[llvm] AMDGPU: Combine nnan fminimum/fmaximum to fminnum_ieee/fmaxnum_ieee (PR #142217)
via llvm-commits
llvm-commits at lists.llvm.org
Fri May 30 14:35:34 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Matt Arsenault (arsenm)
<details>
<summary>Changes</summary>
This improves codegen for gfx950, where fminimum/fmaximum are
legal through fminimum3/fmaximum3, so may have an additional
encoding cost.
---
Patch is 34.47 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/142217.diff
5 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/SIISelLowering.cpp (+11)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.maximum.f16.ll (+44-97)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.maximum.f32.ll (+52-113)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.minimum.f16.ll (+44-97)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.minimum.f32.ll (+52-113)
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
index c61c52ec5843e..2493b4f1bb0a7 100644
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -13822,6 +13822,17 @@ SDValue SITargetLowering::performMinMaxCombine(SDNode *N,
return Res;
}
+ // Prefer fminnum_ieee over fminimum. For gfx950, minimum/maximum are legal
+ // for some types, but at a higher cost since it's implemented with a 3
+ // operand form.
+ const SDNodeFlags Flags = N->getFlags();
+ if ((Opc == ISD::FMINIMUM || Opc == ISD::FMAXIMUM) &&
+ !Subtarget->hasIEEEMinMax() && Flags.hasNoNaNs()) {
+ unsigned NewOpc =
+ Opc == ISD::FMINIMUM ? ISD::FMINNUM_IEEE : ISD::FMAXNUM_IEEE;
+ return DAG.getNode(NewOpc, SDLoc(N), VT, Op0, Op1, Flags);
+ }
+
return SDValue();
}
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.maximum.f16.ll b/llvm/test/CodeGen/AMDGPU/llvm.maximum.f16.ll
index a56c92785d487..92a2f54841eed 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.maximum.f16.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.maximum.f16.ll
@@ -113,17 +113,11 @@ define half @v_maximum_f16__nnan(half %src0, half %src1) {
; GFX8-NEXT: v_max_f16_e32 v0, v0, v1
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_maximum_f16__nnan:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_max_f16_e32 v0, v0, v1
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_maximum_f16__nnan:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_pk_maximum3_f16 v0, v0, v1, v1
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_maximum_f16__nnan:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_max_f16_e32 v0, v0, v1
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_maximum_f16__nnan:
; GFX10: ; %bb.0:
@@ -270,17 +264,11 @@ define half @v_maximum_f16__nnan_nsz(half %src0, half %src1) {
; GFX8-NEXT: v_max_f16_e32 v0, v0, v1
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_maximum_f16__nnan_nsz:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_max_f16_e32 v0, v0, v1
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_maximum_f16__nnan_nsz:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_pk_maximum3_f16 v0, v0, v1, v1
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_maximum_f16__nnan_nsz:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_max_f16_e32 v0, v0, v1
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_maximum_f16__nnan_nsz:
; GFX10: ; %bb.0:
@@ -771,17 +759,11 @@ define <2 x half> @v_maximum_v2f16__nnan(<2 x half> %src0, <2 x half> %src1) {
; GFX8-NEXT: v_or_b32_e32 v0, v0, v2
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_maximum_v2f16__nnan:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_pk_max_f16 v0, v0, v1
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_maximum_v2f16__nnan:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_pk_maximum3_f16 v0, v0, v1, v1
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_maximum_v2f16__nnan:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_pk_max_f16 v0, v0, v1
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_maximum_v2f16__nnan:
; GFX10: ; %bb.0:
@@ -939,17 +921,11 @@ define <2 x half> @v_maximum_v2f16__nnan_nsz(<2 x half> %src0, <2 x half> %src1)
; GFX8-NEXT: v_or_b32_e32 v0, v0, v2
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_maximum_v2f16__nnan_nsz:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_pk_max_f16 v0, v0, v1
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_maximum_v2f16__nnan_nsz:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_pk_maximum3_f16 v0, v0, v1, v1
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_maximum_v2f16__nnan_nsz:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_pk_max_f16 v0, v0, v1
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_maximum_v2f16__nnan_nsz:
; GFX10: ; %bb.0:
@@ -1296,19 +1272,12 @@ define <3 x half> @v_maximum_v3f16__nnan(<3 x half> %src0, <3 x half> %src1) {
; GFX8-NEXT: v_or_b32_e32 v0, v0, v4
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_maximum_v3f16__nnan:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_pk_max_f16 v0, v0, v2
-; GFX900-NEXT: v_pk_max_f16 v1, v1, v3
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_maximum_v3f16__nnan:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_pk_maximum3_f16 v1, v1, v3, v3
-; GFX950-NEXT: v_pk_maximum3_f16 v0, v0, v2, v2
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_maximum_v3f16__nnan:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_pk_max_f16 v1, v1, v3
+; GFX9-NEXT: v_pk_max_f16 v0, v0, v2
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_maximum_v3f16__nnan:
; GFX10: ; %bb.0:
@@ -1501,19 +1470,12 @@ define <3 x half> @v_maximum_v3f16__nnan_nsz(<3 x half> %src0, <3 x half> %src1)
; GFX8-NEXT: v_or_b32_e32 v0, v0, v4
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_maximum_v3f16__nnan_nsz:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_pk_max_f16 v0, v0, v2
-; GFX900-NEXT: v_pk_max_f16 v1, v1, v3
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_maximum_v3f16__nnan_nsz:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_pk_maximum3_f16 v1, v1, v3, v3
-; GFX950-NEXT: v_pk_maximum3_f16 v0, v0, v2, v2
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_maximum_v3f16__nnan_nsz:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_pk_max_f16 v1, v1, v3
+; GFX9-NEXT: v_pk_max_f16 v0, v0, v2
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_maximum_v3f16__nnan_nsz:
; GFX10: ; %bb.0:
@@ -1741,19 +1703,12 @@ define <4 x half> @v_maximum_v4f16__nnan(<4 x half> %src0, <4 x half> %src1) {
; GFX8-NEXT: v_or_b32_e32 v1, v1, v4
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_maximum_v4f16__nnan:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_pk_max_f16 v0, v0, v2
-; GFX900-NEXT: v_pk_max_f16 v1, v1, v3
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_maximum_v4f16__nnan:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_pk_maximum3_f16 v0, v0, v2, v2
-; GFX950-NEXT: v_pk_maximum3_f16 v1, v1, v3, v3
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_maximum_v4f16__nnan:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_pk_max_f16 v0, v0, v2
+; GFX9-NEXT: v_pk_max_f16 v1, v1, v3
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_maximum_v4f16__nnan:
; GFX10: ; %bb.0:
@@ -1981,19 +1936,12 @@ define <4 x half> @v_maximum_v4f16__nnan_nsz(<4 x half> %src0, <4 x half> %src1)
; GFX8-NEXT: v_or_b32_e32 v1, v1, v4
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_maximum_v4f16__nnan_nsz:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_pk_max_f16 v0, v0, v2
-; GFX900-NEXT: v_pk_max_f16 v1, v1, v3
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_maximum_v4f16__nnan_nsz:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_pk_maximum3_f16 v0, v0, v2, v2
-; GFX950-NEXT: v_pk_maximum3_f16 v1, v1, v3, v3
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_maximum_v4f16__nnan_nsz:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_pk_max_f16 v0, v0, v2
+; GFX9-NEXT: v_pk_max_f16 v1, v1, v3
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_maximum_v4f16__nnan_nsz:
; GFX10: ; %bb.0:
@@ -2788,4 +2736,3 @@ define <16 x half> @v_maximum_v16f16(<16 x half> %src0, <16 x half> %src1) {
}
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; GCN: {{.*}}
-; GFX9: {{.*}}
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.maximum.f32.ll b/llvm/test/CodeGen/AMDGPU/llvm.maximum.f32.ll
index 826bf427503ab..6c4f13a4eab8f 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.maximum.f32.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.maximum.f32.ll
@@ -85,17 +85,11 @@ define float @v_maximum_f32__nnan(float %src0, float %src1) {
; GFX8-NEXT: v_max_f32_e32 v0, v0, v1
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_maximum_f32__nnan:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_max_f32_e32 v0, v0, v1
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_maximum_f32__nnan:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_maximum3_f32 v0, v0, v1, v1
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_maximum_f32__nnan:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_max_f32_e32 v0, v0, v1
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_maximum_f32__nnan:
; GFX10: ; %bb.0:
@@ -199,17 +193,11 @@ define float @v_maximum_f32__nnan_nsz(float %src0, float %src1) {
; GFX8-NEXT: v_max_f32_e32 v0, v0, v1
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_maximum_f32__nnan_nsz:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_max_f32_e32 v0, v0, v1
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_maximum_f32__nnan_nsz:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_maximum3_f32 v0, v0, v1, v1
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_maximum_f32__nnan_nsz:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_max_f32_e32 v0, v0, v1
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_maximum_f32__nnan_nsz:
; GFX10: ; %bb.0:
@@ -568,19 +556,12 @@ define <2 x float> @v_maximum_v2f32__nnan(<2 x float> %src0, <2 x float> %src1)
; GFX8-NEXT: v_max_f32_e32 v1, v1, v3
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_maximum_v2f32__nnan:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_max_f32_e32 v0, v0, v2
-; GFX900-NEXT: v_max_f32_e32 v1, v1, v3
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_maximum_v2f32__nnan:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_maximum3_f32 v0, v0, v2, v2
-; GFX950-NEXT: v_maximum3_f32 v1, v1, v3, v3
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_maximum_v2f32__nnan:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_max_f32_e32 v0, v0, v2
+; GFX9-NEXT: v_max_f32_e32 v1, v1, v3
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_maximum_v2f32__nnan:
; GFX10: ; %bb.0:
@@ -704,19 +685,12 @@ define <2 x float> @v_maximum_v2f32__nnan_nsz(<2 x float> %src0, <2 x float> %sr
; GFX8-NEXT: v_max_f32_e32 v1, v1, v3
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_maximum_v2f32__nnan_nsz:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_max_f32_e32 v0, v0, v2
-; GFX900-NEXT: v_max_f32_e32 v1, v1, v3
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_maximum_v2f32__nnan_nsz:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_maximum3_f32 v0, v0, v2, v2
-; GFX950-NEXT: v_maximum3_f32 v1, v1, v3, v3
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_maximum_v2f32__nnan_nsz:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_max_f32_e32 v0, v0, v2
+; GFX9-NEXT: v_max_f32_e32 v1, v1, v3
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_maximum_v2f32__nnan_nsz:
; GFX10: ; %bb.0:
@@ -971,21 +945,13 @@ define <3 x float> @v_maximum_v3f32__nnan(<3 x float> %src0, <3 x float> %src1)
; GFX8-NEXT: v_max_f32_e32 v2, v2, v5
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_maximum_v3f32__nnan:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_max_f32_e32 v0, v0, v3
-; GFX900-NEXT: v_max_f32_e32 v1, v1, v4
-; GFX900-NEXT: v_max_f32_e32 v2, v2, v5
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_maximum_v3f32__nnan:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_maximum3_f32 v0, v0, v3, v3
-; GFX950-NEXT: v_maximum3_f32 v1, v1, v4, v4
-; GFX950-NEXT: v_maximum3_f32 v2, v2, v5, v5
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_maximum_v3f32__nnan:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_max_f32_e32 v0, v0, v3
+; GFX9-NEXT: v_max_f32_e32 v1, v1, v4
+; GFX9-NEXT: v_max_f32_e32 v2, v2, v5
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_maximum_v3f32__nnan:
; GFX10: ; %bb.0:
@@ -1131,21 +1097,13 @@ define <3 x float> @v_maximum_v3f32__nnan_nsz(<3 x float> %src0, <3 x float> %sr
; GFX8-NEXT: v_max_f32_e32 v2, v2, v5
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_maximum_v3f32__nnan_nsz:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_max_f32_e32 v0, v0, v3
-; GFX900-NEXT: v_max_f32_e32 v1, v1, v4
-; GFX900-NEXT: v_max_f32_e32 v2, v2, v5
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_maximum_v3f32__nnan_nsz:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_maximum3_f32 v0, v0, v3, v3
-; GFX950-NEXT: v_maximum3_f32 v1, v1, v4, v4
-; GFX950-NEXT: v_maximum3_f32 v2, v2, v5, v5
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_maximum_v3f32__nnan_nsz:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_max_f32_e32 v0, v0, v3
+; GFX9-NEXT: v_max_f32_e32 v1, v1, v4
+; GFX9-NEXT: v_max_f32_e32 v2, v2, v5
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_maximum_v3f32__nnan_nsz:
; GFX10: ; %bb.0:
@@ -1310,23 +1268,14 @@ define <4 x float> @v_maximum_v4f32__nnan(<4 x float> %src0, <4 x float> %src1)
; GFX8-NEXT: v_max_f32_e32 v3, v3, v7
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_maximum_v4f32__nnan:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_max_f32_e32 v0, v0, v4
-; GFX900-NEXT: v_max_f32_e32 v1, v1, v5
-; GFX900-NEXT: v_max_f32_e32 v2, v2, v6
-; GFX900-NEXT: v_max_f32_e32 v3, v3, v7
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_maximum_v4f32__nnan:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_maximum3_f32 v0, v0, v4, v4
-; GFX950-NEXT: v_maximum3_f32 v1, v1, v5, v5
-; GFX950-NEXT: v_maximum3_f32 v2, v2, v6, v6
-; GFX950-NEXT: v_maximum3_f32 v3, v3, v7, v7
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_maximum_v4f32__nnan:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_max_f32_e32 v0, v0, v4
+; GFX9-NEXT: v_max_f32_e32 v1, v1, v5
+; GFX9-NEXT: v_max_f32_e32 v2, v2, v6
+; GFX9-NEXT: v_max_f32_e32 v3, v3, v7
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_maximum_v4f32__nnan:
; GFX10: ; %bb.0:
@@ -1493,23 +1442,14 @@ define <4 x float> @v_maximum_v4f32__nnan_nsz(<4 x float> %src0, <4 x float> %sr
; GFX8-NEXT: v_max_f32_e32 v3, v3, v7
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_maximum_v4f32__nnan_nsz:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_max_f32_e32 v0, v0, v4
-; GFX900-NEXT: v_max_f32_e32 v1, v1, v5
-; GFX900-NEXT: v_max_f32_e32 v2, v2, v6
-; GFX900-NEXT: v_max_f32_e32 v3, v3, v7
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_maximum_v4f32__nnan_nsz:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_maximum3_f32 v0, v0, v4, v4
-; GFX950-NEXT: v_maximum3_f32 v1, v1, v5, v5
-; GFX950-NEXT: v_maximum3_f32 v2, v2, v6, v6
-; GFX950-NEXT: v_maximum3_f32 v3, v3, v7, v7
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_maximum_v4f32__nnan_nsz:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_max_f32_e32 v0, v0, v4
+; GFX9-NEXT: v_max_f32_e32 v1, v1, v5
+; GFX9-NEXT: v_max_f32_e32 v2, v2, v6
+; GFX9-NEXT: v_max_f32_e32 v3, v3, v7
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_maximum_v4f32__nnan_nsz:
; GFX10: ; %bb.0:
@@ -2051,4 +1991,3 @@ define <16 x float> @v_maximum_v16f32(<16 x float> %src0, <16 x float> %src1) {
}
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; GCN: {{.*}}
-; GFX9: {{.*}}
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.minimum.f16.ll b/llvm/test/CodeGen/AMDGPU/llvm.minimum.f16.ll
index 3dcc70b0ea3b6..9e82b41bb9585 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.minimum.f16.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.minimum.f16.ll
@@ -91,17 +91,11 @@ define half @v_minimum_f16__nnan(half %src0, half %src1) {
; GFX8-NEXT: v_min_f16_e32 v0, v0, v1
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_minimum_f16__nnan:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_min_f16_e32 v0, v0, v1
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_minimum_f16__nnan:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_pk_minimum3_f16 v0, v0, v1, v1
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_minimum_f16__nnan:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_min_f16_e32 v0, v0, v1
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_minimum_f16__nnan:
; GFX10: ; %bb.0:
@@ -225,17 +219,11 @@ define half @v_minimum_f16__nnan_nsz(half %src0, half %src1) {
; GFX8-NEXT: v_min_f16_e32 v0, v0, v1
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_minimum_f16__nnan_nsz:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_min_f16_e32 v0, v0, v1
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_minimum_f16__nnan_nsz:
-; GFX950: ; %bb.0:
-; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX950-NEXT: v_pk_minimum3_f16 v0, v0, v1, v1
-; GFX950-NEXT: s_setpc_b64 s[30:31]
+; GFX9-LABEL: v_minimum_f16__nnan_nsz:
+; GFX9: ; %bb.0:
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_min_f16_e32 v0, v0, v1
+; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: v_minimum_f16__nnan_nsz:
; GFX10: ; %bb.0:
@@ -646,17 +634,11 @@ define <2 x half> @v_minimum_v2f16__nnan(<2 x half> %src0, <2 x half> %src1) {
; GFX8-NEXT: v_or_b32_e32 v0, v0, v2
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
-; GFX900-LABEL: v_minimum_v2f16__nnan:
-; GFX900: ; %bb.0:
-; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX900-NEXT: v_pk_min_f16 v0, v0, v1
-; GFX900-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX950-LABEL: v_minimum_v2f16__...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/142217
More information about the llvm-commits
mailing list