXT: CNDE_INT T1.Y, PV.W, PV.Z, 0.0,
; EG-NEXT: SUB_INT * T2.W, T0.X, T2.W,
@@ -567,170 +566,168 @@ define amdgpu_kernel void @fp_to_sint_v4i64(ptr addrspace(1) %out, <4 x float> %
;
; EG-LABEL: fp_to_sint_v4i64:
; EG: ; %bb.0:
-; EG-NEXT: ALU 101, @6, KC0[CB0:0-32], KC1[]
-; EG-NEXT: ALU 54, @108, KC0[CB0:0-32], KC1[]
-; EG-NEXT: MEM_RAT_CACHELESS STORE_RAW T4.XYZW, T0.X, 0
-; EG-NEXT: MEM_RAT_CACHELESS STORE_RAW T6.XYZW, T2.X, 1
+; EG-NEXT: ALU 99, @6, KC0[CB0:0-32], KC1[]
+; EG-NEXT: ALU 54, @106, KC0[CB0:0-32], KC1[]
+; EG-NEXT: MEM_RAT_CACHELESS STORE_RAW T1.XYZW, T2.X, 0
+; EG-NEXT: MEM_RAT_CACHELESS STORE_RAW T6.XYZW, T0.X, 1
; EG-NEXT: CF_END
; EG-NEXT: PAD
; EG-NEXT: ALU clause starting at 6:
; EG-NEXT: MOV * T0.W, literal.x,
; EG-NEXT: 8(1.121039e-44), 0(0.000000e+00)
-; EG-NEXT: BFE_UINT T1.W, KC0[4].X, literal.x, PV.W,
-; EG-NEXT: AND_INT * T2.W, KC0[4].X, literal.y,
+; EG-NEXT: BFE_UINT T1.W, KC0[3].Z, literal.x, PV.W,
+; EG-NEXT: AND_INT * T2.W, KC0[3].Z, literal.y,
; EG-NEXT: 23(3.222986e-44), 8388607(1.175494e-38)
-; EG-NEXT: OR_INT T0.Z, PS, literal.x,
-; EG-NEXT: BFE_UINT T2.W, KC0[3].Z, literal.y, T0.W,
-; EG-NEXT: ADD_INT * T3.W, PV.W, literal.z,
-; EG-NEXT: 8388608(1.175494e-38), 23(3.222986e-44)
-; EG-NEXT: -150(nan), 0(0.000000e+00)
-; EG-NEXT: ADD_INT T0.Y, PV.W, literal.x,
-; EG-NEXT: AND_INT T1.Z, PS, literal.y,
-; EG-NEXT: NOT_INT T4.W, PS,
-; EG-NEXT: LSHR * T5.W, PV.Z, 1,
-; EG-NEXT: -127(nan), 31(4.344025e-44)
+; EG-NEXT: OR_INT T2.W, PS, literal.x,
+; EG-NEXT: ADD_INT * T3.W, PV.W, literal.y,
+; EG-NEXT: 8388608(1.175494e-38), -150(nan)
; EG-NEXT: ADD_INT T0.X, T1.W, literal.x,
-; EG-NEXT: BIT_ALIGN_INT T1.Y, 0.0, PS, PV.W,
-; EG-NEXT: AND_INT T2.Z, T3.W, literal.y, BS:VEC_201
-; EG-NEXT: LSHL T3.W, T0.Z, PV.Z,
-; EG-NEXT: SUB_INT * T1.W, literal.z, T1.W,
-; EG-NEXT: -127(nan), 32(4.484155e-44)
-; EG-NEXT: 150(2.101948e-43), 0(0.000000e+00)
-; EG-NEXT: AND_INT T1.X, PS, literal.x,
-; EG-NEXT: BIT_ALIGN_INT T2.Y, 0.0, T0.Z, PS,
-; EG-NEXT: AND_INT T0.Z, KC0[3].Z, literal.y,
-; EG-NEXT: CNDE_INT T1.W, PV.Z, PV.Y, PV.W,
-; EG-NEXT: SETGT_INT * T4.W, PV.X, literal.z,
+; EG-NEXT: BFE_UINT T0.Y, KC0[4].X, literal.y, T0.W,
+; EG-NEXT: AND_INT T0.Z, PS, literal.z,
+; EG-NEXT: NOT_INT T4.W, PS,
+; EG-NEXT: LSHR * T5.W, PV.W, 1,
+; EG-NEXT: -127(nan), 23(3.222986e-44)
+; EG-NEXT: 31(4.344025e-44), 0(0.000000e+00)
+; EG-NEXT: BIT_ALIGN_INT T1.X, 0.0, PS, PV.W,
+; EG-NEXT: AND_INT T1.Y, T3.W, literal.x,
+; EG-NEXT: LSHL T0.Z, T2.W, PV.Z, BS:VEC_120/SCL_212
+; EG-NEXT: AND_INT T3.W, KC0[4].X, literal.y,
+; EG-NEXT: ADD_INT * T4.W, PV.Y, literal.z,
; EG-NEXT: 32(4.484155e-44), 8388607(1.175494e-38)
+; EG-NEXT: -150(nan), 0(0.000000e+00)
+; EG-NEXT: AND_INT T2.Y, PS, literal.x,
+; EG-NEXT: OR_INT T1.Z, PV.W, literal.y,
+; EG-NEXT: CNDE_INT T3.W, PV.Y, PV.X, PV.Z,
+; EG-NEXT: SETGT_INT * T5.W, T0.X, literal.z,
+; EG-NEXT: 31(4.344025e-44), 8388608(1.175494e-38)
; EG-NEXT: 23(3.222986e-44), 0(0.000000e+00)
-; EG-NEXT: CNDE_INT T2.X, PS, 0.0, PV.W,
-; EG-NEXT: OR_INT T1.Y, PV.Z, literal.x,
-; EG-NEXT: ADD_INT T0.Z, T2.W, literal.y,
-; EG-NEXT: CNDE_INT T1.W, PV.X, PV.Y, 0.0,
-; EG-NEXT: CNDE_INT * T3.W, T2.Z, T3.W, 0.0,
-; EG-NEXT: 8388608(1.175494e-38), -150(nan)
-; EG-NEXT: CNDE_INT T1.X, T4.W, PV.W, PS,
-; EG-NEXT: ASHR T2.Y, KC0[4].X, literal.x,
-; EG-NEXT: AND_INT T1.Z, PV.Z, literal.x,
-; EG-NEXT: NOT_INT T1.W, PV.Z,
-; EG-NEXT: LSHR * T3.W, PV.Y, 1,
-; EG-NEXT: 31(4.344025e-44), 0(0.000000e+00)
-; EG-NEXT: BIT_ALIGN_INT T3.X, 0.0, PS, PV.W,
-; EG-NEXT: LSHL T3.Y, T1.Y, PV.Z,
-; EG-NEXT: XOR_INT T1.Z, PV.X, PV.Y,
-; EG-NEXT: XOR_INT T1.W, T2.X, PV.Y,
-; EG-NEXT: SUB_INT * T2.W, literal.x, T2.W,
-; EG-NEXT: 150(2.101948e-43), 0(0.000000e+00)
-; EG-NEXT: AND_INT T1.X, T0.Z, literal.x,
-; EG-NEXT: AND_INT T4.Y, PS, literal.x,
-; EG-NEXT: BIT_ALIGN_INT T0.Z, 0.0, T1.Y, PS, BS:VEC_021/SCL_122
-; EG-NEXT: SUB_INT T1.W, PV.W, T2.Y,
-; EG-NEXT: SUBB_UINT * T2.W, PV.Z, T2.Y,
-; EG-NEXT: 32(4.484155e-44), 0(0.000000e+00)
-; EG-NEXT: SUB_INT T2.X, PV.W, PS,
-; EG-NEXT: CNDE_INT T1.Y, PV.Y, PV.Z, 0.0,
-; EG-NEXT: CNDE_INT T0.Z, PV.X, T3.Y, 0.0,
-; EG-NEXT: CNDE_INT T1.W, PV.X, T3.X, T3.Y, BS:VEC_021/SCL_122
-; EG-NEXT: SETGT_INT * T2.W, T0.Y, literal.x,
+; EG-NEXT: CNDE_INT T3.Y, PS, 0.0, PV.W,
+; EG-NEXT: SUB_INT T2.Z, literal.x, T1.W,
+; EG-NEXT: LSHL T1.W, PV.Z, PV.Y,
+; EG-NEXT: AND_INT * T3.W, T4.W, literal.y,
+; EG-NEXT: 150(2.101948e-43), 32(4.484155e-44)
+; EG-NEXT: CNDE_INT T1.X, PS, PV.W, 0.0,
+; EG-NEXT: AND_INT T2.Y, PV.Z, literal.x,
+; EG-NEXT: SUB_INT T3.Z, literal.y, T0.Y,
+; EG-NEXT: NOT_INT T4.W, T4.W,
+; EG-NEXT: LSHR * T6.W, T1.Z, 1,
+; EG-NEXT: 32(4.484155e-44), 150(2.101948e-43)
+; EG-NEXT: BIT_ALIGN_INT T2.X, 0.0, T2.W, T2.Z,
+; EG-NEXT: ADD_INT T0.Y, T0.Y, literal.x,
+; EG-NEXT: BIT_ALIGN_INT T2.Z, 0.0, PS, PV.W,
+; EG-NEXT: BIT_ALIGN_INT T2.W, 0.0, T1.Z, PV.Z,
+; EG-NEXT: AND_INT * T4.W, PV.Z, literal.y,
+; EG-NEXT: -127(nan), 32(4.484155e-44)
+; EG-NEXT: CNDE_INT T3.X, PS, PV.W, 0.0,
+; EG-NEXT: CNDE_INT T4.Y, T3.W, PV.Z, T1.W,
+; EG-NEXT: SETGT_INT T1.Z, PV.Y, literal.x,
+; EG-NEXT: CNDE_INT T1.W, T1.Y, T0.Z, 0.0,
+; EG-NEXT: CNDE_INT * T2.W, T2.Y, PV.X, 0.0,
; EG-NEXT: 23(3.222986e-44), 0(0.000000e+00)
-; EG-NEXT: BFE_UINT T1.X, KC0[3].W, literal.x, T0.W,
-; EG-NEXT: AND_INT T3.Y, KC0[3].W, literal.y,
-; EG-NEXT: CNDE_INT T2.Z, PS, 0.0, PV.W,
-; EG-NEXT: CNDE_INT T1.W, PS, PV.Y, PV.Z,
-; EG-NEXT: ASHR * T2.W, KC0[3].Z, literal.z,
-; EG-NEXT: 23(3.222986e-44), 8388607(1.175494e-38)
+; EG-NEXT: CNDE_INT T2.X, T5.W, PS, PV.W,
+; EG-NEXT: ASHR T1.Y, KC0[3].Z, literal.x,
+; EG-NEXT: CNDE_INT T0.Z, PV.Z, 0.0, PV.Y,
+; EG-NEXT: CNDE_INT T1.W, PV.Z, PV.X, T1.X,
+; EG-NEXT: ASHR * T2.W, KC0[4].X, literal.x,
; EG-NEXT: 31(4.344025e-44), 0(0.000000e+00)
-; EG-NEXT: BFE_UINT T3.X, KC0[3].Y, literal.x, T0.W,
-; EG-NEXT: XOR_INT T1.Y, PV.W, PS,
+; EG-NEXT: XOR_INT T2.Y, PV.W, PS,
; EG-NEXT: XOR_INT T0.Z, PV.Z, PS,
-; EG-NEXT: OR_INT T0.W, PV.Y, literal.y,
-; EG-NEXT: SUB_INT * T1.W, literal.z, PV.X,
-; EG-NEXT: 23(3.222986e-44), 8388608(1.175494e-38)
+; EG-NEXT: XOR_INT T1.W, PV.X, PV.Y,
+; EG-NEXT: XOR_INT * T3.W, T3.Y, PV.Y,
+; EG-NEXT: SUB_INT T3.Y, PS, T1.Y,
+; EG-NEXT: SUBB_UINT T1.Z, PV.W, T1.Y,
+; EG-NEXT: SUB_INT T3.W, PV.Z, T2.W,
+; EG-NEXT: SUBB_UINT * T4.W, PV.Y, T2.W,
+; EG-NEXT: SUB_INT T4.Y, PV.W, PS,
+; EG-NEXT: SUB_INT T0.Z, PV.Y, PV.Z,
+; EG-NEXT: BFE_UINT T3.W, KC0[3].Y, literal.x, T0.W,
+; EG-NEXT: AND_INT * T4.W, KC0[3].Y, literal.y,
+; EG-NEXT: 23(3.222986e-44), 8388607(1.175494e-38)
+; EG-NEXT: SETGT_INT T0.X, 0.0, T0.X,
+; EG-NEXT: ADD_INT T3.Y, PV.W, literal.x,
+; EG-NEXT: OR_INT T1.Z, PS, literal.y,
+; EG-NEXT: BFE_UINT T0.W, KC0[3].W, literal.z, T0.W,
+; EG-NEXT: ADD_INT * T4.W, PV.W, literal.w,
+; EG-NEXT: -127(nan), 8388608(1.175494e-38)
+; EG-NEXT: 23(3.222986e-44), -150(nan)
+; EG-NEXT: AND_INT T1.X, KC0[3].W, literal.x,
+; EG-NEXT: ADD_INT T5.Y, PV.W, literal.y,
+; EG-NEXT: SUB_INT T2.Z, literal.z, T3.W,
+; EG-NEXT: NOT_INT T3.W, PS,
+; EG-NEXT: LSHR * T5.W, PV.Z, 1,
+; EG-NEXT: 8388607(1.175494e-38), -150(nan)
; EG-NEXT: 150(2.101948e-43), 0(0.000000e+00)
-; EG-NEXT: AND_INT T4.X, KC0[3].Y, literal.x,
-; EG-NEXT: AND_INT T3.Y, PS, literal.y,
-; EG-NEXT: BIT_ALIGN_INT T2.Z, 0.0, PV.W, PS,
-; EG-NEXT: SUB_INT T1.W, PV.Z, T2.W,
-; EG-NEXT: SUBB_UINT * T3.W, PV.Y, T2.W,
-; EG-NEXT: 8388607(1.175494e-38), 32(4.484155e-44)
-; EG-NEXT: SUB_INT T5.X, PV.W, PS,
-; EG-NEXT: SETGT_INT T0.Y, 0.0, T0.Y,
-; EG-NEXT: CNDE_INT T0.Z, PV.Y, PV.Z, 0.0,
-; EG-NEXT: OR_INT T1.W, PV.X, literal.x,
-; EG-NEXT: ADD_INT * T3.W, T3.X, literal.y,
-; EG-NEXT: 8388608(1.175494e-38), -150(nan)
-; EG-NEXT: ADD_INT T4.X, T3.X, literal.x,
-; EG-NEXT: SUB_INT T3.Y, literal.y, T3.X,
-; EG-NEXT: AND_INT T2.Z, PS, literal.z,
-; EG-NEXT: NOT_INT T4.W, PS,
-; EG-NEXT: LSHR * T5.W, PV.W, 1,
-; EG-NEXT: -127(nan), 150(2.101948e-43)
-; EG-NEXT: 31(4.344025e-44), 0(0.000000e+00)
-; EG-NEXT: BIT_ALIGN_INT T3.X, 0.0, PS, PV.W,
-; EG-NEXT: LSHL T4.Y, T1.W, PV.Z,
-; EG-NEXT: AND_INT T2.Z, T3.W, literal.x, BS:VEC_120/SCL_212
-; EG-NEXT: BIT_ALIGN_INT T1.W, 0.0, T1.W, PV.Y, BS:VEC_021/SCL_122
-; EG-NEXT: AND_INT * T3.W, PV.Y, literal.x,
+; EG-NEXT: BIT_ALIGN_INT T2.X, 0.0, PS, PV.W,
+; EG-NEXT: AND_INT T6.Y, PV.Z, literal.x,
+; EG-NEXT: AND_INT T3.Z, PV.Y, literal.y,
+; EG-NEXT: OR_INT T3.W, PV.X, literal.z,
+; EG-NEXT: AND_INT * T5.W, T4.W, literal.y,
+; EG-NEXT: 32(4.484155e-44), 31(4.344025e-44)
+; EG-NEXT: 8388608(1.175494e-38), 0(0.000000e+00)
+; EG-NEXT: BIT_ALIGN_INT T1.X, 0.0, T1.Z, T2.Z,
+; EG-NEXT: LSHL T7.Y, T1.Z, PS,
+; EG-NEXT: AND_INT T1.Z, T4.W, literal.x,
+; EG-NEXT: LSHL T4.W, PV.W, PV.Z,
+; EG-NEXT: AND_INT * T5.W, T5.Y, literal.x,
; EG-NEXT: 32(4.484155e-44), 0(0.000000e+00)
-; EG-NEXT: ADD_INT T6.X, T1.X, literal.x,
-; EG-NEXT: CNDE_INT T3.Y, PS, PV.W, 0.0,
-; EG-NEXT: CNDE_INT * T3.Z, PV.Z, PV.Y, 0.0,
-; EG-NEXT: -150(nan), 0(0.000000e+00)
-; EG-NEXT: ALU clause starting at 108:
-; EG-NEXT: CNDE_INT T1.W, T2.Z, T3.X, T4.Y,
-; EG-NEXT: SETGT_INT * T3.W, T4.X, literal.x,
+; EG-NEXT: CNDE_INT T3.X, PS, PV.W, 0.0,
+; EG-NEXT: CNDE_INT T8.Y, PV.Z, PV.Y, 0.0,
+; EG-NEXT: CNDE_INT * T2.Z, T6.Y, PV.X, 0.0,
+; EG-NEXT: ALU clause starting at 106:
+; EG-NEXT: CNDE_INT T6.W, T1.Z, T2.X, T7.Y, BS:VEC_021/SCL_122
+; EG-NEXT: SETGT_INT * T7.W, T3.Y, literal.x,
; EG-NEXT: 23(3.222986e-44), 0(0.000000e+00)
-; EG-NEXT: CNDE_INT T3.X, PS, 0.0, PV.W,
-; EG-NEXT: CNDE_INT T3.Y, PS, T3.Y, T3.Z,
-; EG-NEXT: AND_INT T2.Z, T6.X, literal.x,
-; EG-NEXT: NOT_INT T1.W, T6.X,
-; EG-NEXT: LSHR * T3.W, T0.W, 1,
-; EG-NEXT: 31(4.344025e-44), 0(0.000000e+00)
-; EG-NEXT: ASHR T7.X, KC0[3].Y, literal.x,
-; EG-NEXT: ADD_INT T4.Y, T1.X, literal.y,
-; EG-NEXT: BIT_ALIGN_INT T3.Z, 0.0, PS, PV.W,
-; EG-NEXT: LSHL T0.W, T0.W, PV.Z,
-; EG-NEXT: AND_INT * T1.W, T6.X, literal.z,
+; EG-NEXT: CNDE_INT T1.X, PS, 0.0, PV.W,
+; EG-NEXT: CNDE_INT T6.Y, PS, T2.Z, T8.Y,
+; EG-NEXT: SUB_INT T1.Z, literal.x, T0.W,
+; EG-NEXT: NOT_INT T6.W, T5.Y,
+; EG-NEXT: LSHR * T7.W, T3.W, 1,
+; EG-NEXT: 150(2.101948e-43), 0(0.000000e+00)
+; EG-NEXT: ASHR T2.X, KC0[3].Y, literal.x,
+; EG-NEXT: ADD_INT T5.Y, T0.W, literal.y,
+; EG-NEXT: BIT_ALIGN_INT T2.Z, 0.0, PS, PV.W,
+; EG-NEXT: BIT_ALIGN_INT T0.W, 0.0, T3.W, PV.Z,
+; EG-NEXT: AND_INT * T3.W, PV.Z, literal.z,
; EG-NEXT: 31(4.344025e-44), -127(nan)
; EG-NEXT: 32(4.484155e-44), 0(0.000000e+00)
-; EG-NEXT: CNDE_INT T1.X, PS, PV.W, 0.0,
-; EG-NEXT: CNDE_INT T5.Y, PS, PV.Z, PV.W,
-; EG-NEXT: SETGT_INT T2.Z, PV.Y, literal.x,
-; EG-NEXT: XOR_INT T0.W, T3.Y, PV.X,
-; EG-NEXT: XOR_INT * T1.W, T3.X, PV.X,
+; EG-NEXT: CNDE_INT T4.X, PS, PV.W, 0.0,
+; EG-NEXT: CNDE_INT T7.Y, T5.W, PV.Z, T4.W,
+; EG-NEXT: SETGT_INT T1.Z, PV.Y, literal.x,
+; EG-NEXT: XOR_INT T0.W, T6.Y, PV.X,
+; EG-NEXT: XOR_INT * T3.W, T1.X, PV.X,
; EG-NEXT: 23(3.222986e-44), 0(0.000000e+00)
-; EG-NEXT: SUB_INT T3.X, PS, T7.X,
-; EG-NEXT: SUBB_UINT T3.Y, PV.W, T7.X,
-; EG-...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/93001
More information about the llvm-commits
mailing list