[llvm] [AMDGPU][True16][MC] test update for v_mul_f16 in true16 (PR #119314)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Dec 9 18:50:22 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-mc
Author: Brox Chen (broxigarchen)
<details>
<summary>Changes</summary>
This is a NFC change. Update mc test for v_mul_f16 in true16 format.
MC source change was done by previous patch and automatically enabled by t16 pesudo
---
Patch is 80.90 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/119314.diff
17 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/VOP2Instructions.td (+1-2)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop2.s (+45-30)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop2_dpp16.s (+37-28)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop2_dpp8.s (+15-6)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop2_t16_err.s (+45-18)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop2_t16_promote.s (+45-18)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16_from_vop2.s (+40-28)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8_from_vop2.s (+20-8)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop3_from_vop2.s (+39-30)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop2.s (+42-30)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop2_dpp16.s (+34-28)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop2_dpp8.s (+12-6)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop2_t16_err.s (+45-18)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop2_t16_promote.s (+45-18)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop2.s (+39-30)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop2_dpp16.s (+44-32)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3_from_vop2_dpp8.s (+24-12)
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/VOP2Instructions.td b/llvm/lib/Target/AMDGPU/VOP2Instructions.td
index 384fec0079a5d9..355528a1f92951 100644
--- a/llvm/lib/Target/AMDGPU/VOP2Instructions.td
+++ b/llvm/lib/Target/AMDGPU/VOP2Instructions.td
@@ -1822,8 +1822,7 @@ defm V_ADD_F16 : VOP2_Real_FULL_t16_and_fake16_gfx11_gfx12<0x032, "v
defm V_SUB_F16 : VOP2_Real_FULL_t16_and_fake16_gfx11_gfx12<0x033, "v_sub_f16">;
defm V_SUBREV_F16_t16 : VOP2_Real_FULL_t16_gfx11_gfx12<0x034, "v_subrev_f16">;
defm V_SUBREV_F16_fake16 : VOP2_Real_FULL_t16_gfx11_gfx12<0x034, "v_subrev_f16">;
-defm V_MUL_F16_t16 : VOP2_Real_FULL_t16_gfx11_gfx12<0x035, "v_mul_f16">;
-defm V_MUL_F16_fake16 : VOP2_Real_FULL_t16_gfx11_gfx12<0x035, "v_mul_f16">;
+defm V_MUL_F16 : VOP2_Real_FULL_t16_and_fake16_gfx11_gfx12<0x035, "v_mul_f16">;
defm V_FMAC_F16 : VOP2_Real_FULL_t16_and_fake16_gfx11_gfx12<0x036, "v_fmac_f16">;
defm V_LDEXP_F16_t16 : VOP2_Real_FULL_t16_gfx11_gfx12<0x03b, "v_ldexp_f16">;
defm V_LDEXP_F16_fake16 : VOP2_Real_FULL_t16_gfx11_gfx12<0x03b, "v_ldexp_f16">;
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop2.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop2.s
index cb7b71935e22ae..440c7201f541b0 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop2.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop2.s
@@ -1582,50 +1582,65 @@ v_mul_dx9_zero_f32 v5, src_scc, v2
v_mul_dx9_zero_f32 v255, 0xaf123456, v255
// GFX11: v_mul_dx9_zero_f32_e32 v255, 0xaf123456, v255 ; encoding: [0xff,0xfe,0xff,0x0f,0x56,0x34,0x12,0xaf]
-v_mul_f16 v5, v1, v2
-// GFX11: v_mul_f16_e32 v5, v1, v2 ; encoding: [0x01,0x05,0x0a,0x6a]
+v_mul_f16 v5.l, v1.l, v2.l
+// GFX11: v_mul_f16_e32 v5.l, v1.l, v2.l ; encoding: [0x01,0x05,0x0a,0x6a]
-v_mul_f16 v5, v127, v2
-// GFX11: v_mul_f16_e32 v5, v127, v2 ; encoding: [0x7f,0x05,0x0a,0x6a]
+v_mul_f16 v5.l, v127.l, v2.l
+// GFX11: v_mul_f16_e32 v5.l, v127.l, v2.l ; encoding: [0x7f,0x05,0x0a,0x6a]
-v_mul_f16 v5, s1, v2
-// GFX11: v_mul_f16_e32 v5, s1, v2 ; encoding: [0x01,0x04,0x0a,0x6a]
+v_mul_f16 v5.l, s1, v2.l
+// GFX11: v_mul_f16_e32 v5.l, s1, v2.l ; encoding: [0x01,0x04,0x0a,0x6a]
-v_mul_f16 v5, s105, v2
-// GFX11: v_mul_f16_e32 v5, s105, v2 ; encoding: [0x69,0x04,0x0a,0x6a]
+v_mul_f16 v5.l, s105, v2.l
+// GFX11: v_mul_f16_e32 v5.l, s105, v2.l ; encoding: [0x69,0x04,0x0a,0x6a]
-v_mul_f16 v5, vcc_lo, v2
-// GFX11: v_mul_f16_e32 v5, vcc_lo, v2 ; encoding: [0x6a,0x04,0x0a,0x6a]
+v_mul_f16 v5.l, vcc_lo, v2.l
+// GFX11: v_mul_f16_e32 v5.l, vcc_lo, v2.l ; encoding: [0x6a,0x04,0x0a,0x6a]
-v_mul_f16 v5, vcc_hi, v2
-// GFX11: v_mul_f16_e32 v5, vcc_hi, v2 ; encoding: [0x6b,0x04,0x0a,0x6a]
+v_mul_f16 v5.l, vcc_hi, v2.l
+// GFX11: v_mul_f16_e32 v5.l, vcc_hi, v2.l ; encoding: [0x6b,0x04,0x0a,0x6a]
-v_mul_f16 v5, ttmp15, v2
-// GFX11: v_mul_f16_e32 v5, ttmp15, v2 ; encoding: [0x7b,0x04,0x0a,0x6a]
+v_mul_f16 v5.l, ttmp15, v2.l
+// GFX11: v_mul_f16_e32 v5.l, ttmp15, v2.l ; encoding: [0x7b,0x04,0x0a,0x6a]
-v_mul_f16 v5, m0, v2
-// GFX11: v_mul_f16_e32 v5, m0, v2 ; encoding: [0x7d,0x04,0x0a,0x6a]
+v_mul_f16 v5.l, m0, v2.l
+// GFX11: v_mul_f16_e32 v5.l, m0, v2.l ; encoding: [0x7d,0x04,0x0a,0x6a]
-v_mul_f16 v5, exec_lo, v2
-// GFX11: v_mul_f16_e32 v5, exec_lo, v2 ; encoding: [0x7e,0x04,0x0a,0x6a]
+v_mul_f16 v5.l, exec_lo, v2.l
+// GFX11: v_mul_f16_e32 v5.l, exec_lo, v2.l ; encoding: [0x7e,0x04,0x0a,0x6a]
-v_mul_f16 v5, exec_hi, v2
-// GFX11: v_mul_f16_e32 v5, exec_hi, v2 ; encoding: [0x7f,0x04,0x0a,0x6a]
+v_mul_f16 v5.l, exec_hi, v2.l
+// GFX11: v_mul_f16_e32 v5.l, exec_hi, v2.l ; encoding: [0x7f,0x04,0x0a,0x6a]
-v_mul_f16 v5, null, v2
-// GFX11: v_mul_f16_e32 v5, null, v2 ; encoding: [0x7c,0x04,0x0a,0x6a]
+v_mul_f16 v5.l, null, v2.l
+// GFX11: v_mul_f16_e32 v5.l, null, v2.l ; encoding: [0x7c,0x04,0x0a,0x6a]
-v_mul_f16 v5, -1, v2
-// GFX11: v_mul_f16_e32 v5, -1, v2 ; encoding: [0xc1,0x04,0x0a,0x6a]
+v_mul_f16 v5.l, -1, v2.l
+// GFX11: v_mul_f16_e32 v5.l, -1, v2.l ; encoding: [0xc1,0x04,0x0a,0x6a]
-v_mul_f16 v5, 0.5, v2
-// GFX11: v_mul_f16_e32 v5, 0.5, v2 ; encoding: [0xf0,0x04,0x0a,0x6a]
+v_mul_f16 v5.l, 0.5, v2.l
+// GFX11: v_mul_f16_e32 v5.l, 0.5, v2.l ; encoding: [0xf0,0x04,0x0a,0x6a]
-v_mul_f16 v5, src_scc, v2
-// GFX11: v_mul_f16_e32 v5, src_scc, v2 ; encoding: [0xfd,0x04,0x0a,0x6a]
+v_mul_f16 v5.l, src_scc, v2.l
+// GFX11: v_mul_f16_e32 v5.l, src_scc, v2.l ; encoding: [0xfd,0x04,0x0a,0x6a]
-v_mul_f16 v127, 0xfe0b, v127
-// GFX11: v_mul_f16_e32 v127, 0xfe0b, v127 ; encoding: [0xff,0xfe,0xfe,0x6a,0x0b,0xfe,0x00,0x00]
+v_mul_f16 v127.l, 0xfe0b, v127.l
+// GFX11: v_mul_f16_e32 v127.l, 0xfe0b, v127.l ; encoding: [0xff,0xfe,0xfe,0x6a,0x0b,0xfe,0x00,0x00]
+
+v_mul_f16 v5.l, v1.h, v2.l
+// GFX11: v_mul_f16_e32 v5.l, v1.h, v2.l ; encoding: [0x81,0x05,0x0a,0x6a]
+
+v_mul_f16 v5.l, v127.h, v2.l
+// GFX11: v_mul_f16_e32 v5.l, v127.h, v2.l ; encoding: [0xff,0x05,0x0a,0x6a]
+
+v_mul_f16 v127.l, 0.5, v127.l
+// GFX11: v_mul_f16_e32 v127.l, 0.5, v127.l ; encoding: [0xf0,0xfe,0xfe,0x6a]
+
+v_mul_f16 v5.h, src_scc, v2.h
+// GFX11: v_mul_f16_e32 v5.h, src_scc, v2.h ; encoding: [0xfd,0x04,0x0b,0x6b]
+
+v_mul_f16 v127.h, 0xfe0b, v127.h
+// GFX11: v_mul_f16_e32 v127.h, 0xfe0b, v127.h ; encoding: [0xff,0xfe,0xff,0x6b,0x0b,0xfe,0x00,0x00]
v_mul_f32 v5, v1, v2
// GFX11: v_mul_f32_e32 v5, v1, v2 ; encoding: [0x01,0x05,0x0a,0x10]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop2_dpp16.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop2_dpp16.s
index 00353c4cdcb496..f2d34ab6457af2 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop2_dpp16.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop2_dpp16.s
@@ -1227,47 +1227,56 @@ v_mul_dx9_zero_f32 v5, v1, v2 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:
v_mul_dx9_zero_f32 v255, -|v255|, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX11: v_mul_dx9_zero_f32_dpp v255, -|v255|, -|v255| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xfe,0xff,0x0f,0xff,0x6f,0xf5,0x30]
-v_mul_f16 v5, v1, v2 quad_perm:[3,2,1,0]
-// GFX11: v_mul_f16_dpp v5, v1, v2 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x1b,0x00,0xff]
+v_mul_f16 v5.l, v1.l, v2.l quad_perm:[3,2,1,0]
+// GFX11: v_mul_f16_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x1b,0x00,0xff]
-v_mul_f16 v5, v1, v2 quad_perm:[0,1,2,3]
-// GFX11: v_mul_f16_dpp v5, v1, v2 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0xe4,0x00,0xff]
+v_mul_f16 v5.l, v1.l, v2.l quad_perm:[0,1,2,3]
+// GFX11: v_mul_f16_dpp v5.l, v1.l, v2.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0xe4,0x00,0xff]
-v_mul_f16 v5, v1, v2 row_mirror
-// GFX11: v_mul_f16_dpp v5, v1, v2 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x40,0x01,0xff]
+v_mul_f16 v5.l, v1.l, v2.l row_mirror
+// GFX11: v_mul_f16_dpp v5.l, v1.l, v2.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x40,0x01,0xff]
-v_mul_f16 v5, v1, v2 row_half_mirror
-// GFX11: v_mul_f16_dpp v5, v1, v2 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x41,0x01,0xff]
+v_mul_f16 v5.l, v1.l, v2.l row_half_mirror
+// GFX11: v_mul_f16_dpp v5.l, v1.l, v2.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x41,0x01,0xff]
-v_mul_f16 v5, v1, v2 row_shl:1
-// GFX11: v_mul_f16_dpp v5, v1, v2 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x01,0x01,0xff]
+v_mul_f16 v5.l, v1.l, v2.l row_shl:1
+// GFX11: v_mul_f16_dpp v5.l, v1.l, v2.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x01,0x01,0xff]
-v_mul_f16 v5, v1, v2 row_shl:15
-// GFX11: v_mul_f16_dpp v5, v1, v2 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x0f,0x01,0xff]
+v_mul_f16 v5.l, v1.l, v2.l row_shl:15
+// GFX11: v_mul_f16_dpp v5.l, v1.l, v2.l row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x0f,0x01,0xff]
-v_mul_f16 v5, v1, v2 row_shr:1
-// GFX11: v_mul_f16_dpp v5, v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x11,0x01,0xff]
+v_mul_f16 v5.l, v1.l, v2.l row_shr:1
+// GFX11: v_mul_f16_dpp v5.l, v1.l, v2.l row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x11,0x01,0xff]
-v_mul_f16 v5, v1, v2 row_shr:15
-// GFX11: v_mul_f16_dpp v5, v1, v2 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x1f,0x01,0xff]
+v_mul_f16 v5.l, v1.l, v2.l row_shr:15
+// GFX11: v_mul_f16_dpp v5.l, v1.l, v2.l row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x1f,0x01,0xff]
-v_mul_f16 v5, v1, v2 row_ror:1
-// GFX11: v_mul_f16_dpp v5, v1, v2 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x21,0x01,0xff]
+v_mul_f16 v5.l, v1.l, v2.l row_ror:1
+// GFX11: v_mul_f16_dpp v5.l, v1.l, v2.l row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x21,0x01,0xff]
-v_mul_f16 v5, v1, v2 row_ror:15
-// GFX11: v_mul_f16_dpp v5, v1, v2 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x2f,0x01,0xff]
+v_mul_f16 v5.l, v1.l, v2.l row_ror:15
+// GFX11: v_mul_f16_dpp v5.l, v1.l, v2.l row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x2f,0x01,0xff]
-v_mul_f16 v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf
-// GFX11: v_mul_f16_dpp v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x50,0x01,0xff]
+v_mul_f16 v5.l, v1.l, v2.l row_share:0 row_mask:0xf bank_mask:0xf
+// GFX11: v_mul_f16_dpp v5.l, v1.l, v2.l row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x50,0x01,0xff]
-v_mul_f16 v5, v1, v2 row_share:15 row_mask:0x0 bank_mask:0x1
-// GFX11: v_mul_f16_dpp v5, v1, v2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x5f,0x01,0x01]
+v_mul_f16 v5.l, v1.l, v2.l row_share:15 row_mask:0x0 bank_mask:0x1
+// GFX11: v_mul_f16_dpp v5.l, v1.l, v2.l row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x5f,0x01,0x01]
-v_mul_f16 v5, v1, v2 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
-// GFX11: v_mul_f16_dpp v5, v1, v2 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x60,0x09,0x13]
+v_mul_f16 v5.l, v1.l, v2.l row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1
+// GFX11: v_mul_f16_dpp v5.l, v1.l, v2.l row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0a,0x6a,0x01,0x60,0x09,0x13]
-v_mul_f16 v127, -|v127|, -|v127| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
-// GFX11: v_mul_f16_dpp v127, -|v127|, -|v127| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xfe,0xfe,0x6a,0x7f,0x6f,0xf5,0x30]
+v_mul_f16 v127.l, -|v127.l|, -|v127.l| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1
+// GFX11: v_mul_f16_dpp v127.l, -|v127.l|, -|v127.l| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xfe,0xfe,0x6a,0x7f,0x6f,0xf5,0x30]
+
+v_mul_f16 v127.l, v127.l, v127.l row_share:15 row_mask:0x0 bank_mask:0x1
+// GFX11: v_mul_f16_dpp v127.l, v127.l, v127.l row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0xfa,0xfe,0xfe,0x6a,0x7f,0x5f,0x01,0x01]
+
+v_mul_f16 v5.h, v1.h, v2.h row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
+// GFX11: v_mul_f16_dpp v5.h, v1.h, v2.h row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0xfa,0x04,0x0b,0x6b,0x81,0x60,0x09,0x13]
+
+v_mul_f16 v127.h, -|v127.h|, -|v127.h| row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
+// GFX11: v_mul_f16_dpp v127.h, -|v127.h|, -|v127.h| row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xfa,0xfe,0xff,0x6b,0xff,0x6f,0xf5,0x30]
v_mul_f32 v5, v1, v2 quad_perm:[3,2,1,0]
// GFX11: v_mul_f32_dpp v5, v1, v2 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x04,0x0a,0x10,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop2_dpp8.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop2_dpp8.s
index 489e6d8c9d63a9..22974f7a4e517b 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop2_dpp8.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop2_dpp8.s
@@ -271,14 +271,23 @@ v_mul_dx9_zero_f32 v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0] fi:1
v_mul_dx9_zero_f32 v255, v255, v255 dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX11: v_mul_dx9_zero_f32_dpp v255, v255, v255 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xfe,0xff,0x0f,0xff,0x00,0x00,0x00]
-v_mul_f16 v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_mul_f16_dpp v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0x04,0x0a,0x6a,0x01,0x77,0x39,0x05]
+v_mul_f16 v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_mul_f16_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0x04,0x0a,0x6a,0x01,0x77,0x39,0x05]
-v_mul_f16 v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0] fi:1
-// GFX11: v_mul_f16_dpp v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0x04,0x0a,0x6a,0x01,0x77,0x39,0x05]
+v_mul_f16 v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0] fi:1
+// GFX11: v_mul_f16_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0x04,0x0a,0x6a,0x01,0x77,0x39,0x05]
-v_mul_f16 v127, v127, v127 dpp8:[0,0,0,0,0,0,0,0] fi:0
-// GFX11: v_mul_f16_dpp v127, v127, v127 dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xfe,0xfe,0x6a,0x7f,0x00,0x00,0x00]
+v_mul_f16 v127.l, v127.l, v127.l dpp8:[0,0,0,0,0,0,0,0]
+// GFX11: v_mul_f16_dpp v127.l, v127.l, v127.l dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xfe,0xfe,0x6a,0x7f,0x00,0x00,0x00]
+
+v_mul_f16 v127.l, v127.l, v127.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_mul_f16_dpp v127.l, v127.l, v127.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0xfe,0xfe,0x6a,0x7f,0x77,0x39,0x05]
+
+v_mul_f16 v5.h, v1.h, v2.h dpp8:[7,6,5,4,3,2,1,0] fi:1
+// GFX11: v_mul_f16_dpp v5.h, v1.h, v2.h dpp8:[7,6,5,4,3,2,1,0] fi:1 ; encoding: [0xea,0x04,0x0b,0x6b,0x81,0x77,0x39,0x05]
+
+v_mul_f16 v127.h, v127.h, v127.h dpp8:[0,0,0,0,0,0,0,0] fi:0
+// GFX11: v_mul_f16_dpp v127.h, v127.h, v127.h dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xe9,0xfe,0xff,0x6b,0xff,0x00,0x00,0x00]
v_mul_f32 v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0]
// GFX11: v_mul_f32_dpp v5, v1, v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xe9,0x04,0x0a,0x10,0x01,0x77,0x39,0x05]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop2_t16_err.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop2_t16_err.s
index e5504074079e50..6b2e72e4c1146f 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop2_t16_err.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop2_t16_err.s
@@ -227,32 +227,59 @@ v_min_f16_e32 v5, v1, v255
v_min_f16_e32 v5, v255, v2
// GFX11: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
-v_mul_f16_dpp v255, v1, v2 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
+v_mul_f16_dpp v255.h, v1.h, v2.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
-v_mul_f16_dpp v255, v1, v2 quad_perm:[3,2,1,0]
-// GFX11: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
+v_mul_f16_dpp v255.h, v1.h, v2.h quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
-v_mul_f16_dpp v5, v1, v255 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
+v_mul_f16_dpp v255.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
-v_mul_f16_dpp v5, v1, v255 quad_perm:[3,2,1,0]
-// GFX11: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
+v_mul_f16_dpp v255.l, v1.l, v2.l quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
-v_mul_f16_dpp v5, v255, v2 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
+v_mul_f16_dpp v5.h, v1.h, v255.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:27: error: invalid operand for instruction
-v_mul_f16_dpp v5, v255, v2 quad_perm:[3,2,1,0]
-// GFX11: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
+v_mul_f16_dpp v5.h, v1.h, v255.h quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:27: error: invalid operand for instruction
-v_mul_f16_e32 v255, v1, v2
-// GFX11: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
+v_mul_f16_dpp v5.h, v255.h, v2.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
-v_mul_f16_e32 v5, v1, v255
-// GFX11: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
+v_mul_f16_dpp v5.h, v255.h, v2.h quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
-v_mul_f16_e32 v5, v255, v2
-// GFX11: :[[@LINE-1]]:1: error: operands are not valid for this GPU or mode
+v_mul_f16_dpp v5.l, v1.l, v255.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:27: error: invalid operand for instruction
+
+v_mul_f16_dpp v5.l, v1.l, v255.l quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:27: error: invalid operand for instruction
+
+v_mul_f16_dpp v5.l, v255.l, v2.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_mul_f16_dpp v5.l, v255.l, v2.l quad_perm:[3,2,1,0]
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_mul_f16_e32 v255.h, v1.h, v2.h
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_mul_f16_e32 v255.l, v1.l, v2.l
+// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
+
+v_mul_f16_e32 v5.h, v1.h, v255.h
+// GFX11: :[[@LINE-1]]:27: error: invalid operand for instruction
+
+v_mul_f16_e32 v5.h, v255.h, v2.h
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
+
+v_mul_f16_e32 v5.l, v1.l, v255.l
+// GFX11: :[[@LINE-1]]:27: error: invalid operand for instruction
+
+v_mul_f16_e32 v5.l, v255.l, v2.l
+// GFX11: :[[@LINE-1]]:21: error: invalid operand for instruction
v_sub_f16_dpp v255.h, v1.h, v2.h dpp8:[7,6,5,4,3,2,1,0]
// GFX11: :[[@LINE-1]]:15: error: invalid operand for instruction
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop2_t16_promote.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop2_t16_promote.s
index 63394502ec14ed..5a87ee451272fc 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop2_t16_promote.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop2_t16_promote.s
@@ -146,32 +146,59 @@ v_min_f16 v5, v255, v2 dpp8:[7,6,5,4,3,2,1,0]
v_min_f16 v5, v255, v2 quad_perm:[3,2,1,0]
// GFX11: v_min_f16_e64_dpp v5, v255, v2 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x3a,0xd5,0xfa,0x04,0x02,0x00,0xff,0x1b,0x00,0xff]
-v_mul_f16 v255, v1, v2
-// GFX11: v_mul_f16_e64 v255, v1, v2 ; encoding: [0xff,0x00,0x35,0xd5,0x01,0x05,0x02,0x00]
+v_mul_f16 v255.h, v1.h, v2.h
+// GFX11: v_mul_f16_e64 v255.h, v1.h, v2.h op_sel:[1,1,1] ; encoding: [0xff,0x58,0x35,0xd5,0x01,0x05,0x02,0x00]
-v_mul_f16 v255, v1, v2 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_mul_f16_e64_dpp v255, v1, v2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x00,0x35,0xd5,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05]
+v_mul_f16 v255.h, v1.h, v2.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_mul_f16_e64_dpp v255.h, v1.h, v2.h op_sel:[1,1,1] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0xff,0x58,0x35,0xd5,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05]
-v_mul_f16 v255, v1, v2 quad_perm:[3,2,1,0]
-// GFX11: v_mul_f16_e64_dpp v255, v1, v2 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x00,0x35,0xd5,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
+v_mul_f16 v255.h, v1.h, v2.h quad_perm:[3,2,1,0]
+// GFX11: v_mul_f16_e64_dpp v255.h, v1.h, v2.h op_sel:[1,1,1] quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0xff,0x58,0x35,0xd5,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
-v_mul_f16 v5, v1, v255
-// GFX11: v_mul_f16_e64 v5, v1, v255 ; encoding: [0x05,0x00,0x35,0xd5,0x01,0xff,0x03,0x00]
+v_mul_f16 v255.l, v1.l, v2.l
+// GFX11: v_mul_f16_e64 v255.l, v1.l, v2.l ; encoding: [0xff,0x00,0x35,0xd5,0x01,0x05,0x02,0x00]
-v_mul_f16 v5, v1, v255 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_mul_f16_e64_dpp v5, v1, v255 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x35,0xd5,0xe9,0xfe,0x03,0x00,0x01,0x77,0x39,0x05]
+v_mul_f16 v2...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/119314
More information about the llvm-commits
mailing list