[llvm] AMDGPU: Test more types with minimumnum and maximumnum (PR #139242)
via llvm-commits
llvm-commits at lists.llvm.org
Fri May 9 03:41:34 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Matt Arsenault (arsenm)
<details>
<summary>Changes</summary>
We had custom lowering for the wider vectors of f16, but missing
test coverage for them. Also add more vector tests for bf16, and
split the bf16 cases into separate files so we can add globalisel
run lines.
---
Patch is 2.40 MiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/139242.diff
4 Files Affected:
- (added) llvm/test/CodeGen/AMDGPU/maximumnum.bf16.ll (+21691)
- (modified) llvm/test/CodeGen/AMDGPU/maximumnum.ll (+1099-492)
- (added) llvm/test/CodeGen/AMDGPU/minimumnum.bf16.ll (+21742)
- (modified) llvm/test/CodeGen/AMDGPU/minimumnum.ll (+1099-498)
``````````diff
diff --git a/llvm/test/CodeGen/AMDGPU/maximumnum.bf16.ll b/llvm/test/CodeGen/AMDGPU/maximumnum.bf16.ll
new file mode 100644
index 0000000000000..9009ec54f174d
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/maximumnum.bf16.ll
@@ -0,0 +1,21691 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx700 < %s | FileCheck -check-prefix=GFX7 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 < %s | FileCheck -check-prefix=GFX8 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=GFX9,GFX900 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx950 < %s | FileCheck -check-prefixes=GFX9,GFX950 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1030 < %s | FileCheck -check-prefix=GFX10 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck -check-prefixes=GFX11,GFX11-TRUE16 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck -check-prefixes=GFX11,GFX11-FAKE16 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1200 -mattr=+real-true16 < %s | FileCheck -check-prefixes=GFX12,GFX12-TRUE16 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1200 -mattr=-real-true16 < %s | FileCheck -check-prefixes=GFX12,GFX12-FAKE16 %s
+
+define bfloat @v_maximumnum_bf16(bfloat %x, bfloat %y) {
+; GFX7-LABEL: v_maximumnum_bf16:
+; GFX7: ; %bb.0:
+; GFX7-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX7-NEXT: v_mul_f32_e32 v0, 1.0, v0
+; GFX7-NEXT: v_mul_f32_e32 v1, 1.0, v1
+; GFX7-NEXT: v_and_b32_e32 v1, 0xffff0000, v1
+; GFX7-NEXT: v_and_b32_e32 v0, 0xffff0000, v0
+; GFX7-NEXT: v_max_f32_e32 v0, v0, v1
+; GFX7-NEXT: v_and_b32_e32 v0, 0xffff0000, v0
+; GFX7-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX8-LABEL: v_maximumnum_bf16:
+; GFX8: ; %bb.0:
+; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX8-NEXT: v_lshlrev_b32_e32 v2, 16, v0
+; GFX8-NEXT: v_cmp_u_f32_e32 vcc, v2, v2
+; GFX8-NEXT: v_lshlrev_b32_e32 v2, 16, v1
+; GFX8-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc
+; GFX8-NEXT: v_cmp_u_f32_e32 vcc, v2, v2
+; GFX8-NEXT: v_cndmask_b32_e32 v1, v1, v0, vcc
+; GFX8-NEXT: v_lshlrev_b32_e32 v2, 16, v1
+; GFX8-NEXT: v_lshlrev_b32_e32 v3, 16, v0
+; GFX8-NEXT: v_cmp_gt_f32_e32 vcc, v3, v2
+; GFX8-NEXT: v_cndmask_b32_e32 v2, v1, v0, vcc
+; GFX8-NEXT: v_lshlrev_b32_e32 v2, 16, v2
+; GFX8-NEXT: v_mul_f32_e32 v2, 1.0, v2
+; GFX8-NEXT: v_bfe_u32 v3, v2, 16, 1
+; GFX8-NEXT: v_add_u32_e32 v3, vcc, v3, v2
+; GFX8-NEXT: s_movk_i32 s4, 0x7fff
+; GFX8-NEXT: v_add_u32_e32 v3, vcc, s4, v3
+; GFX8-NEXT: v_or_b32_e32 v4, 0x400000, v2
+; GFX8-NEXT: v_cmp_u_f32_e32 vcc, v2, v2
+; GFX8-NEXT: v_cndmask_b32_e32 v2, v3, v4, vcc
+; GFX8-NEXT: v_lshrrev_b32_e32 v3, 16, v2
+; GFX8-NEXT: v_cmp_eq_u16_e32 vcc, 0, v0
+; GFX8-NEXT: v_cndmask_b32_e32 v0, v3, v0, vcc
+; GFX8-NEXT: v_cmp_eq_u16_e32 vcc, 0, v1
+; GFX8-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc
+; GFX8-NEXT: v_and_b32_e32 v1, 0xffff0000, v2
+; GFX8-NEXT: v_cmp_eq_f32_e32 vcc, 0, v1
+; GFX8-NEXT: v_cndmask_b32_e32 v0, v3, v0, vcc
+; GFX8-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX900-LABEL: v_maximumnum_bf16:
+; GFX900: ; %bb.0:
+; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX900-NEXT: v_lshlrev_b32_e32 v2, 16, v0
+; GFX900-NEXT: v_cmp_u_f32_e32 vcc, v2, v2
+; GFX900-NEXT: v_lshlrev_b32_e32 v3, 16, v1
+; GFX900-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc
+; GFX900-NEXT: v_cmp_u_f32_e32 vcc, v3, v3
+; GFX900-NEXT: v_cndmask_b32_e32 v1, v1, v0, vcc
+; GFX900-NEXT: v_lshlrev_b32_e32 v2, 16, v0
+; GFX900-NEXT: v_lshlrev_b32_e32 v3, 16, v1
+; GFX900-NEXT: v_cmp_gt_f32_e32 vcc, v2, v3
+; GFX900-NEXT: v_cndmask_b32_e32 v2, v1, v0, vcc
+; GFX900-NEXT: v_lshlrev_b32_e32 v2, 16, v2
+; GFX900-NEXT: v_max_f32_e32 v2, v2, v2
+; GFX900-NEXT: v_bfe_u32 v3, v2, 16, 1
+; GFX900-NEXT: s_movk_i32 s4, 0x7fff
+; GFX900-NEXT: v_add3_u32 v3, v3, v2, s4
+; GFX900-NEXT: v_or_b32_e32 v4, 0x400000, v2
+; GFX900-NEXT: v_cmp_u_f32_e32 vcc, v2, v2
+; GFX900-NEXT: v_cndmask_b32_e32 v2, v3, v4, vcc
+; GFX900-NEXT: v_lshrrev_b32_e32 v3, 16, v2
+; GFX900-NEXT: v_cmp_eq_u16_e32 vcc, 0, v0
+; GFX900-NEXT: v_cndmask_b32_e32 v0, v3, v0, vcc
+; GFX900-NEXT: v_cmp_eq_u16_e32 vcc, 0, v1
+; GFX900-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc
+; GFX900-NEXT: v_and_b32_e32 v1, 0xffff0000, v2
+; GFX900-NEXT: v_cmp_eq_f32_e32 vcc, 0, v1
+; GFX900-NEXT: v_cndmask_b32_e32 v0, v3, v0, vcc
+; GFX900-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX950-LABEL: v_maximumnum_bf16:
+; GFX950: ; %bb.0:
+; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX950-NEXT: v_lshlrev_b32_e32 v2, 16, v0
+; GFX950-NEXT: v_cmp_u_f32_e32 vcc, v2, v2
+; GFX950-NEXT: v_lshlrev_b32_e32 v3, 16, v1
+; GFX950-NEXT: s_nop 0
+; GFX950-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc
+; GFX950-NEXT: v_cmp_u_f32_e32 vcc, v3, v3
+; GFX950-NEXT: v_lshlrev_b32_e32 v2, 16, v0
+; GFX950-NEXT: s_nop 0
+; GFX950-NEXT: v_cndmask_b32_e32 v1, v1, v0, vcc
+; GFX950-NEXT: v_lshlrev_b32_e32 v3, 16, v1
+; GFX950-NEXT: v_cmp_gt_f32_e32 vcc, v2, v3
+; GFX950-NEXT: s_nop 1
+; GFX950-NEXT: v_cndmask_b32_e32 v2, v1, v0, vcc
+; GFX950-NEXT: v_lshlrev_b32_e32 v2, 16, v2
+; GFX950-NEXT: v_max_f32_e32 v2, v2, v2
+; GFX950-NEXT: v_cvt_pk_bf16_f32 v2, v2, s0
+; GFX950-NEXT: v_cmp_eq_u16_e32 vcc, 0, v0
+; GFX950-NEXT: s_nop 1
+; GFX950-NEXT: v_cndmask_b32_e32 v0, v2, v0, vcc
+; GFX950-NEXT: v_cmp_eq_u16_e32 vcc, 0, v1
+; GFX950-NEXT: s_nop 1
+; GFX950-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc
+; GFX950-NEXT: v_lshlrev_b32_e32 v1, 16, v2
+; GFX950-NEXT: v_cmp_eq_f32_e32 vcc, 0, v1
+; GFX950-NEXT: s_nop 1
+; GFX950-NEXT: v_cndmask_b32_e32 v0, v2, v0, vcc
+; GFX950-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: v_maximumnum_bf16:
+; GFX10: ; %bb.0:
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: v_lshlrev_b32_e32 v2, 16, v0
+; GFX10-NEXT: v_lshlrev_b32_e32 v3, 16, v1
+; GFX10-NEXT: v_cmp_u_f32_e32 vcc_lo, v2, v2
+; GFX10-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc_lo
+; GFX10-NEXT: v_cmp_u_f32_e32 vcc_lo, v3, v3
+; GFX10-NEXT: v_lshlrev_b32_e32 v2, 16, v0
+; GFX10-NEXT: v_cndmask_b32_e32 v1, v1, v0, vcc_lo
+; GFX10-NEXT: v_lshlrev_b32_e32 v3, 16, v1
+; GFX10-NEXT: v_cmp_gt_f32_e32 vcc_lo, v2, v3
+; GFX10-NEXT: v_cndmask_b32_e32 v2, v1, v0, vcc_lo
+; GFX10-NEXT: v_lshlrev_b32_e32 v2, 16, v2
+; GFX10-NEXT: v_max_f32_e32 v2, v2, v2
+; GFX10-NEXT: v_bfe_u32 v3, v2, 16, 1
+; GFX10-NEXT: v_or_b32_e32 v4, 0x400000, v2
+; GFX10-NEXT: v_cmp_u_f32_e32 vcc_lo, v2, v2
+; GFX10-NEXT: v_add3_u32 v3, v3, v2, 0x7fff
+; GFX10-NEXT: v_cndmask_b32_e32 v2, v3, v4, vcc_lo
+; GFX10-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v0
+; GFX10-NEXT: v_lshrrev_b32_e32 v3, 16, v2
+; GFX10-NEXT: v_and_b32_e32 v2, 0xffff0000, v2
+; GFX10-NEXT: v_cndmask_b32_e32 v0, v3, v0, vcc_lo
+; GFX10-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v1
+; GFX10-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc_lo
+; GFX10-NEXT: v_cmp_eq_f32_e32 vcc_lo, 0, v2
+; GFX10-NEXT: v_cndmask_b32_e32 v0, v3, v0, vcc_lo
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX11-TRUE16-LABEL: v_maximumnum_bf16:
+; GFX11-TRUE16: ; %bb.0:
+; GFX11-TRUE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX11-TRUE16-NEXT: v_lshlrev_b32_e32 v2, 16, v0
+; GFX11-TRUE16-NEXT: v_mov_b16_e32 v0.h, v1.l
+; GFX11-TRUE16-NEXT: v_lshlrev_b32_e32 v1, 16, v1
+; GFX11-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX11-TRUE16-NEXT: v_cmp_u_f32_e32 vcc_lo, v2, v2
+; GFX11-TRUE16-NEXT: v_cmp_u_f32_e64 s0, v1, v1
+; GFX11-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_4) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX11-TRUE16-NEXT: v_cndmask_b16 v0.l, v0.l, v0.h, vcc_lo
+; GFX11-TRUE16-NEXT: v_cndmask_b16 v1.l, v0.h, v0.l, s0
+; GFX11-TRUE16-NEXT: v_mov_b16_e32 v2.l, v0.l
+; GFX11-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX11-TRUE16-NEXT: v_mov_b16_e32 v3.l, v1.l
+; GFX11-TRUE16-NEXT: v_lshlrev_b32_e32 v2, 16, v2
+; GFX11-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX11-TRUE16-NEXT: v_lshlrev_b32_e32 v3, 16, v3
+; GFX11-TRUE16-NEXT: v_cmp_gt_f32_e32 vcc_lo, v2, v3
+; GFX11-TRUE16-NEXT: v_cndmask_b16 v2.l, v1.l, v0.l, vcc_lo
+; GFX11-TRUE16-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v0.l
+; GFX11-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX11-TRUE16-NEXT: v_lshlrev_b32_e32 v2, 16, v2
+; GFX11-TRUE16-NEXT: v_max_f32_e32 v2, v2, v2
+; GFX11-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_2) | instid1(VALU_DEP_3)
+; GFX11-TRUE16-NEXT: v_bfe_u32 v3, v2, 16, 1
+; GFX11-TRUE16-NEXT: v_or_b32_e32 v4, 0x400000, v2
+; GFX11-TRUE16-NEXT: v_cmp_u_f32_e64 s0, v2, v2
+; GFX11-TRUE16-NEXT: v_add3_u32 v3, v3, v2, 0x7fff
+; GFX11-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_2)
+; GFX11-TRUE16-NEXT: v_cndmask_b32_e64 v2, v3, v4, s0
+; GFX11-TRUE16-NEXT: v_cmp_eq_u16_e64 s0, 0, v1.l
+; GFX11-TRUE16-NEXT: v_cndmask_b16 v0.l, v2.h, v0.l, vcc_lo
+; GFX11-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX11-TRUE16-NEXT: v_and_b32_e32 v3, 0xffff0000, v2
+; GFX11-TRUE16-NEXT: v_cndmask_b16 v0.l, v0.l, v1.l, s0
+; GFX11-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX11-TRUE16-NEXT: v_cmp_eq_f32_e32 vcc_lo, 0, v3
+; GFX11-TRUE16-NEXT: v_cndmask_b16 v0.l, v2.h, v0.l, vcc_lo
+; GFX11-TRUE16-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX11-FAKE16-LABEL: v_maximumnum_bf16:
+; GFX11-FAKE16: ; %bb.0:
+; GFX11-FAKE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX11-FAKE16-NEXT: v_lshlrev_b32_e32 v2, 16, v0
+; GFX11-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_2) | instid1(VALU_DEP_2)
+; GFX11-FAKE16-NEXT: v_cmp_u_f32_e32 vcc_lo, v2, v2
+; GFX11-FAKE16-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc_lo
+; GFX11-FAKE16-NEXT: v_lshlrev_b32_e32 v3, 16, v1
+; GFX11-FAKE16-NEXT: v_lshlrev_b32_e32 v2, 16, v0
+; GFX11-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_1) | instid1(VALU_DEP_1)
+; GFX11-FAKE16-NEXT: v_cmp_u_f32_e32 vcc_lo, v3, v3
+; GFX11-FAKE16-NEXT: v_cndmask_b32_e32 v1, v1, v0, vcc_lo
+; GFX11-FAKE16-NEXT: v_lshlrev_b32_e32 v3, 16, v1
+; GFX11-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_1)
+; GFX11-FAKE16-NEXT: v_cmp_gt_f32_e32 vcc_lo, v2, v3
+; GFX11-FAKE16-NEXT: v_cndmask_b32_e32 v2, v1, v0, vcc_lo
+; GFX11-FAKE16-NEXT: v_lshlrev_b32_e32 v2, 16, v2
+; GFX11-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX11-FAKE16-NEXT: v_max_f32_e32 v2, v2, v2
+; GFX11-FAKE16-NEXT: v_bfe_u32 v3, v2, 16, 1
+; GFX11-FAKE16-NEXT: v_or_b32_e32 v4, 0x400000, v2
+; GFX11-FAKE16-NEXT: v_cmp_u_f32_e32 vcc_lo, v2, v2
+; GFX11-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX11-FAKE16-NEXT: v_add3_u32 v3, v3, v2, 0x7fff
+; GFX11-FAKE16-NEXT: v_cndmask_b32_e32 v2, v3, v4, vcc_lo
+; GFX11-FAKE16-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v0
+; GFX11-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_1) | instid1(VALU_DEP_2)
+; GFX11-FAKE16-NEXT: v_lshrrev_b32_e32 v3, 16, v2
+; GFX11-FAKE16-NEXT: v_and_b32_e32 v2, 0xffff0000, v2
+; GFX11-FAKE16-NEXT: v_cndmask_b32_e32 v0, v3, v0, vcc_lo
+; GFX11-FAKE16-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v1
+; GFX11-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_4)
+; GFX11-FAKE16-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc_lo
+; GFX11-FAKE16-NEXT: v_cmp_eq_f32_e32 vcc_lo, 0, v2
+; GFX11-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_2)
+; GFX11-FAKE16-NEXT: v_cndmask_b32_e32 v0, v3, v0, vcc_lo
+; GFX11-FAKE16-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX12-TRUE16-LABEL: v_maximumnum_bf16:
+; GFX12-TRUE16: ; %bb.0:
+; GFX12-TRUE16-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX12-TRUE16-NEXT: s_wait_expcnt 0x0
+; GFX12-TRUE16-NEXT: s_wait_samplecnt 0x0
+; GFX12-TRUE16-NEXT: s_wait_bvhcnt 0x0
+; GFX12-TRUE16-NEXT: s_wait_kmcnt 0x0
+; GFX12-TRUE16-NEXT: v_lshlrev_b32_e32 v2, 16, v0
+; GFX12-TRUE16-NEXT: v_mov_b16_e32 v0.h, v1.l
+; GFX12-TRUE16-NEXT: v_lshlrev_b32_e32 v1, 16, v1
+; GFX12-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX12-TRUE16-NEXT: v_cmp_u_f32_e32 vcc_lo, v2, v2
+; GFX12-TRUE16-NEXT: v_cmp_u_f32_e64 s0, v1, v1
+; GFX12-TRUE16-NEXT: s_wait_alu 0xfffd
+; GFX12-TRUE16-NEXT: v_cndmask_b16 v0.l, v0.l, v0.h, vcc_lo
+; GFX12-TRUE16-NEXT: s_wait_alu 0xf1ff
+; GFX12-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_2)
+; GFX12-TRUE16-NEXT: v_cndmask_b16 v1.l, v0.h, v0.l, s0
+; GFX12-TRUE16-NEXT: v_mov_b16_e32 v2.l, v0.l
+; GFX12-TRUE16-NEXT: v_mov_b16_e32 v3.l, v1.l
+; GFX12-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX12-TRUE16-NEXT: v_lshlrev_b32_e32 v2, 16, v2
+; GFX12-TRUE16-NEXT: v_lshlrev_b32_e32 v3, 16, v3
+; GFX12-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_3) | instid1(VALU_DEP_2)
+; GFX12-TRUE16-NEXT: v_cmp_gt_f32_e32 vcc_lo, v2, v3
+; GFX12-TRUE16-NEXT: s_wait_alu 0xfffd
+; GFX12-TRUE16-NEXT: v_cndmask_b16 v2.l, v1.l, v0.l, vcc_lo
+; GFX12-TRUE16-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v0.l
+; GFX12-TRUE16-NEXT: v_lshlrev_b32_e32 v2, 16, v2
+; GFX12-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX12-TRUE16-NEXT: v_max_num_f32_e32 v2, v2, v2
+; GFX12-TRUE16-NEXT: v_bfe_u32 v3, v2, 16, 1
+; GFX12-TRUE16-NEXT: v_or_b32_e32 v4, 0x400000, v2
+; GFX12-TRUE16-NEXT: v_cmp_u_f32_e64 s0, v2, v2
+; GFX12-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(SKIP_1) | instid1(VALU_DEP_1)
+; GFX12-TRUE16-NEXT: v_add3_u32 v3, v3, v2, 0x7fff
+; GFX12-TRUE16-NEXT: s_wait_alu 0xf1ff
+; GFX12-TRUE16-NEXT: v_cndmask_b32_e64 v2, v3, v4, s0
+; GFX12-TRUE16-NEXT: v_cmp_eq_u16_e64 s0, 0, v1.l
+; GFX12-TRUE16-NEXT: s_wait_alu 0xfffd
+; GFX12-TRUE16-NEXT: v_cndmask_b16 v0.l, v2.h, v0.l, vcc_lo
+; GFX12-TRUE16-NEXT: v_and_b32_e32 v3, 0xffff0000, v2
+; GFX12-TRUE16-NEXT: s_wait_alu 0xf1ff
+; GFX12-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX12-TRUE16-NEXT: v_cndmask_b16 v0.l, v0.l, v1.l, s0
+; GFX12-TRUE16-NEXT: v_cmp_eq_f32_e32 vcc_lo, 0, v3
+; GFX12-TRUE16-NEXT: s_wait_alu 0xfffd
+; GFX12-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2)
+; GFX12-TRUE16-NEXT: v_cndmask_b16 v0.l, v2.h, v0.l, vcc_lo
+; GFX12-TRUE16-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX12-FAKE16-LABEL: v_maximumnum_bf16:
+; GFX12-FAKE16: ; %bb.0:
+; GFX12-FAKE16-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX12-FAKE16-NEXT: s_wait_expcnt 0x0
+; GFX12-FAKE16-NEXT: s_wait_samplecnt 0x0
+; GFX12-FAKE16-NEXT: s_wait_bvhcnt 0x0
+; GFX12-FAKE16-NEXT: s_wait_kmcnt 0x0
+; GFX12-FAKE16-NEXT: v_lshlrev_b32_e32 v2, 16, v0
+; GFX12-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_3) | instid1(VALU_DEP_2)
+; GFX12-FAKE16-NEXT: v_cmp_u_f32_e32 vcc_lo, v2, v2
+; GFX12-FAKE16-NEXT: s_wait_alu 0xfffd
+; GFX12-FAKE16-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc_lo
+; GFX12-FAKE16-NEXT: v_lshlrev_b32_e32 v3, 16, v1
+; GFX12-FAKE16-NEXT: v_lshlrev_b32_e32 v2, 16, v0
+; GFX12-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_2) | instid1(VALU_DEP_1)
+; GFX12-FAKE16-NEXT: v_cmp_u_f32_e32 vcc_lo, v3, v3
+; GFX12-FAKE16-NEXT: s_wait_alu 0xfffd
+; GFX12-FAKE16-NEXT: v_cndmask_b32_e32 v1, v1, v0, vcc_lo
+; GFX12-FAKE16-NEXT: v_lshlrev_b32_e32 v3, 16, v1
+; GFX12-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_2) | instid1(VALU_DEP_1)
+; GFX12-FAKE16-NEXT: v_cmp_gt_f32_e32 vcc_lo, v2, v3
+; GFX12-FAKE16-NEXT: s_wait_alu 0xfffd
+; GFX12-FAKE16-NEXT: v_cndmask_b32_e32 v2, v1, v0, vcc_lo
+; GFX12-FAKE16-NEXT: v_lshlrev_b32_e32 v2, 16, v2
+; GFX12-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX12-FAKE16-NEXT: v_max_num_f32_e32 v2, v2, v2
+; GFX12-FAKE16-NEXT: v_bfe_u32 v3, v2, 16, 1
+; GFX12-FAKE16-NEXT: v_or_b32_e32 v4, 0x400000, v2
+; GFX12-FAKE16-NEXT: v_cmp_u_f32_e32 vcc_lo, v2, v2
+; GFX12-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(SKIP_1) | instid1(VALU_DEP_1)
+; GFX12-FAKE16-NEXT: v_add3_u32 v3, v3, v2, 0x7fff
+; GFX12-FAKE16-NEXT: s_wait_alu 0xfffd
+; GFX12-FAKE16-NEXT: v_cndmask_b32_e32 v2, v3, v4, vcc_lo
+; GFX12-FAKE16-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v0
+; GFX12-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_2) | instid1(VALU_DEP_2)
+; GFX12-FAKE16-NEXT: v_lshrrev_b32_e32 v3, 16, v2
+; GFX12-FAKE16-NEXT: v_and_b32_e32 v2, 0xffff0000, v2
+; GFX12-FAKE16-NEXT: s_wait_alu 0xfffd
+; GFX12-FAKE16-NEXT: v_cndmask_b32_e32 v0, v3, v0, vcc_lo
+; GFX12-FAKE16-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v1
+; GFX12-FAKE16-NEXT: s_wait_alu 0xfffd
+; GFX12-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_2) | instid1(VALU_DEP_2)
+; GFX12-FAKE16-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc_lo
+; GFX12-FAKE16-NEXT: v_cmp_eq_f32_e32 vcc_lo, 0, v2
+; GFX12-FAKE16-NEXT: s_wait_alu 0xfffd
+; GFX12-FAKE16-NEXT: v_cndmask_b32_e32 v0, v3, v0, vcc_lo
+; GFX12-FAKE16-NEXT: s_setpc_b64 s[30:31]
+ %result = call bfloat @llvm.maximumnum.bf16(bfloat %x, bfloat %y)
+ ret bfloat %result
+}
+
+define bfloat @v_maximumnum_bf16_nnan(bfloat %x, bfloat %y) {
+; GFX7-LABEL: v_maximumnum_bf16_nnan:
+; GFX7: ; %bb.0:
+; GFX7-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX7-NEXT: v_mul_f32_e32 v0, 1.0, v0
+; GFX7-NEXT: v_mul_f32_e32 v1, 1.0, v1
+; GFX7-NEXT: v_and_b32_e32 v1, 0xffff0000, v1
+; GFX7-NEXT: v_and_b32_e32 v0, 0xffff0000, v0
+; GFX7-NEXT: v_max_f32_e32 v0, v0, v1
+; GFX7-NEXT: v_and_b32_e32 v0, 0xffff0000, v0
+; GFX7-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX8-LABEL: v_maximumnum_bf16_nnan:
+; GFX8: ; %bb.0:
+; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX8-NEXT: v_lshlrev_b32_e32 v2, 16, v1
+; GFX8-NEXT: v_lshlrev_b32_e32 v3, 16, v0
+; GFX8-NEXT: v_cmp_gt_f32_e32 vcc, v3, v2
+; GFX8-NEXT: v_cndmask_b32_e32 v2, v1, v0, vcc
+; GFX8-NEXT: v_cmp_eq_u16_e32 vcc, 0, v0
+; GFX8-NEXT: v_cndmask_b32_e32 v0, v2, v0, vcc
+; GFX8-NEXT: v_cmp_eq_u16_e32 vcc, 0, v1
+; GFX8-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc
+; GFX8-NEXT: v_lshlrev_b32_e32 v1, 16, v2
+; GFX8-NEXT: v_cmp_eq_f32_e32 vcc, 0, v1
+; GFX8-NEXT: v_cndmask_b32_e32 v0, v2, v0, vcc
+; GFX8-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX900-LABEL: v_maximumnum_bf16_nnan:
+; GFX900: ; %bb.0:
+; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX900-NEXT: v_lshlrev_b32_e32 v2, 16, v1
+; GFX900-NEXT: v_lshlrev_b32_e32 v3, 16, v0
+; GFX900-NEXT: v_cmp_gt_f32_e32 vcc, v3, v2
+; GFX900-NEXT: v_cndmask_b32_e32 v2, v1, v0, vcc
+; GFX900-NEXT: v_cmp_eq_u16_e32 vcc, 0, v0
+; GFX900-NEXT: v_cndmask_b32_e32 v0, v2, v0, vcc
+; GFX900-NEXT: v_cmp_eq_u16_e32 vcc, 0, v1
+; GFX900-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc
+; GFX900-NEXT: v_lshlrev_b32_e32 v1, 16, v2
+; GFX900-NEXT: v_cmp_eq_f32_e32 vcc, 0, v1
+; GFX900-NEXT: v_cndmask_b32_e32 v0, v2, v0, vcc
+; GFX900-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX950-LABEL: v_maximumnum_bf16_nnan:
+; GFX950: ; %bb.0:
+; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX950-NEXT: v_lshlrev_b32_e32 v2, 16, v1
+; GFX950-NEXT: v_lshlrev_b32_e32 v3, 16, v0
+; GFX950-NEXT: v_cmp_gt_f32_e32 vcc, v3, v2
+; GFX950-NEXT: s_nop 1
+; GFX950-NEXT: v_cndmask_b32_e32 v2, v1, v0, vcc
+; GFX950-NEXT: v_cmp_eq_u16_e32 vcc, 0, v0
+; GFX950-NEXT: s_nop 1
+; GFX950-NEXT: v_cndmask_b32_e32 v0, v2, v0, vcc
+; GFX950-NEXT: v_cmp_eq_u16_e32 vcc, 0, v1
+; GFX950-NEXT: s_nop 1
+; ...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/139242
More information about the llvm-commits
mailing list